Initial commit

config.json

@@ -0,0 +1,129 @@
+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 65536,
+  "model_type": "mixtral",
+  "num_attention_heads": 48,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 56,
+  "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": 1.558404548701109,
+    "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",
+      "model.layers.32.block_sparse_moe.gate",
+      "model.layers.33.block_sparse_moe.gate",
+      "model.layers.34.block_sparse_moe.gate",
+      "model.layers.35.block_sparse_moe.gate",
+      "model.layers.36.block_sparse_moe.gate",
+      "model.layers.37.block_sparse_moe.gate",
+      "model.layers.38.block_sparse_moe.gate",
+      "model.layers.39.block_sparse_moe.gate",
+      "model.layers.40.block_sparse_moe.gate",
+      "model.layers.41.block_sparse_moe.gate",
+      "model.layers.42.block_sparse_moe.gate",
+      "model.layers.43.block_sparse_moe.gate",
+      "model.layers.44.block_sparse_moe.gate",
+      "model.layers.45.block_sparse_moe.gate",
+      "model.layers.46.block_sparse_moe.gate",
+      "model.layers.47.block_sparse_moe.gate",
+      "model.layers.48.block_sparse_moe.gate",
+      "model.layers.49.block_sparse_moe.gate",
+      "model.layers.50.block_sparse_moe.gate",
+      "model.layers.51.block_sparse_moe.gate",
+      "model.layers.52.block_sparse_moe.gate",
+      "model.layers.53.block_sparse_moe.gate",
+      "model.layers.54.block_sparse_moe.gate",
+      "model.layers.55.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,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.50.0"
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03bae71f4003ef63feea404e2c58cf07515426b7b20fe559ff0fc252804a19f
+size 4998803472

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3b7a70fd57ffbe352c919536a297cf9af885f0233ec8337219c4b6f578319b
+size 4907602348

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ec284dee2da83c2eb910ea36ba41ddfc142162adb0d6f85e4b9984044c818c
+size 4907602332

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25acf8cbbe61f96d7e0eef5c36d48af60133f0a53c41e68c77e21c60f67f2728
+size 4907602316

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609cf30a5246a163a987eaec90c7e2a4c4f9a53bf00c8c6f71445528d04e3c56
+size 4907602300

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff010f78b8f264838c4047e2ec36d128da5e2bc436eeba3b4f44680dc962555c
+size 4907602276

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3d2b4e80806d5b77ad9131356fdccbf4384e28cb4c8fc35fededd3fe098db0
+size 4907602444

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1872d8cc30ef61898ca5cc60100e079e0e7ff84565e818520ef9e45d771dcab4
+size 4907602428

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f44be62f97279515f933d0b0f3eadbe0235fe96c451ea2ebefd4684b3d7c549
+size 4907602412

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444c2ccea8b2aea3aa76c8bf45d6eb0ef2a02ce6ebf3a8015225734165d83662
+size 4907602396

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539a0354e8820e3080ff5344612d81ce1884d6d7ca5317735103149cee64aa0d
+size 4907602380

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f233759a57923f0f8e1b8087e39aa5a25b7e9b9fb29f70b76b804e023b70ad
+size 4907602364

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e063bdd744110276ddc1126518630937de0cf220d0428f3a20a0da21a9d72be0
+size 4907602348

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54c45aec5cf90b57ae812fbc69bc0ef35d3684557535d1bd56a060b573a3d40
+size 4907602332

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7ba449e3af29aa39370d8f48aa1fcfbe361012a600123ace25972bd58bc577
+size 4907602316

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0c7f7ea5eabd3c0106c44760347ae4b5c39042ec13eaafb97e3c2454fb2011
+size 4907602300

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3629742239796d962005d961ba5b508b5562c5e084d4c7840ceade9c68d0bf66
+size 4907602284

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31361b272f9134cb09f45272f9af3336f49dce01d829c2070705de308c472f8
+size 4907602268

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27dd8ae0707ca53bb620856b5bc84fb5bedba7c31decd9a93f33727059b5685
+size 4907602252

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4946b5ad48491f9d586b88c0d4014b9337f6d71dad6ee726711229f0c359f0
+size 4907602236

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0426ded609b7c23035ac91ab4ffa7b9ea131daecbaf32541fda1cf3b848d0055
+size 4907602220

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9cb8a0a55e5db3a3a9495810a82b2643e79e20cf9b10663149384d983fe7eec
+size 4970418388

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4df83081b0d4ae7fe3a120689637ceebb72e8f90abd724ca39a8dbd97b393e
+size 4995682384

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f5c8376be690c808269e82fa133a35acedae4717d9b8afa3f180332d14f314
+size 4970516900

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383f552959b325074ed36db432066f441b1f1bb2d33acdadd2a43ae173608be0
+size 4907577508

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020244d20ba19f7862f17c63239e8b4862ea3a2e8023b47c25029eba91d20ad5
+size 4907602572

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593e19d03edcd5aa168fba206b37cf191518216af6b31fe8f98351ee4a96b69f
+size 4907602556

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786f80082a6d52b4db5c6643204c8d47ba6c89637cfa94c708ab49957b109e47
+size 4907602540

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceeabed3ab724f0929ecd9ad6b45d768d8729bd0dd02773731593de6aaf0cdad
+size 3300041576

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 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "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 +1,46 @@
+{
+  "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' %}{% set loop_messages = messages[1:] %}{{ messages[0]['content'].strip() }}{% else %}{% set loop_messages = messages %}{{ 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions.' }}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ ' USER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% else %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ '\nUSER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' ASSISTANT:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}