Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- README.md +45 -0
- chat_template.jinja +137 -0
- config.json +48 -0
- generation_config.json +11 -0
- model-00002-of-00046.safetensors +3 -0
- model-00003-of-00046.safetensors +3 -0
- model-00004-of-00046.safetensors +3 -0
- model-00006-of-00046.safetensors +3 -0
- model-00007-of-00046.safetensors +3 -0
- model-00008-of-00046.safetensors +3 -0
- model-00009-of-00046.safetensors +3 -0
- model-00010-of-00046.safetensors +3 -0
- model-00011-of-00046.safetensors +3 -0
- model-00012-of-00046.safetensors +3 -0
- model-00013-of-00046.safetensors +3 -0
- model-00014-of-00046.safetensors +3 -0
- model-00015-of-00046.safetensors +3 -0
- model-00016-of-00046.safetensors +3 -0
- model-00017-of-00046.safetensors +3 -0
- model-00018-of-00046.safetensors +3 -0
- model-00019-of-00046.safetensors +3 -0
- model-00020-of-00046.safetensors +3 -0
- model-00022-of-00046.safetensors +3 -0
- model-00023-of-00046.safetensors +3 -0
- model-00024-of-00046.safetensors +3 -0
- model-00025-of-00046.safetensors +3 -0
- model-00026-of-00046.safetensors +3 -0
- model-00027-of-00046.safetensors +3 -0
- model-00028-of-00046.safetensors +3 -0
- model-00029-of-00046.safetensors +3 -0
- model-00030-of-00046.safetensors +3 -0
- model-00031-of-00046.safetensors +3 -0
- model-00032-of-00046.safetensors +3 -0
- model-00033-of-00046.safetensors +3 -0
- model-00034-of-00046.safetensors +3 -0
- model-00035-of-00046.safetensors +3 -0
- model-00036-of-00046.safetensors +3 -0
- model-00037-of-00046.safetensors +3 -0
- model-00038-of-00046.safetensors +3 -0
- model-00039-of-00046.safetensors +3 -0
- model-00040-of-00046.safetensors +3 -0
- model-00042-of-00046.safetensors +3 -0
- model-00043-of-00046.safetensors +3 -0
- model-00044-of-00046.safetensors +3 -0
- model-00045-of-00046.safetensors +3 -0
- model-00046-of-00046.safetensors +3 -0
- model.safetensors.index.json +788 -0
- special_tokens_map.json +40 -0
- tokenizer.json +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: mlx
|
| 3 |
+
tags:
|
| 4 |
+
- prime-rl
|
| 5 |
+
- verifiers
|
| 6 |
+
- prime-intellect
|
| 7 |
+
- reinforcement-learning
|
| 8 |
+
- reasoning
|
| 9 |
+
- agentic
|
| 10 |
+
- mixture-of-experts
|
| 11 |
+
- mlx
|
| 12 |
+
license: mit
|
| 13 |
+
language:
|
| 14 |
+
- en
|
| 15 |
+
base_model: PrimeIntellect/INTELLECT-3
|
| 16 |
+
pipeline_tag: text-generation
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# mlx-community/INTELLECT-3-bf16
|
| 20 |
+
|
| 21 |
+
This model [mlx-community/INTELLECT-3-bf16](https://huggingface.co/mlx-community/INTELLECT-3-bf16) was
|
| 22 |
+
converted to MLX format from [PrimeIntellect/INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3)
|
| 23 |
+
using mlx-lm version **0.28.3**.
|
| 24 |
+
|
| 25 |
+
## Use with mlx
|
| 26 |
+
|
| 27 |
+
```bash
|
| 28 |
+
pip install mlx-lm
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
```python
|
| 32 |
+
from mlx_lm import load, generate
|
| 33 |
+
|
| 34 |
+
model, tokenizer = load("mlx-community/INTELLECT-3-bf16")
|
| 35 |
+
|
| 36 |
+
prompt = "hello"
|
| 37 |
+
|
| 38 |
+
if tokenizer.chat_template is not None:
|
| 39 |
+
messages = [{"role": "user", "content": prompt}]
|
| 40 |
+
prompt = tokenizer.apply_chat_template(
|
| 41 |
+
messages, add_generation_prompt=True
|
| 42 |
+
)
|
| 43 |
+
|
| 44 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 45 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% macro render_extra_keys(json_dict, handled_keys) %}
|
| 2 |
+
{%- if json_dict is mapping %}
|
| 3 |
+
{%- for json_key in json_dict if json_key not in handled_keys %}
|
| 4 |
+
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
|
| 5 |
+
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
| 8 |
+
{%- endif %}
|
| 9 |
+
{%- endfor %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{% endmacro %}
|
| 12 |
+
|
| 13 |
+
{%- if messages[0]["role"] == "system" %}
|
| 14 |
+
{%- set system_message = messages[0]["content"] %}
|
| 15 |
+
{%- set loop_messages = messages[1:] %}
|
| 16 |
+
{%- else %}
|
| 17 |
+
{%- set loop_messages = messages %}
|
| 18 |
+
{%- endif %}
|
| 19 |
+
|
| 20 |
+
{%- if not tools is defined %}
|
| 21 |
+
{%- set tools = [] %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
|
| 24 |
+
{%- if system_message is defined %}
|
| 25 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 28 |
+
{{- "<|im_start|>system\nYou are INTELLECT-3, a helpful assistant developed by Prime Intellect, that can interact with a computer to solve tasks." }}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 32 |
+
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
|
| 33 |
+
{{- "<tools>" }}
|
| 34 |
+
{%- for tool in tools %}
|
| 35 |
+
{%- if tool.function is defined %}
|
| 36 |
+
{%- set tool = tool.function %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
| 39 |
+
{%- if tool.description is defined %}
|
| 40 |
+
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- '\n<parameters>' }}
|
| 43 |
+
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
| 44 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 45 |
+
{{- '\n<parameter>' }}
|
| 46 |
+
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
| 47 |
+
{%- if param_fields.type is defined %}
|
| 48 |
+
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- if param_fields.description is defined %}
|
| 51 |
+
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- set handled_keys = ['name', 'type', 'description'] %}
|
| 54 |
+
{{- render_extra_keys(param_fields, handled_keys) }}
|
| 55 |
+
{{- '\n</parameter>' }}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{% set handled_keys = ['type', 'properties'] %}
|
| 59 |
+
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
| 60 |
+
{{- '\n</parameters>' }}
|
| 61 |
+
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
| 62 |
+
{{- render_extra_keys(tool, handled_keys) }}
|
| 63 |
+
{{- '\n</function>' }}
|
| 64 |
+
{%- endfor %}
|
| 65 |
+
{{- "\n</tools>" }}
|
| 66 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- if system_message is defined %}
|
| 69 |
+
{{- '<|im_end|>\n' }}
|
| 70 |
+
{%- else %}
|
| 71 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 72 |
+
{{- '<|im_end|>\n' }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- for message in loop_messages %}
|
| 76 |
+
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 77 |
+
{{- '<|im_start|>' + message.role }}
|
| 78 |
+
{%- if message.content is defined and message.content is string %}
|
| 79 |
+
{%- if message.reasoning_content is defined -%}
|
| 80 |
+
{%- if message.reasoning_content -%}
|
| 81 |
+
{{ '\n<think>' + message.reasoning_content.strip() + '</think>' }}
|
| 82 |
+
{%- else -%}
|
| 83 |
+
{{ '\n<think></think>' }}
|
| 84 |
+
{%- endif -%}
|
| 85 |
+
{%- endif -%}
|
| 86 |
+
{{- '\n' + message.content | trim + '\n' }}
|
| 87 |
+
{%- endif %}
|
| 88 |
+
{%- for tool_call in message.tool_calls %}
|
| 89 |
+
{%- if tool_call.function is defined %}
|
| 90 |
+
{%- set tool_call = tool_call.function %}
|
| 91 |
+
{%- endif %}
|
| 92 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 93 |
+
{%- if tool_call.arguments is defined %}
|
| 94 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 95 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 96 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 97 |
+
{{- args_value }}
|
| 98 |
+
{{- '\n</parameter>\n' }}
|
| 99 |
+
{%- endfor %}
|
| 100 |
+
{%- endif %}
|
| 101 |
+
{{- '</function>\n</tool_call>' }}
|
| 102 |
+
{%- endfor %}
|
| 103 |
+
{{- '<|im_end|>\n' }}
|
| 104 |
+
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
|
| 105 |
+
{{- '<|im_start|>' + message.role }}
|
| 106 |
+
{%- if message.role == "assistant" and message.reasoning_content is defined %}
|
| 107 |
+
{%- if message.reasoning_content -%}
|
| 108 |
+
{{ '\n<think>' + message.reasoning_content.strip() + '</think>' }}
|
| 109 |
+
{%- else -%}
|
| 110 |
+
{{ '\n<think></think>' }}
|
| 111 |
+
{%- endif -%}
|
| 112 |
+
{%- if message.content.strip() -%}
|
| 113 |
+
{{ '\n' + message.content.strip() }}
|
| 114 |
+
{%- endif -%}
|
| 115 |
+
{%- else %}
|
| 116 |
+
{{- '\n' + message.content }}
|
| 117 |
+
{%- endif %}
|
| 118 |
+
{{- '<|im_end|>' + '\n' }}
|
| 119 |
+
{%- elif message.role == "tool" %}
|
| 120 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 121 |
+
{{- '<|im_start|>user\n' }}
|
| 122 |
+
{%- endif %}
|
| 123 |
+
{{- '<tool_response>\n' }}
|
| 124 |
+
{{- message.content }}
|
| 125 |
+
{{- '\n</tool_response>\n' }}
|
| 126 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 127 |
+
{{- '<|im_end|>\n' }}
|
| 128 |
+
{%- elif loop.last %}
|
| 129 |
+
{{- '<|im_end|>\n' }}
|
| 130 |
+
{%- endif %}
|
| 131 |
+
{%- else %}
|
| 132 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 133 |
+
{%- endif %}
|
| 134 |
+
{%- endfor %}
|
| 135 |
+
{%- if add_generation_prompt %}
|
| 136 |
+
{{- '<|im_start|>assistant\n<think>' }}
|
| 137 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Glm4MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_glm4_moe.Glm4MoeConfig",
|
| 9 |
+
"AutoModel": "modeling_glm4_moe.Glm4MoeModel",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_glm4_moe.Glm4MoeForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"dtype": "bfloat16",
|
| 13 |
+
"eos_token_id": [
|
| 14 |
+
151334,
|
| 15 |
+
151329
|
| 16 |
+
],
|
| 17 |
+
"first_k_dense_replace": 1,
|
| 18 |
+
"head_dim": 128,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 4096,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 10944,
|
| 23 |
+
"max_position_embeddings": 131072,
|
| 24 |
+
"model_type": "glm4_moe",
|
| 25 |
+
"moe_intermediate_size": 1408,
|
| 26 |
+
"n_group": 1,
|
| 27 |
+
"n_routed_experts": 128,
|
| 28 |
+
"n_shared_experts": 1,
|
| 29 |
+
"norm_topk_prob": true,
|
| 30 |
+
"num_attention_heads": 96,
|
| 31 |
+
"num_experts_per_tok": 8,
|
| 32 |
+
"num_hidden_layers": 46,
|
| 33 |
+
"num_key_value_heads": 8,
|
| 34 |
+
"num_nextn_predict_layers": 1,
|
| 35 |
+
"pad_token_id": 151329,
|
| 36 |
+
"partial_rotary_factor": 0.5,
|
| 37 |
+
"rms_norm_eps": 1e-05,
|
| 38 |
+
"rope_scaling": null,
|
| 39 |
+
"rope_theta": 1000000,
|
| 40 |
+
"routed_scaling_factor": 1.0,
|
| 41 |
+
"tie_word_embeddings": false,
|
| 42 |
+
"topk_group": 1,
|
| 43 |
+
"transformers_version": "4.56.1",
|
| 44 |
+
"use_cache": false,
|
| 45 |
+
"use_grouped_mm": true,
|
| 46 |
+
"use_qk_norm": false,
|
| 47 |
+
"vocab_size": 151552
|
| 48 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151334,
|
| 5 |
+
151329
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151329,
|
| 8 |
+
"transformers_version": "4.56.1",
|
| 9 |
+
"use_cache": false,
|
| 10 |
+
"temperature": 0.6
|
| 11 |
+
}
|
model-00002-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56935253fbb17738747b142646a325ff7a3a23de556a6054e3ce947320d1de72
|
| 3 |
+
size 4682988045
|
model-00003-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de963fe19603d45fde93c950de966c827a27105a84ea43c9c560e978c02a39c7
|
| 3 |
+
size 4682988045
|
model-00004-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b0c0ebad3c4feaf48abbc93d367ac8aea3ab2bed69381873f369311d01f16b0
|
| 3 |
+
size 4682988045
|
model-00006-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7613f6a1245e2f6f20b9a4e7716a2bdc4496149cd74dbdfa426d2ff1bbbb8bcc
