Upload folder using huggingface_hub
Browse files- README.md +75 -1
- config.json +35 -0
- merges.txt +0 -0
- model-00001-of-00001.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +38 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,77 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- moe
|
| 5 |
+
- merge
|
| 6 |
+
- mergekit
|
| 7 |
+
- lazymergekit
|
| 8 |
+
- ahxt/LiteLlama-460M-1T
|
| 9 |
+
- ahxt/LiteLlama-460M-1T
|
| 10 |
+
- ahxt/LiteLlama-460M-1T
|
| 11 |
+
- ahxt/LiteLlama-460M-1T
|
| 12 |
+
- ahxt/LiteLlama-460M-1T
|
| 13 |
+
- ahxt/LiteLlama-460M-1T
|
| 14 |
+
- ahxt/LiteLlama-460M-1T
|
| 15 |
+
- ahxt/LiteLlama-460M-1T
|
| 16 |
---
|
| 17 |
+
|
| 18 |
+
# LiteLlamix-8x460M-1T
|
| 19 |
+
|
| 20 |
+
LiteLlamix-8x460M-1T is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
| 21 |
+
* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
|
| 22 |
+
* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
|
| 23 |
+
* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
|
| 24 |
+
* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
|
| 25 |
+
* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
|
| 26 |
+
* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
|
| 27 |
+
* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
|
| 28 |
+
* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
|
| 29 |
+
|
| 30 |
+
## 🧩 Configuration
|
| 31 |
+
|
| 32 |
+
```yaml
|
| 33 |
+
base_model: ahxt/LiteLlama-460M-1T
|
| 34 |
+
gate_mode: hidden
|
| 35 |
+
dtype: bfloat16
|
| 36 |
+
experts:
|
| 37 |
+
- source_model: ahxt/LiteLlama-460M-1T
|
| 38 |
+
positive_prompts: [""]
|
| 39 |
+
- source_model: ahxt/LiteLlama-460M-1T
|
| 40 |
+
positive_prompts: [""]
|
| 41 |
+
- source_model: ahxt/LiteLlama-460M-1T
|
| 42 |
+
positive_prompts: [""]
|
| 43 |
+
- source_model: ahxt/LiteLlama-460M-1T
|
| 44 |
+
positive_prompts: [""]
|
| 45 |
+
- source_model: ahxt/LiteLlama-460M-1T
|
| 46 |
+
positive_prompts: [""]
|
| 47 |
+
- source_model: ahxt/LiteLlama-460M-1T
|
| 48 |
+
positive_prompts: [""]
|
| 49 |
+
- source_model: ahxt/LiteLlama-460M-1T
|
| 50 |
+
positive_prompts: [""]
|
| 51 |
+
- source_model: ahxt/LiteLlama-460M-1T
|
| 52 |
+
positive_prompts: [""]
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
## 💻 Usage
|
| 56 |
+
|
| 57 |
+
```python
|
| 58 |
+
!pip install -qU transformers bitsandbytes accelerate
|
| 59 |
+
|
| 60 |
+
from transformers import AutoTokenizer
|
| 61 |
+
import transformers
|
| 62 |
+
import torch
|
| 63 |
+
|
| 64 |
+
model = "aloobun/LiteLlamix-8x460M-1T"
|
| 65 |
+
|
| 66 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
| 67 |
+
pipeline = transformers.pipeline(
|
| 68 |
+
"text-generation",
|
| 69 |
+
model=model,
|
| 70 |
+
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
|
| 71 |
+
)
|
| 72 |
+
|
| 73 |
+
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
|
| 74 |
+
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 75 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
| 76 |
+
print(outputs[0]["generated_text"])
|
| 77 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ahxt/LiteLlama-460M-1T",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layernorm_epsilon": 1e-05,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"model_type": "mixtral",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_experts_per_tok": 2,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"num_key_value_heads": 2,
|
| 21 |
+
"num_local_experts": 8,
|
| 22 |
+
"output_router_logits": false,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 10000.0,
|
| 28 |
+
"router_aux_loss_coef": 0.001,
|
| 29 |
+
"sliding_window": null,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.36.2",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 50304
|
| 35 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00001.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ad9e48da718d1f6d5812292793c30864f63f9a9203853eea62d3219d16ea3bf
|
| 3 |
+
size 5151718160
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "lm_head.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors"}}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "#",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"1": {
|
| 6 |
+
"content": "\"",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"2": {
|
| 14 |
+
"content": "#",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"50256": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<|endoftext|>",
|
| 31 |
+
"clean_up_tokenization_spaces": true,
|
| 32 |
+
"eos_token": "#",
|
| 33 |
+
"errors": "replace",
|
| 34 |
+
"model_max_length": 1024,
|
| 35 |
+
"pad_token": "<|endoftext|>",
|
| 36 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 37 |
+
"unk_token": "<|endoftext|>"
|
| 38 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|