Upload folder using huggingface_hub

README.md

@@ -0,0 +1,11 @@
+## Mixtral-8x7B-Instruct-v0.1-FP8-v1
+
+* Weights and activations are per-tensor quantized to float8_e4m3.
+* Quantization with AutoFP8.
+* Calibration dataset: Ultrachat-200k
+* Samples: 4096
+* Sequence length: 8192
+
+## Evaluation
+
+TBA

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "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",
+    "ignored_layers": [
+      "model.layers.25.block_sparse_moe.gate",
+      "model.layers.2.block_sparse_moe.gate",
+      "model.layers.4.block_sparse_moe.gate",
+      "model.layers.26.block_sparse_moe.gate",
+      "model.layers.27.block_sparse_moe.gate",
+      "model.layers.20.block_sparse_moe.gate",
+      "model.layers.1.block_sparse_moe.gate",
+      "model.layers.30.block_sparse_moe.gate",
+      "model.layers.0.block_sparse_moe.gate",
+      "model.layers.5.block_sparse_moe.gate",
+      "model.layers.31.block_sparse_moe.gate",
+      "model.layers.12.block_sparse_moe.gate",
+      "model.layers.10.block_sparse_moe.gate",
+      "model.layers.19.block_sparse_moe.gate",
+      "model.layers.13.block_sparse_moe.gate",
+      "model.layers.24.block_sparse_moe.gate",
+      "model.layers.28.block_sparse_moe.gate",
+      "lm_head",
+      "model.layers.6.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.23.block_sparse_moe.gate",
+      "model.layers.7.block_sparse_moe.gate",
+      "model.layers.11.block_sparse_moe.gate",
+      "model.layers.22.block_sparse_moe.gate",
+      "model.layers.18.block_sparse_moe.gate",
+      "model.layers.29.block_sparse_moe.gate",
+      "model.layers.9.block_sparse_moe.gate",
+      "model.layers.21.block_sparse_moe.gate",
+      "model.layers.3.block_sparse_moe.gate",
+      "model.layers.8.block_sparse_moe.gate",
+      "model.layers.14.block_sparse_moe.gate"
+    ],
+    "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": "bfloat16",
+  "transformers_version": "4.40.2",
+  "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": "4.40.2"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212ad34d793d2085e294b3393779389256049339c13ddddd37da133089d5fd91
+size 4951721656

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566a1e38dcd44e1aa5f4be968c23c0e710dd510cee58671a5397817cd4445cd9
+size 4999891208

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca950705c99be774b72d30064922fda14449034b2337ec4db2ffc46c94722547
+size 4983197192

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94b11287bc1213889d3a5003f4d74774ad7f6207bbdbe6924015409048a3d77
+size 4999891496

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063c13d36917eacef8647824f561e6586649d9124ba379b893a70991034ab416
+size 4999908096

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d824cf6a402c113085628c7b48ebeb15d8f704d05aa6eb4e80bf33f94e198f31
+size 4983180880

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39242f6ab907535c5085c947e42c3a098a6ec6d5fee1e0b94f1950964fb9fe95
+size 4999891496

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d163c3994a85f160eb81b8a3fccdbe8eac8adf4ea1285306413651fd78a9e00
+size 4983197472

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47912e99ecd9790ffd972cbb677ba7f12e43f4d1bcad69f5e7b08344dd2361af
+size 4999891496

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7980fd3ebb09ba40fe1df4bdacb843f6954795af7bd644330734ac149b0d03f
+size 2065814256

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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "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
+}