|
| 3 |
+
size 4682988041
|
model-00007-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92d273678d9a330d8025f571d8e9ae5e68aec3f51171d4edb335a7382b022b28
|
| 3 |
+
size 4682988045
|
model-00008-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f6a2506892cd9ff1969994b12cc04ed78c2f003383b5ab041d8efcdbbba66ac
|
| 3 |
+
size 4682988045
|
model-00009-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f580fbda88c304493b99dce3e7aa1e876dccc8b0d9da47cf85620eb65a5a986
|
| 3 |
+
size 4682988043
|
model-00010-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaa1e402eabbc1000e696d42e6bd49032643da893d028fc0eb0fe4c310f6db76
|
| 3 |
+
size 4682988054
|
model-00011-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a105b9333352c1e3e33f99fad94bceec6cf96007d39dc8e2293ae9e22e196876
|
| 3 |
+
size 4682988062
|
model-00012-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7965c7e07f296d5d1467c5f57ddb3ed7e8e726a9d672f2808990d7db620ae886
|
| 3 |
+
size 4682988062
|
model-00013-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:371e66dcfec48be5b9973c079310408d8d50679dec0c572e3590037f69c44193
|
| 3 |
+
size 4682988058
|
model-00014-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d72eb59515d84d6e3098543e0954c88849db48a828a8860f7d8516807bebb747
|
| 3 |
+
size 4682988062
|
model-00015-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a6320c30c1530687309e284d8e6a300b286fd405ad6a17d76b5be73dfecb246
|
| 3 |
+
size 4682988062
|
model-00016-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e2ec969d47994d4aa885cd171cee675c93846c1c8f4891b97b869496b023fbf
|
| 3 |
+
size 4682988062
|
model-00017-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5da7fb7406a05b4e39e29f60bd3f1513f7429db3a080fcf45546f0d3843cba3b
|
| 3 |
+
size 4682988062
|
model-00018-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a79dbcb6ccbb30f8063043a6532ca328bed9691ad81ed7780521080033142d6f
|
| 3 |
+
size 4682988062
|
model-00019-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ffc268247b756c1cbe4a80414a5b7e6a52cf8fbf8325d46d3319bc051798016
|
| 3 |
+
size 4682988062
|
model-00020-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:569a7403c3d358c01cc70ed46efa3be0b27f92d406ec9bffd059a3d3ed18d165
|
| 3 |
+
size 4682988062
|
model-00022-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:552605f1085903e482e1944ae1231819b2c750c7bf35fca81da9ad89a2395cad
|
| 3 |
+
size 4682988062
|
model-00023-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b584d002fb4479e3d6034470fe2da48f3cdc2a16471fbeb0114cb9847d705df
|
| 3 |
+
size 4682988062
|
model-00024-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db64e11d41022cb70f7052726359c7ecb0a10a8764cd8f06b79896200d4f28d3
|
| 3 |
+
size 4682988062
|
model-00025-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cddbeee3c1a8c0c2b0055aadd716a9195174fc955aa84f1f302e572daa38f3b
|
| 3 |
+
size 4682988062
|
model-00026-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c3411d57caeb0a35f412ddb82abf7b3048a734875ca790cbbfbcca13149aecd
|
| 3 |
+
size 4682988062
|
model-00027-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c63a09bbff6d33a83ebb0549580dd12c997f824c22c5311c4587eab6a4f2ebd5
|
| 3 |
+
size 4682988062
|
model-00028-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9432acef7271b1603abc1ad957186b28c562a94b0b0b42ba6203c3728c32f3af
|
| 3 |
+
size 4682988062
|
model-00029-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e88608fa1a8a7b01fef1b5966a9f15c38b1b3509ac03b3a74636ea743957e203
|
| 3 |
+
size 4682988062
|
model-00030-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25b77f9bdeca85bc0a14d24976b4c5d19bd80a810961eceae420feb3065767e9
|
| 3 |
+
size 4682988062
|
model-00031-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30b58a6a04d0811c19e9796cf8df2f6fe04420bccad0980eaf35b8fe2c73f173
|
| 3 |
+
size 4682988062
|
model-00032-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6802339cf4221a44e536601e7a7015cff7c872890154b1ff214af88b7db17908
|
| 3 |
+
size 4682988062
|
model-00033-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2245dffd273b869b21203f389d79fa870cae63498dab757dea158cbc989f54f2
|
| 3 |
+
size 4682988062
|
model-00034-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b9998309678d97a46c4bbd2eac42a8b6053552bd4ed37f51a105f1b33c61ed6
|
| 3 |
+
size 4682988062
|
model-00035-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c41d8cbddb385eb30f2b8cbc895111c167a2ff660a2c3063a8bfcb0b5ea3d735
|
| 3 |
+
size 4682988062
|
model-00036-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7289867855a521d168afc87df11c81c26e6126f824d0ae00c06461024b79e5ae
|
| 3 |
+
size 4682988062
|
model-00037-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9ec21a92c992dc7600d32f74f76f5fbeeb527c0b130e3e6da1dd747558815b8
|
| 3 |
+
size 4682988062
|
model-00038-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d6bda1cdb0598c54340ac25889ad5d0b6baca3948dcd195a68fdbb3fd8eecae
|
| 3 |
+
size 4682988062
|
model-00039-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60348863c640ff16025919f58acc73742dc53a6cd954322b6979e53cce5a5691
|
| 3 |
+
size 4682988062
|
model-00040-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62dc5ddf08db50211f809b08a51cc6613bfc08e05d431ea6e36c2ce833057b52
|
| 3 |
+
size 4682988058
|
model-00042-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84600a0fa800a0be76a1f5f05d4ecfbcf27acb58a653dd83bbae4bd9b4623680
|
| 3 |
+
size 4682988062
|
model-00043-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6e71d85a049b2d0dcc9e768a39d87c493fb3d2b13e7840fd366f66363353818
|
| 3 |
+
size 4682988062
|
model-00044-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:892cc5acb2e01969116889ff5b38af955308036056efdee29e9e71b89c091a51
|
| 3 |
+
size 4682988062
|
model-00045-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1a215ffa1a130cddf2fd6938780cf464af70333a3eb413d7102f6f1672929b2
|
| 3 |
+
size 4682988062
|
model-00046-of-00046.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d8ee562d842542cfffc115c6ecdde9b3ef60e8ae97e4c15b9b91c25199ac5cf
|
| 3 |
+
size 2753586862
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,788 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 213704514048,
|
| 4 |
+
"total_parameters": 106852251264
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00046-of-00046.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00046.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00046.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00046.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00046.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00046.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00046.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00046.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00046.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00046.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00046.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00046.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00046.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00046.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00046.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate.e_score_correction_bias": "model-00002-of-00046.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate.weight": "model-00002-of-00046.safetensors",
|
| 24 |
+
"model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00046.safetensors",
|
| 25 |
+
"model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00046.safetensors",
|
| 26 |
+
"model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00046.safetensors",
|
| 27 |
+
"model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00002-of-00046.safetensors",
|
| 28 |
+
"model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00046.safetensors",
|
| 29 |
+
"model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00046.safetensors",
|
| 30 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00046.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00046.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00046.safetensors",
|
| 33 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00046.safetensors",
|
| 34 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00046.safetensors",
|
| 35 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00046.safetensors",
|
| 36 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00046.safetensors",
|
| 37 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00046.safetensors",
|
| 38 |
+
"model.layers.10.input_layernorm.weight": "model-00011-of-00046.safetensors",
|
| 39 |
+
"model.layers.10.mlp.gate.e_score_correction_bias": "model-00011-of-00046.safetensors",
|
| 40 |
+
"model.layers.10.mlp.gate.weight": "model-00011-of-00046.safetensors",
|
| 41 |
+
"model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00046.safetensors",
|
| 42 |
+
"model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00046.safetensors",
|
| 43 |
+
"model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00046.safetensors",
|
| 44 |
+
"model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00011-of-00046.safetensors",
|
| 45 |
+
"model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00046.safetensors",
|
| 46 |
+
"model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00010-of-00046.safetensors",
|
| 47 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00011-of-00046.safetensors",
|
| 48 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00010-of-00046.safetensors",
|
| 49 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00010-of-00046.safetensors",
|
| 50 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00010-of-00046.safetensors",
|
| 51 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00010-of-00046.safetensors",
|
| 52 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00010-of-00046.safetensors",
|
| 53 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00010-of-00046.safetensors",
|
| 54 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00010-of-00046.safetensors",
|
| 55 |
+
"model.layers.11.input_layernorm.weight": "model-00012-of-00046.safetensors",
|
| 56 |
+
"model.layers.11.mlp.gate.e_score_correction_bias": "model-00012-of-00046.safetensors",
|
| 57 |
+
"model.layers.11.mlp.gate.weight": "model-00012-of-00046.safetensors",
|
| 58 |
+
"model.layers.11.mlp.shared_experts.down_proj.weight": "model-00012-of-00046.safetensors",
|
| 59 |
+
"model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00012-of-00046.safetensors",
|
| 60 |
+
"model.layers.11.mlp.shared_experts.up_proj.weight": "model-00012-of-00046.safetensors",
|
| 61 |
+
"model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00012-of-00046.safetensors",
|
| 62 |
+
"model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00046.safetensors",
|
| 63 |
+
"model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00011-of-00046.safetensors",
|
| 64 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00012-of-00046.safetensors",
|
| 65 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00011-of-00046.safetensors",
|
| 66 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00011-of-00046.safetensors",
|
| 67 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00011-of-00046.safetensors",
|
| 68 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00011-of-00046.safetensors",
