Upload folder using huggingface_hub

config.json

@@ -51,7 +51,7 @@
     "quantization_status": "compressed",
     "sparsity_config": {
       "format": "dense",
-      "global_sparsity": 0.14375328644374685,
+      "global_sparsity": 0.14329888201729718,
       "ignore": [],
       "registry_requires_subclass": false,
       "sparsity_structure": "unstructured",
@@ -63,7 +63,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892873b79abcf66508b526a74179177e303de9b4b1464a6177096348faa7fd76
+oid sha256:f3c99c37708043eee70aa1961dcda6621a800fe68feaa47f280f1083e5b2a53f
 size 761968800

recipe.yaml

@@ -1,6 +1,6 @@
 DEFAULT_stage:
   DEFAULT_modifiers:
     GPTQModifier:
+      scheme: W4A16
       targets: Linear
       ignore: [lm_head]
-      scheme: W4A16

tokenizer_config.json

@@ -32,6 +32,7 @@
   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 2048,
   "pad_token": "</s>",