Upload of AutoGPTQ quantized model

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "build/vietnamese-llama-2-7b-4bit-32g",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

gptq_model-4bit-32g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6abb57d6348925afa805a40411e1b56b74314b8856dc7ec8f1ca92162aa4681
+size 7512816872

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "build/vietnamese-llama-2-7b-4bit-32g",
+  "model_file_base_name": "gptq_model-4bit-32g"
+}