|
| 69 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00011-of-00046.safetensors",
|
| 70 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00011-of-00046.safetensors",
|
| 71 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00011-of-00046.safetensors",
|
| 72 |
+
"model.layers.12.input_layernorm.weight": "model-00013-of-00046.safetensors",
|
| 73 |
+
"model.layers.12.mlp.gate.e_score_correction_bias": "model-00013-of-00046.safetensors",
|
| 74 |
+
"model.layers.12.mlp.gate.weight": "model-00013-of-00046.safetensors",
|
| 75 |
+
"model.layers.12.mlp.shared_experts.down_proj.weight": "model-00013-of-00046.safetensors",
|
| 76 |
+
"model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00013-of-00046.safetensors",
|
| 77 |
+
"model.layers.12.mlp.shared_experts.up_proj.weight": "model-00013-of-00046.safetensors",
|
| 78 |
+
"model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00013-of-00046.safetensors",
|
| 79 |
+
"model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00046.safetensors",
|
| 80 |
+
"model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00012-of-00046.safetensors",
|
| 81 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00013-of-00046.safetensors",
|
| 82 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00012-of-00046.safetensors",
|
| 83 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00012-of-00046.safetensors",
|
| 84 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00012-of-00046.safetensors",
|
| 85 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00012-of-00046.safetensors",
|
| 86 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00012-of-00046.safetensors",
|
| 87 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00012-of-00046.safetensors",
|
| 88 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00012-of-00046.safetensors",
|
| 89 |
+
"model.layers.13.input_layernorm.weight": "model-00014-of-00046.safetensors",
|
| 90 |
+
"model.layers.13.mlp.gate.e_score_correction_bias": "model-00014-of-00046.safetensors",
|
| 91 |
+
"model.layers.13.mlp.gate.weight": "model-00014-of-00046.safetensors",
|
| 92 |
+
"model.layers.13.mlp.shared_experts.down_proj.weight": "model-00014-of-00046.safetensors",
|
| 93 |
+
"model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00014-of-00046.safetensors",
|
| 94 |
+
"model.layers.13.mlp.shared_experts.up_proj.weight": "model-00014-of-00046.safetensors",
|
| 95 |
+
"model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00014-of-00046.safetensors",
|
| 96 |
+
"model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00046.safetensors",
|
| 97 |
+
"model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00013-of-00046.safetensors",
|
| 98 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00014-of-00046.safetensors",
|
| 99 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00013-of-00046.safetensors",
|
| 100 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00013-of-00046.safetensors",
|
| 101 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00013-of-00046.safetensors",
|
| 102 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00013-of-00046.safetensors",
|
| 103 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00013-of-00046.safetensors",
|
| 104 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00013-of-00046.safetensors",
|
| 105 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00013-of-00046.safetensors",
|
| 106 |
+
"model.layers.14.input_layernorm.weight": "model-00015-of-00046.safetensors",
|
| 107 |
+
"model.layers.14.mlp.gate.e_score_correction_bias": "model-00015-of-00046.safetensors",
|
| 108 |
+
"model.layers.14.mlp.gate.weight": "model-00015-of-00046.safetensors",
|
| 109 |
+
"model.layers.14.mlp.shared_experts.down_proj.weight": "model-00015-of-00046.safetensors",
|
| 110 |
+
"model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00015-of-00046.safetensors",
|
| 111 |
+
"model.layers.14.mlp.shared_experts.up_proj.weight": "model-00015-of-00046.safetensors",
|
| 112 |
+
"model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00015-of-00046.safetensors",
|
| 113 |
+
"model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00046.safetensors",
|
| 114 |
+
"model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00014-of-00046.safetensors",
|
| 115 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00015-of-00046.safetensors",
|
| 116 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00014-of-00046.safetensors",
|
| 117 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00014-of-00046.safetensors",
|
| 118 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00014-of-00046.safetensors",
|
| 119 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00014-of-00046.safetensors",
|
| 120 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00014-of-00046.safetensors",
|
| 121 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00014-of-00046.safetensors",
|
| 122 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00014-of-00046.safetensors",
|
| 123 |
+
"model.layers.15.input_layernorm.weight": "model-00016-of-00046.safetensors",
|
| 124 |
+
"model.layers.15.mlp.gate.e_score_correction_bias": "model-00016-of-00046.safetensors",
|
| 125 |
+
"model.layers.15.mlp.gate.weight": "model-00016-of-00046.safetensors",
|
| 126 |
+
"model.layers.15.mlp.shared_experts.down_proj.weight": "model-00016-of-00046.safetensors",
|
| 127 |
+
"model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00016-of-00046.safetensors",
|
| 128 |
+
"model.layers.15.mlp.shared_experts.up_proj.weight": "model-00016-of-00046.safetensors",
|
| 129 |
+
"model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00016-of-00046.safetensors",
|
| 130 |
+
"model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00046.safetensors",
|
| 131 |
+
"model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00015-of-00046.safetensors",
|
| 132 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00016-of-00046.safetensors",
|
| 133 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00015-of-00046.safetensors",
|
| 134 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00015-of-00046.safetensors",
|
| 135 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00015-of-00046.safetensors",
|
| 136 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00015-of-00046.safetensors",
|
| 137 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00015-of-00046.safetensors",
|
| 138 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00015-of-00046.safetensors",
|
| 139 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00015-of-00046.safetensors",
|
| 140 |
+
"model.layers.16.input_layernorm.weight": "model-00017-of-00046.safetensors",
|
| 141 |
+
"model.layers.16.mlp.gate.e_score_correction_bias": "model-00017-of-00046.safetensors",
|
| 142 |
+
"model.layers.16.mlp.gate.weight": "model-00017-of-00046.safetensors",
|
| 143 |
+
"model.layers.16.mlp.shared_experts.down_proj.weight": "model-00017-of-00046.safetensors",
|
| 144 |
+
"model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00017-of-00046.safetensors",
|
| 145 |
+
"model.layers.16.mlp.shared_experts.up_proj.weight": "model-00017-of-00046.safetensors",
|
| 146 |
+
"model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00017-of-00046.safetensors",
|
| 147 |
+
"model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00046.safetensors",
|
| 148 |
+
"model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00016-of-00046.safetensors",
|
| 149 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00017-of-00046.safetensors",
|
| 150 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00016-of-00046.safetensors",
|
| 151 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00016-of-00046.safetensors",
|
| 152 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00016-of-00046.safetensors",
|
| 153 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00016-of-00046.safetensors",
|
| 154 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00016-of-00046.safetensors",
|
| 155 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00016-of-00046.safetensors",
|
| 156 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00016-of-00046.safetensors",
|
| 157 |
+
"model.layers.17.input_layernorm.weight": "model-00018-of-00046.safetensors",
|
| 158 |
+
"model.layers.17.mlp.gate.e_score_correction_bias": "model-00018-of-00046.safetensors",
|
| 159 |
+
"model.layers.17.mlp.gate.weight": "model-00018-of-00046.safetensors",
|
| 160 |
+
"model.layers.17.mlp.shared_experts.down_proj.weight": "model-00018-of-00046.safetensors",
|
| 161 |
+
"model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00018-of-00046.safetensors",
|
| 162 |
+
"model.layers.17.mlp.shared_experts.up_proj.weight": "model-00018-of-00046.safetensors",
|
| 163 |
+
"model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00018-of-00046.safetensors",
|
| 164 |
+
"model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00046.safetensors",
|
| 165 |
+
"model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00017-of-00046.safetensors",
|
| 166 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00018-of-00046.safetensors",
|
| 167 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00017-of-00046.safetensors",
|
| 168 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00017-of-00046.safetensors",
|
| 169 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00017-of-00046.safetensors",
|
| 170 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00017-of-00046.safetensors",
|
| 171 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00017-of-00046.safetensors",
|
| 172 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00017-of-00046.safetensors",
|
| 173 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00017-of-00046.safetensors",
|
| 174 |
+
"model.layers.18.input_layernorm.weight": "model-00019-of-00046.safetensors",
|
| 175 |
+
"model.layers.18.mlp.gate.e_score_correction_bias": "model-00019-of-00046.safetensors",
|
| 176 |
+
"model.layers.18.mlp.gate.weight": "model-00019-of-00046.safetensors",
|
| 177 |
+
"model.layers.18.mlp.shared_experts.down_proj.weight": "model-00019-of-00046.safetensors",
|
| 178 |
+
"model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00019-of-00046.safetensors",
|
| 179 |
+
"model.layers.18.mlp.shared_experts.up_proj.weight": "model-00019-of-00046.safetensors",
|
| 180 |
+
"model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00019-of-00046.safetensors",
|
| 181 |
+
"model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00046.safetensors",
|
| 182 |
+
"model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00018-of-00046.safetensors",
|
| 183 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00019-of-00046.safetensors",
|
| 184 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00018-of-00046.safetensors",
|
| 185 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00018-of-00046.safetensors",
|
| 186 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00018-of-00046.safetensors",
|
| 187 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00018-of-00046.safetensors",
|
| 188 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00018-of-00046.safetensors",
|
| 189 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00018-of-00046.safetensors",
