GPTQ model commit

config.json

@@ -4,7 +4,7 @@
         "MistralForCausalLM"
     ],
     "bos_token_id": 1,
-    "eos_token_id": 2,
+    "eos_token_id": 32000,
     "hidden_act": "silu",
     "hidden_size": 4096,
     "initializer_range": 0.02,

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "max_length": 8192,
+  "pad_token_id": 0,
+  "temperature": 0.5,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f25783decf6ff3c0e3d33ec8daf6a62143f4fc4c03cefee8136045d25096f32
+oid sha256:1c70c7dd854eabede11c53381176b9c166307b8b21b2af8986f08305e975760a
 size 7675619912

tokenizer_config.json

@@ -50,7 +50,7 @@
   "bos_token": "<s>",
   "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|end_of_turn|>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,