Upload folder using huggingface_hub

config.json

@@ -0,0 +1,112 @@
+{
+  "_name_or_path": "/model/mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "quantization_config": {
+    "activation_scheme": "static",
+    "export": {
+      "kv_cache_group": [
+        "*k_proj",
+        "*v_proj"
+      ],
+      "pack_method": "reorder",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "ignored_layers": [
+      "model.layers.0.self_attn.o_proj",
+      "model.layers.0.block_sparse_moe.gate",
+      "model.layers.1.self_attn.o_proj",
+      "model.layers.1.block_sparse_moe.gate",
+      "model.layers.2.self_attn.o_proj",
+      "model.layers.2.block_sparse_moe.gate",
+      "model.layers.3.self_attn.o_proj",
+      "model.layers.3.block_sparse_moe.gate",
+      "model.layers.4.self_attn.o_proj",
+      "model.layers.4.block_sparse_moe.gate",
+      "model.layers.5.self_attn.o_proj",
+      "model.layers.5.block_sparse_moe.gate",
+      "model.layers.6.self_attn.o_proj",
+      "model.layers.6.block_sparse_moe.gate",
+      "model.layers.7.self_attn.o_proj",
+      "model.layers.7.block_sparse_moe.gate",
+      "model.layers.8.self_attn.o_proj",
+      "model.layers.8.block_sparse_moe.gate",
+      "model.layers.9.self_attn.o_proj",
+      "model.layers.9.block_sparse_moe.gate",
+      "model.layers.10.self_attn.o_proj",
+      "model.layers.10.block_sparse_moe.gate",
+      "model.layers.11.self_attn.o_proj",
+      "model.layers.11.block_sparse_moe.gate",
+      "model.layers.12.self_attn.o_proj",
+      "model.layers.12.block_sparse_moe.gate",
+      "model.layers.13.self_attn.o_proj",
+      "model.layers.13.block_sparse_moe.gate",
+      "model.layers.14.self_attn.o_proj",
+      "model.layers.14.block_sparse_moe.gate",
+      "model.layers.15.self_attn.o_proj",
+      "model.layers.15.block_sparse_moe.gate",
+      "model.layers.16.self_attn.o_proj",
+      "model.layers.16.block_sparse_moe.gate",
+      "model.layers.17.self_attn.o_proj",
+      "model.layers.17.block_sparse_moe.gate",
+      "model.layers.18.self_attn.o_proj",
+      "model.layers.18.block_sparse_moe.gate",
+      "model.layers.19.self_attn.o_proj",
+      "model.layers.19.block_sparse_moe.gate",
+      "model.layers.20.self_attn.o_proj",
+      "model.layers.20.block_sparse_moe.gate",
+      "model.layers.21.self_attn.o_proj",
+      "model.layers.21.block_sparse_moe.gate",
+      "model.layers.22.self_attn.o_proj",
+      "model.layers.22.block_sparse_moe.gate",
+      "model.layers.23.self_attn.o_proj",
+      "model.layers.23.block_sparse_moe.gate",
+      "model.layers.24.self_attn.o_proj",
+      "model.layers.24.block_sparse_moe.gate",
+      "model.layers.25.self_attn.o_proj",
+      "model.layers.25.block_sparse_moe.gate",
+      "model.layers.26.self_attn.o_proj",
+      "model.layers.26.block_sparse_moe.gate",
+      "model.layers.27.self_attn.o_proj",
+      "model.layers.27.block_sparse_moe.gate",
+      "model.layers.28.self_attn.o_proj",
+      "model.layers.28.block_sparse_moe.gate",
+      "model.layers.29.self_attn.o_proj",
+      "model.layers.29.block_sparse_moe.gate",
+      "model.layers.30.self_attn.o_proj",
+      "model.layers.30.block_sparse_moe.gate",
+      "model.layers.31.self_attn.o_proj",
+      "model.layers.31.block_sparse_moe.gate",
+      "lm_head"
+    ],
+    "kv_cache_scheme": "static",
+    "quant_method": "fp8"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb950c9534c37a1a23de2cbc4cee35a1d8190f2e85aa2102b8e33242afef858
+size 4960111600

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d681596f0d5034a261fa558709e8901cc5a5898c5aa9417a8307a47d7c0242d6
+size 4991502916

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00b5e2ce10654caf281d8ff1e641b53dd3cc7917bf6f4d8b578d8c6d50bc986
+size 4991519940

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2292011a9f7aae4705836f87599d765b4b34cf44330ab4ce2ee007a07683f2b9
+size 4991569892

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9056294f3a654d736cb87a7f6e96e2637d2081891855a83be34c8a69d36a9a7c
+size 4991503324

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df81de3e2a20de00ac63c9e12707b4e2caf099a3325b582e3a350056d73ba1ae
+size 4991586796

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e325f381fc0a185a3506e34dd066bab362ecfddaa3626e80c5ec37283f8404d3
+size 4991503204

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef36f466071df886a0cac5ea8f338c4699de89cd6d9ff608576bb5a5b1b5d383
+size 4991520228

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bf4c7d74cf9125239b7b32587e4b2fefb7a99e3bd71728cae5c4e80a551f84
+size 4991569892

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ef3bf088cb3893f98692dbc3504ae848ba3591274d124b3314d6936b718f7c
+size 2611077968

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}