|
| 190 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00018-of-00046.safetensors",
|
| 191 |
+
"model.layers.19.input_layernorm.weight": "model-00020-of-00046.safetensors",
|
| 192 |
+
"model.layers.19.mlp.gate.e_score_correction_bias": "model-00020-of-00046.safetensors",
|
| 193 |
+
"model.layers.19.mlp.gate.weight": "model-00020-of-00046.safetensors",
|
| 194 |
+
"model.layers.19.mlp.shared_experts.down_proj.weight": "model-00020-of-00046.safetensors",
|
| 195 |
+
"model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00020-of-00046.safetensors",
|
| 196 |
+
"model.layers.19.mlp.shared_experts.up_proj.weight": "model-00020-of-00046.safetensors",
|
| 197 |
+
"model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00020-of-00046.safetensors",
|
| 198 |
+
"model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00046.safetensors",
|
| 199 |
+
"model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00019-of-00046.safetensors",
|
| 200 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00020-of-00046.safetensors",
|
| 201 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00019-of-00046.safetensors",
|
| 202 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00019-of-00046.safetensors",
|
| 203 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00019-of-00046.safetensors",
|
| 204 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00019-of-00046.safetensors",
|
| 205 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00019-of-00046.safetensors",
|
| 206 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00019-of-00046.safetensors",
|
| 207 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00019-of-00046.safetensors",
|
| 208 |
+
"model.layers.2.input_layernorm.weight": "model-00003-of-00046.safetensors",
|
| 209 |
+
"model.layers.2.mlp.gate.e_score_correction_bias": "model-00003-of-00046.safetensors",
|
| 210 |
+
"model.layers.2.mlp.gate.weight": "model-00003-of-00046.safetensors",
|
| 211 |
+
"model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00046.safetensors",
|
| 212 |
+
"model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00046.safetensors",
|
| 213 |
+
"model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00046.safetensors",
|
| 214 |
+
"model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00003-of-00046.safetensors",
|
| 215 |
+
"model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00046.safetensors",
|
| 216 |
+
"model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00002-of-00046.safetensors",
|
| 217 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00046.safetensors",
|
| 218 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00046.safetensors",
|
| 219 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00046.safetensors",
|
| 220 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00046.safetensors",
|
| 221 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00046.safetensors",
|
| 222 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00046.safetensors",
|
| 223 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00046.safetensors",
|
| 224 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00046.safetensors",
|
| 225 |
+
"model.layers.20.input_layernorm.weight": "model-00021-of-00046.safetensors",
|
| 226 |
+
"model.layers.20.mlp.gate.e_score_correction_bias": "model-00021-of-00046.safetensors",
|
| 227 |
+
"model.layers.20.mlp.gate.weight": "model-00021-of-00046.safetensors",
|
| 228 |
+
"model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00046.safetensors",
|
| 229 |
+
"model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00021-of-00046.safetensors",
|
| 230 |
+
"model.layers.20.mlp.shared_experts.up_proj.weight": "model-00021-of-00046.safetensors",
|
| 231 |
+
"model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00021-of-00046.safetensors",
|
| 232 |
+
"model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00046.safetensors",
|
| 233 |
+
"model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00020-of-00046.safetensors",
|
| 234 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00021-of-00046.safetensors",
|
| 235 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00020-of-00046.safetensors",
|
| 236 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00020-of-00046.safetensors",
|
| 237 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00020-of-00046.safetensors",
|
| 238 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00020-of-00046.safetensors",
|
| 239 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00020-of-00046.safetensors",
|
| 240 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00020-of-00046.safetensors",
|
| 241 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00020-of-00046.safetensors",
|
| 242 |
+
"model.layers.21.input_layernorm.weight": "model-00022-of-00046.safetensors",
|
| 243 |
+
"model.layers.21.mlp.gate.e_score_correction_bias": "model-00022-of-00046.safetensors",
|
| 244 |
+
"model.layers.21.mlp.gate.weight": "model-00022-of-00046.safetensors",
|
| 245 |
+
"model.layers.21.mlp.shared_experts.down_proj.weight": "model-00022-of-00046.safetensors",
|
| 246 |
+
"model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00022-of-00046.safetensors",
|
| 247 |
+
"model.layers.21.mlp.shared_experts.up_proj.weight": "model-00022-of-00046.safetensors",
|
| 248 |
+
"model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00022-of-00046.safetensors",
|
| 249 |
+
"model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00046.safetensors",
|
| 250 |
+
"model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00021-of-00046.safetensors",
|
| 251 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00022-of-00046.safetensors",
|
| 252 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00021-of-00046.safetensors",
|
| 253 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00021-of-00046.safetensors",
|
| 254 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00021-of-00046.safetensors",
|
| 255 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00021-of-00046.safetensors",
|
| 256 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00021-of-00046.safetensors",
|
| 257 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00021-of-00046.safetensors",
|
| 258 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00021-of-00046.safetensors",
|
| 259 |
+
"model.layers.22.input_layernorm.weight": "model-00023-of-00046.safetensors",
|
| 260 |
+
"model.layers.22.mlp.gate.e_score_correction_bias": "model-00023-of-00046.safetensors",
|
| 261 |
+
"model.layers.22.mlp.gate.weight": "model-00023-of-00046.safetensors",
|
| 262 |
+
"model.layers.22.mlp.shared_experts.down_proj.weight": "model-00023-of-00046.safetensors",
|
| 263 |
+
"model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00023-of-00046.safetensors",
|
| 264 |
+
"model.layers.22.mlp.shared_experts.up_proj.weight": "model-00023-of-00046.safetensors",
|
| 265 |
+
"model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00023-of-00046.safetensors",
|
| 266 |
+
"model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00046.safetensors",
|
| 267 |
+
"model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00022-of-00046.safetensors",
|
| 268 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00023-of-00046.safetensors",
|
| 269 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00022-of-00046.safetensors",
|
| 270 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00022-of-00046.safetensors",
|
| 271 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00022-of-00046.safetensors",
|
| 272 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00022-of-00046.safetensors",
|
| 273 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00022-of-00046.safetensors",
|
| 274 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00022-of-00046.safetensors",
|
| 275 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00022-of-00046.safetensors",
|
| 276 |
+
"model.layers.23.input_layernorm.weight": "model-00024-of-00046.safetensors",
|
| 277 |
+
"model.layers.23.mlp.gate.e_score_correction_bias": "model-00024-of-00046.safetensors",
|
| 278 |
+
"model.layers.23.mlp.gate.weight": "model-00024-of-00046.safetensors",
|
| 279 |
+
"model.layers.23.mlp.shared_experts.down_proj.weight": "model-00024-of-00046.safetensors",
|
| 280 |
+
"model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00024-of-00046.safetensors",
|
| 281 |
+
"model.layers.23.mlp.shared_experts.up_proj.weight": "model-00024-of-00046.safetensors",
|
| 282 |
+
"model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00024-of-00046.safetensors",
|
| 283 |
+
"model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00046.safetensors",
|
| 284 |
+
"model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00023-of-00046.safetensors",
|
| 285 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00024-of-00046.safetensors",
|
| 286 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00023-of-00046.safetensors",
|
| 287 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00023-of-00046.safetensors",
|
| 288 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00023-of-00046.safetensors",
|
| 289 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00023-of-00046.safetensors",
|
| 290 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00023-of-00046.safetensors",
|
| 291 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00023-of-00046.safetensors",
|
| 292 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00023-of-00046.safetensors",
|
| 293 |
+
"model.layers.24.input_layernorm.weight": "model-00025-of-00046.safetensors",
|
| 294 |
+
"model.layers.24.mlp.gate.e_score_correction_bias": "model-00025-of-00046.safetensors",
|
| 295 |
+
"model.layers.24.mlp.gate.weight": "model-00025-of-00046.safetensors",
|
| 296 |
+
"model.layers.24.mlp.shared_experts.down_proj.weight": "model-00025-of-00046.safetensors",
|
| 297 |
+
"model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00025-of-00046.safetensors",
|
| 298 |
+
"model.layers.24.mlp.shared_experts.up_proj.weight": "model-00025-of-00046.safetensors",
|
| 299 |
+
"model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00025-of-00046.safetensors",
|
| 300 |
+
"model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00046.safetensors",
|
| 301 |
+
"model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00024-of-00046.safetensors",
|
| 302 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00025-of-00046.safetensors",
|
| 303 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00024-of-00046.safetensors",
|
| 304 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00024-of-00046.safetensors",
|
| 305 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00024-of-00046.safetensors",
|
| 306 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00024-of-00046.safetensors",
|
| 307 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00024-of-00046.safetensors",
|
| 308 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00024-of-00046.safetensors",
|
| 309 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00024-of-00046.safetensors",
|
| 310 |
+
"model.layers.25.input_layernorm.weight": "model-00026-of-00046.safetensors",
|
| 311 |
+
"model.layers.25.mlp.gate.e_score_correction_bias": "model-00026-of-00046.safetensors",
|
| 312 |
