add model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,106 @@
+{
+  "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "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": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": 1.557213913701282,
+    "ignore": [
+      "model.layers.0.block_sparse_moe.gate",
+      "model.layers.1.block_sparse_moe.gate",
+      "model.layers.2.block_sparse_moe.gate",
+      "model.layers.3.block_sparse_moe.gate",
+      "model.layers.4.block_sparse_moe.gate",
+      "model.layers.5.block_sparse_moe.gate",
+      "model.layers.6.block_sparse_moe.gate",
+      "model.layers.7.block_sparse_moe.gate",
+      "model.layers.8.block_sparse_moe.gate",
+      "model.layers.9.block_sparse_moe.gate",
+      "model.layers.10.block_sparse_moe.gate",
+      "model.layers.11.block_sparse_moe.gate",
+      "model.layers.12.block_sparse_moe.gate",
+      "model.layers.13.block_sparse_moe.gate",
+      "model.layers.14.block_sparse_moe.gate",
+      "model.layers.15.block_sparse_moe.gate",
+      "model.layers.16.block_sparse_moe.gate",
+      "model.layers.17.block_sparse_moe.gate",
+      "model.layers.18.block_sparse_moe.gate",
+      "model.layers.19.block_sparse_moe.gate",
+      "model.layers.20.block_sparse_moe.gate",
+      "model.layers.21.block_sparse_moe.gate",
+      "model.layers.22.block_sparse_moe.gate",
+      "model.layers.23.block_sparse_moe.gate",
+      "model.layers.24.block_sparse_moe.gate",
+      "model.layers.25.block_sparse_moe.gate",
+      "model.layers.26.block_sparse_moe.gate",
+      "model.layers.27.block_sparse_moe.gate",
+      "model.layers.28.block_sparse_moe.gate",
+      "model.layers.29.block_sparse_moe.gate",
+      "model.layers.30.block_sparse_moe.gate",
+      "model.layers.31.block_sparse_moe.gate",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  },
+  "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": "bfloat16",
+  "transformers_version": "4.48.3",
+  "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": "4.48.3"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ef1af4911fe0a431c6e770f66273795418b9ed6670ffd363974569c08ec8f9
+size 4951723964

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31ef2b505179c06a114bb00ef3e343c8d1df93e0353d86fdec19da3e283f61b
+size 4999891908

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8bcf2aa18fc3618c099026402b96da810bbf85dd02089435962bbda8fcda9c
+size 4983198264

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328229876c7e86d2852ec3d6e9717e18c0d5ff876c2ca0ea6ca2166eb3bb56e9
+size 4999892156

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c5c558330e24513d18a311ab49ea0c7e5a81c527853e45180a0c0834aa7153
+size 4999908932

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b9597cee89e904b3957717a2bc4199645ccf64f2d5b61d71aeeaf61b3e39d4
+size 4983181632

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d14bd053b49e0efee1eb3e0804919d25dc41681b5a5aef1cb3a2f2f5f2c394
+size 4999892284

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d6aa3e29d831eb8d9e1fc0a19aecb074b329a2d75d144441675dce631726aa
+size 4983198472

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41682f27c3a47c60abfc7d8ddd9548aef19d86f1f3e346603e3998a14da3703e
+size 4999892236

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb1e8b4b1b50af852e9793dce909550648d773e7bec81594f60fed59e2bc212
+size 2065815152

recipe.yaml

@@ -0,0 +1,6 @@
+DEFAULT_stage:
+  DEFAULT_modifiers:
+    QuantizationModifier:
+      ignore: [lm_head, 're:.*block_sparse_moe.gate']
+      targets: [Linear]
+      scheme: FP8

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835cf54bb933752267652500a9243a9002107bbb4501b99f8d2f46ccfdad2567
+size 3505608

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
+}