Upload of AutoGPTQ quantized model

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/ibex/user/xuj0h/LLM_ckpt/llama-pretrained-RLHF-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "dropout": 0.0,
+  "end_token_id": 2,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

gptq_model-4bit-128g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1531b16078158007c3f685585875a63b6ec0e051526fd8b901f600e776ff329
+size 3896994967

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "/ibex/user/xuj0h/LLM_ckpt/Quant/AceGPT-7b-chat-GPTQ",
+  "model_file_base_name": "gptq_model-4bit-128g"
+}

tokenizer_config.json

@@ -22,7 +22,6 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": {
     "__type": "AddedToken",
@@ -31,6 +30,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "use_default_system_prompt": true
+  }
 }