+
"model.layers.25.mlp.gate.weight": "model-00026-of-00046.safetensors",
|
| 313 |
+
"model.layers.25.mlp.shared_experts.down_proj.weight": "model-00026-of-00046.safetensors",
|
| 314 |
+
"model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00026-of-00046.safetensors",
|
| 315 |
+
"model.layers.25.mlp.shared_experts.up_proj.weight": "model-00026-of-00046.safetensors",
|
| 316 |
+
"model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00026-of-00046.safetensors",
|
| 317 |
+
"model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00046.safetensors",
|
| 318 |
+
"model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00025-of-00046.safetensors",
|
| 319 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00026-of-00046.safetensors",
|
| 320 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00025-of-00046.safetensors",
|
| 321 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00025-of-00046.safetensors",
|
| 322 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00025-of-00046.safetensors",
|
| 323 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00025-of-00046.safetensors",
|
| 324 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00025-of-00046.safetensors",
|
| 325 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00025-of-00046.safetensors",
|
| 326 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00025-of-00046.safetensors",
|
| 327 |
+
"model.layers.26.input_layernorm.weight": "model-00027-of-00046.safetensors",
|
| 328 |
+
"model.layers.26.mlp.gate.e_score_correction_bias": "model-00027-of-00046.safetensors",
|
| 329 |
+
"model.layers.26.mlp.gate.weight": "model-00027-of-00046.safetensors",
|
| 330 |
+
"model.layers.26.mlp.shared_experts.down_proj.weight": "model-00027-of-00046.safetensors",
|
| 331 |
+
"model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00027-of-00046.safetensors",
|
| 332 |
+
"model.layers.26.mlp.shared_experts.up_proj.weight": "model-00027-of-00046.safetensors",
|
| 333 |
+
"model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00027-of-00046.safetensors",
|
| 334 |
+
"model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00046.safetensors",
|
| 335 |
+
"model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00026-of-00046.safetensors",
|
| 336 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00027-of-00046.safetensors",
|
| 337 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00026-of-00046.safetensors",
|
| 338 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00026-of-00046.safetensors",
|
| 339 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00026-of-00046.safetensors",
|
| 340 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00026-of-00046.safetensors",
|
| 341 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00026-of-00046.safetensors",
|
| 342 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00026-of-00046.safetensors",
|
| 343 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00026-of-00046.safetensors",
|
| 344 |
+
"model.layers.27.input_layernorm.weight": "model-00028-of-00046.safetensors",
|
| 345 |
+
"model.layers.27.mlp.gate.e_score_correction_bias": "model-00028-of-00046.safetensors",
|
| 346 |
+
"model.layers.27.mlp.gate.weight": "model-00028-of-00046.safetensors",
|
| 347 |
+
"model.layers.27.mlp.shared_experts.down_proj.weight": "model-00028-of-00046.safetensors",
|
| 348 |
+
"model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00028-of-00046.safetensors",
|
| 349 |
+
"model.layers.27.mlp.shared_experts.up_proj.weight": "model-00028-of-00046.safetensors",
|
| 350 |
+
"model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00028-of-00046.safetensors",
|
| 351 |
+
"model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00046.safetensors",
|
| 352 |
+
"model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00027-of-00046.safetensors",
|
| 353 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00028-of-00046.safetensors",
|
| 354 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00027-of-00046.safetensors",
|
| 355 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00027-of-00046.safetensors",
|
| 356 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00027-of-00046.safetensors",
|
| 357 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00027-of-00046.safetensors",
|
| 358 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00027-of-00046.safetensors",
|
| 359 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00027-of-00046.safetensors",
|
| 360 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00027-of-00046.safetensors",
|
| 361 |
+
"model.layers.28.input_layernorm.weight": "model-00029-of-00046.safetensors",
|
| 362 |
+
"model.layers.28.mlp.gate.e_score_correction_bias": "model-00029-of-00046.safetensors",
|
| 363 |
+
"model.layers.28.mlp.gate.weight": "model-00029-of-00046.safetensors",
|
| 364 |
+
"model.layers.28.mlp.shared_experts.down_proj.weight": "model-00029-of-00046.safetensors",
|
| 365 |
+
"model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00029-of-00046.safetensors",
|
| 366 |
+
"model.layers.28.mlp.shared_experts.up_proj.weight": "model-00029-of-00046.safetensors",
|
| 367 |
+
"model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00029-of-00046.safetensors",
|
| 368 |
+
"model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00028-of-00046.safetensors",
|
| 369 |
+
"model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00028-of-00046.safetensors",
|
| 370 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00029-of-00046.safetensors",
|
| 371 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00028-of-00046.safetensors",
|
| 372 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00028-of-00046.safetensors",
|
| 373 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00028-of-00046.safetensors",
|
| 374 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00028-of-00046.safetensors",
|
| 375 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00028-of-00046.safetensors",
|
| 376 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00028-of-00046.safetensors",
|
| 377 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00028-of-00046.safetensors",
|
| 378 |
+
"model.layers.29.input_layernorm.weight": "model-00030-of-00046.safetensors",
|
| 379 |
+
"model.layers.29.mlp.gate.e_score_correction_bias": "model-00030-of-00046.safetensors",
|
| 380 |
+
"model.layers.29.mlp.gate.weight": "model-00030-of-00046.safetensors",
|
| 381 |
+
"model.layers.29.mlp.shared_experts.down_proj.weight": "model-00030-of-00046.safetensors",
|
| 382 |
+
"model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00030-of-00046.safetensors",
|
| 383 |
+
"model.layers.29.mlp.shared_experts.up_proj.weight": "model-00030-of-00046.safetensors",
|
| 384 |
+
"model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00030-of-00046.safetensors",
|
| 385 |
+
"model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00046.safetensors",
|
| 386 |
+
"model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00029-of-00046.safetensors",
|
| 387 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00030-of-00046.safetensors",
|
| 388 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00029-of-00046.safetensors",
|
| 389 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00029-of-00046.safetensors",
|
| 390 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00029-of-00046.safetensors",
|
| 391 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00029-of-00046.safetensors",
|
| 392 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00029-of-00046.safetensors",
|
| 393 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00029-of-00046.safetensors",
|
| 394 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00029-of-00046.safetensors",
|
| 395 |
+
"model.layers.3.input_layernorm.weight": "model-00004-of-00046.safetensors",
|
| 396 |
+
"model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00046.safetensors",
|
| 397 |
+
"model.layers.3.mlp.gate.weight": "model-00004-of-00046.safetensors",
|
| 398 |
+
"model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00046.safetensors",
|
| 399 |
+
"model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00046.safetensors",
|
| 400 |
+
"model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00046.safetensors",
|
| 401 |
+
"model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00004-of-00046.safetensors",
|
| 402 |
+
"model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00046.safetensors",
|
| 403 |
+
"model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00003-of-00046.safetensors",
|
| 404 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00046.safetensors",
|
| 405 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00046.safetensors",
|
| 406 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00046.safetensors",
|
| 407 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00046.safetensors",
|
| 408 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00046.safetensors",
|
| 409 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00046.safetensors",
|
| 410 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00046.safetensors",
|
| 411 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00046.safetensors",
|
| 412 |
+
"model.layers.30.input_layernorm.weight": "model-00031-of-00046.safetensors",
|
| 413 |
+
"model.layers.30.mlp.gate.e_score_correction_bias": "model-00031-of-00046.safetensors",
|
| 414 |
+
"model.layers.30.mlp.gate.weight": "model-00031-of-00046.safetensors",
|
| 415 |
+
"model.layers.30.mlp.shared_experts.down_proj.weight": "model-00031-of-00046.safetensors",
|
| 416 |
+
"model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00031-of-00046.safetensors",
|
| 417 |
+
"model.layers.30.mlp.shared_experts.up_proj.weight": "model-00031-of-00046.safetensors",
|
| 418 |
+
"model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00031-of-00046.safetensors",
|
| 419 |
+
"model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00046.safetensors",
|
| 420 |
+
"model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00030-of-00046.safetensors",
|
| 421 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00031-of-00046.safetensors",
|
| 422 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00030-of-00046.safetensors",
|
| 423 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00030-of-00046.safetensors",
|
| 424 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00030-of-00046.safetensors",
|
| 425 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00030-of-00046.safetensors",
|
| 426 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00030-of-00046.safetensors",
|
| 427 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00030-of-00046.safetensors",
|
| 428 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00030-of-00046.safetensors",
|
| 429 |
+
"model.layers.31.input_layernorm.weight": "model-00032-of-00046.safetensors",
|
| 430 |
+
"model.layers.31.mlp.gate.e_score_correction_bias": "model-00032-of-00046.safetensors",
|
| 431 |
+
"model.layers.31.mlp.gate.weight": "model-00032-of-00046.safetensors",
|
| 432 |
+
"model.layers.31.mlp.shared_experts.down_proj.weight": "model-00032-of-00046.safetensors",
|
| 433 |
+
"model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00032-of-00046.safetensors",
|
