GPTQ model commit

config.json

@@ -0,0 +1,55 @@
+{
+    "_name_or_path": "/workspace/process/01-ai_yi-6b/source",
+    "architectures": [
+        "YiForCausalLM"
+    ],
+    "auto_map": {
+        "AutoConfig": "configuration_yi.YiConfig",
+        "AutoModel": "modeling_yi.YiModel",
+        "AutoModelForCausalLM": "modeling_yi.YiForCausalLM"
+    },
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 4096,
+    "model_type": "Yi",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "quantization_config": {
+        "batch_size": 1,
+        "bits": 4,
+        "block_name_to_quantize": "model.layers",
+        "cache_block_outputs": true,
+        "damp_percent": 0.1,
+        "desc_act": true,
+        "exllama_config": {
+            "version": 1
+        },
+        "group_size": 128,
+        "max_input_length": null,
+        "model_seqlen": 4096,
+        "module_name_preceding_first_block": [
+            "model.embed_tokens"
+        ],
+        "pad_token_id": null,
+        "quant_method": "gptq",
+        "sym": true,
+        "tokenizer": null,
+        "true_sequential": true,
+        "use_cuda_fp16": false,
+        "use_exllama": false
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 5000000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.35.0",
+    "use_cache": true,
+    "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb0b667cb7eb3e68b3dcfa388ec882005e349764ef56da540e65a018cb6439c
+size 3932430856

quantize_config.json

@@ -0,0 +1,8 @@
+{
+    "bits": 8,
+    "group_size": 128,
+    "damp_percent": 0.1,
+    "desc_act": true,
+    "sym": true,
+    "true_sequential": true
+}