Upload folder using huggingface_hub

config.json

@@ -0,0 +1,105 @@
+{
+  "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": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "strategy": "token",
+          "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": "channel",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": 1.5571329863166834,
+    "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": "4.50.1",
+  "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": "4.50.1"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459e77fd21b0699481404a255c1f0cc35c7641063317a07acff67bda9ea37dd8
+size 4953469880

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25bfa7862747755bd378df93a3012c23f70d52e7f80a545ca09dbf2a20cac977
+size 4943020616

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fbec67ce4ae5d5c7f5cad47ccd2d69b76e5df2c4fab26bf585175a82341a69a
+size 4985067320

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ea48502215e1de4af2614420f967d2b8c683036056763b835360b7cbdaa75b
+size 4943000328

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b857724d71cd59a7b62801b7892c570141e93edfc6279ae26e1d69ab2d2cf0
+size 4943020808

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3635672cb304ea3a911fb6b5a87774d3abdbf58b51499f4535252fd6cd410cb
+size 4985067528

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e30f1a6e43607866d4a31da9832ba5fe41ddd357d4fdca93387d06e4fbfada7
+size 4943000328

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4748fbe597f028f6323895ad01f77a53d6400b970b3642002f27e61a1f7a6186
+size 4985067528

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3439f8cc4b67295f8fd8d152ce634a5e86a685d92464db217f54c737ad715493
+size 4943020816

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6f637486bb62909d40b7fab4e7cf04c173692457abb852f49259b8d97d7942
+size 2360191832

recipe.yaml

@@ -0,0 +1,6 @@
+DEFAULT_stage:
+  DEFAULT_modifiers:
+    QuantizationModifier:
+      ignore: [lm_head, 're:.*block_sparse_moe.gate']
+      targets: [Linear]
+      scheme: FP8_DYNAMIC

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_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
+}