Upload folder using huggingface_hub

README.md

@@ -0,0 +1 @@
+First two layers of `mistralai/Mixtral-8x7B-Instruct-v0.1`.

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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": 2,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "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": "float32",
+  "transformers_version": "4.51.3",
+  "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": "4.51.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba28c558c054384603797f1b2a1f110a834873017d8321de653557a0092b984
+size 4920052720

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fa16cee7e108e3381310d67ae011b2404cceb38d3df413e31481375f6ef6af
+size 4865559920

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6047a83004b2072055b249a1160613cd32a9ffbd26f1d812dc59846224d6fd84
+size 2873149136

model.safetensors.index.json

@@ -0,0 +1,72 @@
+{
+  "metadata": {
+    "total_size": 12658753536
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

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 +1,45 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "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
+}