| 434 |
+
"model.layers.31.mlp.shared_experts.up_proj.weight": "model-00032-of-00046.safetensors",
|
| 435 |
+
"model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00032-of-00046.safetensors",
|
| 436 |
+
"model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00031-of-00046.safetensors",
|
| 437 |
+
"model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00031-of-00046.safetensors",
|
| 438 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00032-of-00046.safetensors",
|
| 439 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00031-of-00046.safetensors",
|
| 440 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00031-of-00046.safetensors",
|
| 441 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00031-of-00046.safetensors",
|
| 442 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00031-of-00046.safetensors",
|
| 443 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00031-of-00046.safetensors",
|
| 444 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00031-of-00046.safetensors",
|
| 445 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00031-of-00046.safetensors",
|
| 446 |
+
"model.layers.32.input_layernorm.weight": "model-00033-of-00046.safetensors",
|
| 447 |
+
"model.layers.32.mlp.gate.e_score_correction_bias": "model-00033-of-00046.safetensors",
|
| 448 |
+
"model.layers.32.mlp.gate.weight": "model-00033-of-00046.safetensors",
|
| 449 |
+
"model.layers.32.mlp.shared_experts.down_proj.weight": "model-00033-of-00046.safetensors",
|
| 450 |
+
"model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00033-of-00046.safetensors",
|
| 451 |
+
"model.layers.32.mlp.shared_experts.up_proj.weight": "model-00033-of-00046.safetensors",
|
| 452 |
+
"model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00033-of-00046.safetensors",
|
| 453 |
+
"model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00046.safetensors",
|
| 454 |
+
"model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00032-of-00046.safetensors",
|
| 455 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00033-of-00046.safetensors",
|
| 456 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00032-of-00046.safetensors",
|
| 457 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00032-of-00046.safetensors",
|
| 458 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00032-of-00046.safetensors",
|
| 459 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00032-of-00046.safetensors",
|
| 460 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00032-of-00046.safetensors",
|
| 461 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00032-of-00046.safetensors",
|
| 462 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00032-of-00046.safetensors",
|
| 463 |
+
"model.layers.33.input_layernorm.weight": "model-00034-of-00046.safetensors",
|
| 464 |
+
"model.layers.33.mlp.gate.e_score_correction_bias": "model-00034-of-00046.safetensors",
|
| 465 |
+
"model.layers.33.mlp.gate.weight": "model-00034-of-00046.safetensors",
|
| 466 |
+
"model.layers.33.mlp.shared_experts.down_proj.weight": "model-00034-of-00046.safetensors",
|
| 467 |
+
"model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00034-of-00046.safetensors",
|
| 468 |
+
"model.layers.33.mlp.shared_experts.up_proj.weight": "model-00034-of-00046.safetensors",
|
| 469 |
+
"model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00034-of-00046.safetensors",
|
| 470 |
+
"model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00033-of-00046.safetensors",
|
| 471 |
+
"model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00033-of-00046.safetensors",
|
| 472 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00034-of-00046.safetensors",
|
| 473 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00033-of-00046.safetensors",
|
| 474 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00033-of-00046.safetensors",
|
| 475 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00033-of-00046.safetensors",
|
| 476 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00033-of-00046.safetensors",
|
| 477 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00033-of-00046.safetensors",
|
| 478 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00033-of-00046.safetensors",
|
| 479 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00033-of-00046.safetensors",
|
| 480 |
+
"model.layers.34.input_layernorm.weight": "model-00035-of-00046.safetensors",
|
| 481 |
+
"model.layers.34.mlp.gate.e_score_correction_bias": "model-00035-of-00046.safetensors",
|
| 482 |
+
"model.layers.34.mlp.gate.weight": "model-00035-of-00046.safetensors",
|
| 483 |
+
"model.layers.34.mlp.shared_experts.down_proj.weight": "model-00035-of-00046.safetensors",
|
| 484 |
+
"model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00035-of-00046.safetensors",
|
| 485 |
+
"model.layers.34.mlp.shared_experts.up_proj.weight": "model-00035-of-00046.safetensors",
|
| 486 |
+
"model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00035-of-00046.safetensors",
|
| 487 |
+
"model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00034-of-00046.safetensors",
|
| 488 |
+
"model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00034-of-00046.safetensors",
|
| 489 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00035-of-00046.safetensors",
|
| 490 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00034-of-00046.safetensors",
|
| 491 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00034-of-00046.safetensors",
|
| 492 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00034-of-00046.safetensors",
|
| 493 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00034-of-00046.safetensors",
|
| 494 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00034-of-00046.safetensors",
|
| 495 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00034-of-00046.safetensors",
|
| 496 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00034-of-00046.safetensors",
|
| 497 |
+
"model.layers.35.input_layernorm.weight": "model-00036-of-00046.safetensors",
|
| 498 |
+
"model.layers.35.mlp.gate.e_score_correction_bias": "model-00036-of-00046.safetensors",
|
| 499 |
+
"model.layers.35.mlp.gate.weight": "model-00036-of-00046.safetensors",
|
| 500 |
+
"model.layers.35.mlp.shared_experts.down_proj.weight": "model-00036-of-00046.safetensors",
|
| 501 |
+
"model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00036-of-00046.safetensors",
|
| 502 |
+
"model.layers.35.mlp.shared_experts.up_proj.weight": "model-00036-of-00046.safetensors",
|
| 503 |
+
"model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00036-of-00046.safetensors",
|
| 504 |
+
"model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00046.safetensors",
|
| 505 |
+
"model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00035-of-00046.safetensors",
|
| 506 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00036-of-00046.safetensors",
|
| 507 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00035-of-00046.safetensors",
|
| 508 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00035-of-00046.safetensors",
|
| 509 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00035-of-00046.safetensors",
|
| 510 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00035-of-00046.safetensors",
|
| 511 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00035-of-00046.safetensors",
|
| 512 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00035-of-00046.safetensors",
|
| 513 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00035-of-00046.safetensors",
|
| 514 |
+
"model.layers.36.input_layernorm.weight": "model-00037-of-00046.safetensors",
|
| 515 |
+
"model.layers.36.mlp.gate.e_score_correction_bias": "model-00037-of-00046.safetensors",
|
| 516 |
+
"model.layers.36.mlp.gate.weight": "model-00037-of-00046.safetensors",
|
| 517 |
+
"model.layers.36.mlp.shared_experts.down_proj.weight": "model-00037-of-00046.safetensors",
|
| 518 |
+
"model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00037-of-00046.safetensors",
|
| 519 |
+
"model.layers.36.mlp.shared_experts.up_proj.weight": "model-00037-of-00046.safetensors",
|
| 520 |
+
"model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00037-of-00046.safetensors",
|
| 521 |
+
"model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00036-of-00046.safetensors",
|
| 522 |
+
"model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00036-of-00046.safetensors",
|
| 523 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00037-of-00046.safetensors",
|
| 524 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00036-of-00046.safetensors",
|
| 525 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00036-of-00046.safetensors",
|
| 526 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00036-of-00046.safetensors",
|
| 527 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00036-of-00046.safetensors",
|
| 528 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00036-of-00046.safetensors",
|
| 529 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00036-of-00046.safetensors",
|
| 530 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00036-of-00046.safetensors",
|
| 531 |
+
"model.layers.37.input_layernorm.weight": "model-00038-of-00046.safetensors",
|
| 532 |
+
"model.layers.37.mlp.gate.e_score_correction_bias": "model-00038-of-00046.safetensors",
|
| 533 |
+
"model.layers.37.mlp.gate.weight": "model-00038-of-00046.safetensors",
|
| 534 |
+
"model.layers.37.mlp.shared_experts.down_proj.weight": "model-00038-of-00046.safetensors",
|
| 535 |
+
"model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00038-of-00046.safetensors",
|
| 536 |
+
"model.layers.37.mlp.shared_experts.up_proj.weight": "model-00038-of-00046.safetensors",
|
| 537 |
+
"model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00038-of-00046.safetensors",
|
| 538 |
+
"model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00037-of-00046.safetensors",
|
| 539 |
+
"model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00037-of-00046.safetensors",
|
| 540 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00038-of-00046.safetensors",
|
| 541 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00037-of-00046.safetensors",
|
| 542 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00037-of-00046.safetensors",
|
| 543 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00037-of-00046.safetensors",
|
| 544 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00037-of-00046.safetensors",
|
| 545 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00037-of-00046.safetensors",
|
| 546 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00037-of-00046.safetensors",
|
| 547 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00037-of-00046.safetensors",
|
| 548 |
+
"model.layers.38.input_layernorm.weight": "model-00039-of-00046.safetensors",
|
| 549 |
+
"model.layers.38.mlp.gate.e_score_correction_bias": "model-00039-of-00046.safetensors",
|
| 550 |
+
"model.layers.38.mlp.gate.weight": "model-00039-of-00046.safetensors",
|
| 551 |
+
"model.layers.38.mlp.shared_experts.down_proj.weight": "model-00039-of-00046.safetensors",
|
| 552 |
+
"model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00039-of-00046.safetensors",
|
| 553 |
+
"model.layers.38.mlp.shared_experts.up_proj.weight": "model-00039-of-00046.safetensors",
|
| 554 |
+
