Upload folder using huggingface_hub

config.json

@@ -55,7 +55,7 @@
   "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:c92e5a3de86e62cd5a3b885ae32d70894a1d528c7a8776f9664e23e554160322
+oid sha256:623323e0b37bc2d08746bc4699aa009ee56e5126c24b063920982129dcfc034a
 size 1232060880

recipe.yaml

@@ -1,6 +1,6 @@
 DEFAULT_stage:
   DEFAULT_modifiers:
     GPTQModifier:
+      scheme: W8A16
       targets: Linear
       ignore: [lm_head]
-      scheme: W8A16

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>",