"model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00039-of-00046.safetensors",
|
| 555 |
+
"model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00038-of-00046.safetensors",
|
| 556 |
+
"model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00038-of-00046.safetensors",
|
| 557 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00039-of-00046.safetensors",
|
| 558 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00038-of-00046.safetensors",
|
| 559 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00038-of-00046.safetensors",
|
| 560 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00038-of-00046.safetensors",
|
| 561 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00038-of-00046.safetensors",
|
| 562 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00038-of-00046.safetensors",
|
| 563 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00038-of-00046.safetensors",
|
| 564 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00038-of-00046.safetensors",
|
| 565 |
+
"model.layers.39.input_layernorm.weight": "model-00040-of-00046.safetensors",
|
| 566 |
+
"model.layers.39.mlp.gate.e_score_correction_bias": "model-00040-of-00046.safetensors",
|
| 567 |
+
"model.layers.39.mlp.gate.weight": "model-00040-of-00046.safetensors",
|
| 568 |
+
"model.layers.39.mlp.shared_experts.down_proj.weight": "model-00040-of-00046.safetensors",
|
| 569 |
+
"model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00040-of-00046.safetensors",
|
| 570 |
+
"model.layers.39.mlp.shared_experts.up_proj.weight": "model-00040-of-00046.safetensors",
|
| 571 |
+
"model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00040-of-00046.safetensors",
|
| 572 |
+
"model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00039-of-00046.safetensors",
|
| 573 |
+
"model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00039-of-00046.safetensors",
|
| 574 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00040-of-00046.safetensors",
|
| 575 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00039-of-00046.safetensors",
|
| 576 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00039-of-00046.safetensors",
|
| 577 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00039-of-00046.safetensors",
|
| 578 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00039-of-00046.safetensors",
|
| 579 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00039-of-00046.safetensors",
|
| 580 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00039-of-00046.safetensors",
|
| 581 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00039-of-00046.safetensors",
|
| 582 |
+
"model.layers.4.input_layernorm.weight": "model-00005-of-00046.safetensors",
|
| 583 |
+
"model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00046.safetensors",
|
| 584 |
+
"model.layers.4.mlp.gate.weight": "model-00005-of-00046.safetensors",
|
| 585 |
+
"model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00046.safetensors",
|
| 586 |
+
"model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00046.safetensors",
|
| 587 |
+
"model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00046.safetensors",
|
| 588 |
+
"model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00005-of-00046.safetensors",
|
| 589 |
+
"model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00046.safetensors",
|
| 590 |
+
"model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00004-of-00046.safetensors",
|
| 591 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00046.safetensors",
|
| 592 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00004-of-00046.safetensors",
|
| 593 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00004-of-00046.safetensors",
|
| 594 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00004-of-00046.safetensors",
|
| 595 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00004-of-00046.safetensors",
|
| 596 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00004-of-00046.safetensors",
|
| 597 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00004-of-00046.safetensors",
|
| 598 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00004-of-00046.safetensors",
|
| 599 |
+
"model.layers.40.input_layernorm.weight": "model-00041-of-00046.safetensors",
|
| 600 |
+
"model.layers.40.mlp.gate.e_score_correction_bias": "model-00041-of-00046.safetensors",
|
| 601 |
+
"model.layers.40.mlp.gate.weight": "model-00041-of-00046.safetensors",
|
| 602 |
+
"model.layers.40.mlp.shared_experts.down_proj.weight": "model-00041-of-00046.safetensors",
|
| 603 |
+
"model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00041-of-00046.safetensors",
|
| 604 |
+
"model.layers.40.mlp.shared_experts.up_proj.weight": "model-00041-of-00046.safetensors",
|
| 605 |
+
"model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00041-of-00046.safetensors",
|
| 606 |
+
"model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00040-of-00046.safetensors",
|
| 607 |
+
"model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00040-of-00046.safetensors",
|
| 608 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00041-of-00046.safetensors",
|
| 609 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00040-of-00046.safetensors",
|
| 610 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00040-of-00046.safetensors",
|
| 611 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00040-of-00046.safetensors",
|
| 612 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00040-of-00046.safetensors",
|
| 613 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00040-of-00046.safetensors",
|
| 614 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00040-of-00046.safetensors",
|
| 615 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00040-of-00046.safetensors",
|
| 616 |
+
"model.layers.41.input_layernorm.weight": "model-00042-of-00046.safetensors",
|
| 617 |
+
"model.layers.41.mlp.gate.e_score_correction_bias": "model-00042-of-00046.safetensors",
|
| 618 |
+
"model.layers.41.mlp.gate.weight": "model-00042-of-00046.safetensors",
|
| 619 |
+
"model.layers.41.mlp.shared_experts.down_proj.weight": "model-00042-of-00046.safetensors",
|
| 620 |
+
"model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00042-of-00046.safetensors",
|
| 621 |
+
"model.layers.41.mlp.shared_experts.up_proj.weight": "model-00042-of-00046.safetensors",
|
| 622 |
+
"model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00042-of-00046.safetensors",
|
| 623 |
+
"model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00041-of-00046.safetensors",
|
| 624 |
+
"model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00041-of-00046.safetensors",
|
| 625 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00042-of-00046.safetensors",
|
| 626 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00041-of-00046.safetensors",
|
| 627 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00041-of-00046.safetensors",
|
| 628 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00041-of-00046.safetensors",
|
| 629 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00041-of-00046.safetensors",
|
| 630 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00041-of-00046.safetensors",
|
| 631 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00041-of-00046.safetensors",
|
| 632 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00041-of-00046.safetensors",
|
| 633 |
+
"model.layers.42.input_layernorm.weight": "model-00043-of-00046.safetensors",
|
| 634 |
+
"model.layers.42.mlp.gate.e_score_correction_bias": "model-00043-of-00046.safetensors",
|
| 635 |
+
"model.layers.42.mlp.gate.weight": "model-00043-of-00046.safetensors",
|
| 636 |
+
"model.layers.42.mlp.shared_experts.down_proj.weight": "model-00043-of-00046.safetensors",
|
| 637 |
+
"model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00043-of-00046.safetensors",
|
| 638 |
+
"model.layers.42.mlp.shared_experts.up_proj.weight": "model-00043-of-00046.safetensors",
|
| 639 |
+
"model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00043-of-00046.safetensors",
|
| 640 |
+
"model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00042-of-00046.safetensors",
|
| 641 |
+
"model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00042-of-00046.safetensors",
|
| 642 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00043-of-00046.safetensors",
|
| 643 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00042-of-00046.safetensors",
|
| 644 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00042-of-00046.safetensors",
|
| 645 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00042-of-00046.safetensors",
|
| 646 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00042-of-00046.safetensors",
|
| 647 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00042-of-00046.safetensors",
|
| 648 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00042-of-00046.safetensors",
|
| 649 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00042-of-00046.safetensors",
|
| 650 |
+
"model.layers.43.input_layernorm.weight": "model-00044-of-00046.safetensors",
|
| 651 |
+
"model.layers.43.mlp.gate.e_score_correction_bias": "model-00044-of-00046.safetensors",
|
| 652 |
+
"model.layers.43.mlp.gate.weight": "model-00044-of-00046.safetensors",
|
| 653 |
+
"model.layers.43.mlp.shared_experts.down_proj.weight": "model-00044-of-00046.safetensors",
|
| 654 |
+
"model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00044-of-00046.safetensors",
|
| 655 |
+
"model.layers.43.mlp.shared_experts.up_proj.weight": "model-00044-of-00046.safetensors",
|
| 656 |
+
"model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00044-of-00046.safetensors",
|
| 657 |
+
"model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00043-of-00046.safetensors",
|
| 658 |
+
"model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00043-of-00046.safetensors",
|
| 659 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00044-of-00046.safetensors",
|
| 660 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00043-of-00046.safetensors",
|
| 661 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00043-of-00046.safetensors",
|
| 662 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00043-of-00046.safetensors",
|
| 663 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00043-of-00046.safetensors",
|
| 664 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00043-of-00046.safetensors",
|
| 665 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00043-of-00046.safetensors",
|
| 666 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00043-of-00046.safetensors",
|
| 667 |
+
"model.layers.44.input_layernorm.weight": "model-00045-of-00046.safetensors",
|
| 668 |
+
"model.layers.44.mlp.gate.e_score_correction_bias": "model-00045-of-00046.safetensors",
|
| 669 |
+
"model.layers.44.mlp.gate.weight": "model-00045-of-00046.safetensors",
|
| 670 |
+
"model.layers.44.mlp.shared_experts.down_proj.weight": "model-00045-of-00046.safetensors",
|
| 671 |
+
"model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00045-of-00046.safetensors",
|
| 672 |
+
"model.layers.44.mlp.shared_experts.up_proj.weight": "model-00045-of-00046.safetensors",
|
| 673 |
+
"model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00045-of-00046.safetensors",
|
| 674 |
+
"model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00044-of-00046.safetensors",
|
| 675 |
+
"model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00044-of-00046.safetensors",
|
| 676 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00045-of-00046.safetensors",
|
| 677 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00044-of-00046.safetensors",
|
| 678 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00044-of-00046.safetensors",
|
| 679 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00044-of-00046.safetensors",
|
| 680 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00044-of-00046.safetensors",
|
| 681 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00044-of-00046.safetensors",
|
| 682 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00044-of-00046.safetensors",
|
| 683 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00044-of-00046.safetensors",
|
| 684 |
+
"model.layers.45.input_layernorm.weight": "model-00046-of-00046.safetensors",
|
| 685 |
+
"model.layers.45.mlp.gate.e_score_correction_bias": "model-00046-of-00046.safetensors",
|
| 686 |
+
"model.layers.45.mlp.gate.weight": "model-00046-of-00046.safetensors",
|
| 687 |
+
"model.layers.45.mlp.shared_experts.down_proj.weight": "model-00046-of-00046.safetensors",
|
| 688 |
+
"model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00046.safetensors",
|
| 689 |
+
"model.layers.45.mlp.shared_experts.up_proj.weight": "model-00046-of-00046.safetensors",
|
| 690 |
+
"model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00046-of-00046.safetensors",
|
| 691 |
+
"model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00045-of-00046.safetensors",
|
| 692 |
+
"model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00045-of-00046.safetensors",
|
| 693 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00046-of-00046.safetensors",
|
| 694 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00045-of-00046.safetensors",
|
| 695 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00045-of-00046.safetensors",
|
| 696 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00045-of-00046.safetensors",
|
| 697 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00045-of-00046.safetensors",
|
| 698 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00045-of-00046.safetensors",
|
| 699 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00045-of-00046.safetensors",
|
| 700 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00045-of-00046.safetensors",
|
| 701 |
+
"model.layers.5.input_layernorm.weight": "model-00006-of-00046.safetensors",
|
| 702 |
+
"model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00046.safetensors",
|
| 703 |
+
"model.layers.5.mlp.gate.weight": "model-00006-of-00046.safetensors",
|
| 704 |
+
"model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00046.safetensors",
|
| 705 |
+
"model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00046.safetensors",
|
| 706 |
+
"model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00046.safetensors",
|
| 707 |
+
"model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00006-of-00046.safetensors",
|
| 708 |
+
"model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00046.safetensors",
|
| 709 |
+
"model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00005-of-00046.safetensors",
|
| 710 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00006-of-00046.safetensors",
|
| 711 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00005-of-00046.safetensors",
|
| 712 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00046.safetensors",
|
| 713 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00046.safetensors",
|
| 714 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00005-of-00046.safetensors",
|
| 715 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00046.safetensors",
|
| 716 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00005-of-00046.safetensors",
|
| 717 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00046.safetensors",
|
| 718 |
+
"model.layers.6.input_layernorm.weight": "model-00007-of-00046.safetensors",
|
| 719 |
+
"model.layers.6.mlp.gate.e_score_correction_bias": "model-00007-of-00046.safetensors",
|
| 720 |
+
"model.layers.6.mlp.gate.weight": "model-00007-of-00046.safetensors",
|
| 721 |
+
"model.layers.6.mlp.shared_experts.down_proj.weight": "model-00007-of-00046.safetensors",
|
| 722 |
+
"model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00007-of-00046.safetensors",
|
| 723 |
+
"model.layers.6.mlp.shared_experts.up_proj.weight": "model-00007-of-00046.safetensors",
|
| 724 |
+
"model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00007-of-00046.safetensors",
|
| 725 |
+
"model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00046.safetensors",
|
| 726 |
+
"model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00006-of-00046.safetensors",
|
| 727 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00007-of-00046.safetensors",
|
| 728 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00006-of-00046.safetensors",
|
| 729 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00006-of-00046.safetensors",
|
| 730 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00006-of-00046.safetensors",
|
| 731 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00006-of-00046.safetensors",
|
| 732 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00006-of-00046.safetensors",
|
| 733 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00006-of-00046.safetensors",
|
| 734 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00006-of-00046.safetensors",
|
| 735 |
+
"model.layers.7.input_layernorm.weight": "model-00008-of-00046.safetensors",
|
| 736 |
+
"model.layers.7.mlp.gate.e_score_correction_bias": "model-00008-of-00046.safetensors",
|
| 737 |
+
"model.layers.7.mlp.gate.weight": "model-00008-of-00046.safetensors",
|
| 738 |
+
"model.layers.7.mlp.shared_experts.down_proj.weight": "model-00008-of-00046.safetensors",
|
| 739 |
+
"model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00008-of-00046.safetensors",
|
| 740 |
+
"model.layers.7.mlp.shared_experts.up_proj.weight": "model-00008-of-00046.safetensors",
|
| 741 |
+
"model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00008-of-00046.safetensors",
|
| 742 |
+
"model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00046.safetensors",
|
| 743 |
+
"model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00007-of-00046.safetensors",
|
| 744 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00008-of-00046.safetensors",
|
| 745 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00007-of-00046.safetensors",
|
| 746 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00007-of-00046.safetensors",
|
| 747 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00007-of-00046.safetensors",
|
| 748 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00007-of-00046.safetensors",
|
| 749 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00007-of-00046.safetensors",
|
| 750 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00007-of-00046.safetensors",
|
| 751 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00007-of-00046.safetensors",
|
| 752 |
+
"model.layers.8.input_layernorm.weight": "model-00009-of-00046.safetensors",
|
| 753 |
+
"model.layers.8.mlp.gate.e_score_correction_bias": "model-00009-of-00046.safetensors",
|
| 754 |
+
"model.layers.8.mlp.gate.weight": "model-00009-of-00046.safetensors",
|
| 755 |
+
"model.layers.8.mlp.shared_experts.down_proj.weight": "model-00009-of-00046.safetensors",
|
| 756 |
+
"model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00009-of-00046.safetensors",
|
| 757 |
+
"model.layers.8.mlp.shared_experts.up_proj.weight": "model-00009-of-00046.safetensors",
|
| 758 |
+
"model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00009-of-00046.safetensors",
|
| 759 |
+
"model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00046.safetensors",
|
| 760 |
+
"model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00008-of-00046.safetensors",
|
| 761 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00009-of-00046.safetensors",
|
| 762 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00008-of-00046.safetensors",
|
| 763 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00008-of-00046.safetensors",
|
| 764 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00008-of-00046.safetensors",
|
| 765 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00008-of-00046.safetensors",
|
| 766 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00008-of-00046.safetensors",
|
| 767 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00008-of-00046.safetensors",
|
| 768 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00008-of-00046.safetensors",
|
| 769 |
+
"model.layers.9.input_layernorm.weight": "model-00010-of-00046.safetensors",
|
| 770 |
+
"model.layers.9.mlp.gate.e_score_correction_bias": "model-00010-of-00046.safetensors",
|
| 771 |
+
"model.layers.9.mlp.gate.weight": "model-00010-of-00046.safetensors",
|
| 772 |
+
"model.layers.9.mlp.shared_experts.down_proj.weight": "model-00010-of-00046.safetensors",
|
| 773 |
+
"model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00010-of-00046.safetensors",
|
| 774 |
+
"model.layers.9.mlp.shared_experts.up_proj.weight": "model-00010-of-00046.safetensors",
|
| 775 |
+
"model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00010-of-00046.safetensors",
|
| 776 |
+
"model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00046.safetensors",
|
| 777 |
+
"model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00009-of-00046.safetensors",
|
| 778 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00010-of-00046.safetensors",
|
| 779 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00009-of-00046.safetensors",
|
| 780 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00009-of-00046.safetensors",
|
| 781 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00009-of-00046.safetensors",
|
| 782 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00009-of-00046.safetensors",
|
| 783 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00009-of-00046.safetensors",
|
| 784 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00009-of-00046.safetensors",
|
| 785 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00009-of-00046.safetensors",
|
| 786 |
+
"model.norm.weight": "model-00046-of-00046.safetensors"
|
| 787 |
+
}
|
| 788 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"[MASK]",
|
| 5 |
+
"[gMASK]",
|
| 6 |
+
"[sMASK]",
|
| 7 |
+
"<sop>",
|
| 8 |
+
"<eop>",
|
| 9 |
+
"<|system|>",
|
| 10 |
+
"<|user|>",
|
| 11 |
+
"<|assistant|>",
|
| 12 |
+
"<|observation|>",
|
| 13 |
+
"<|begin_of_image|>",
|
| 14 |
+
"<|end_of_image|>",
|
| 15 |
+
"<|begin_of_video|>",
|
| 16 |
+
"<|end_of_video|>",
|
| 17 |
+
"<|begin_of_audio|>",
|
| 18 |
+
"<|end_of_audio|>",
|
| 19 |
+
"<|begin_of_transcription|>",
|
| 20 |
+
"<|end_of_transcription|>",
|
| 21 |
+
"<|code_prefix|>",
|
| 22 |
+
"<|code_middle|>",
|
| 23 |
+
"<|code_suffix|>",
|
| 24 |
+
"/nothink"
|
| 25 |
+
],
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|im_end|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"pad_token": {
|
| 34 |
+
"content": "<|endoftext|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:840a2be2f18847f07571118fb785c9bde4726991852229d98469e421bf5d1064
|
| 3 |
+
size 19971076
|