初始化项目，由ModelHub XC社区提供模型

Model: ModelCloud.AI/Meta-Llama-3.1-8B-gptq-4bit
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,49 @@
+---
+tags:
+- gptq
+- 4bit
+- int4
+- gptqmodel
+- modelcloud
+- llama-3.1
+- 8b
+- base
+license: llama3.1
+---
+This model has been quantized using [GPTQModel](https://github.com/ModelCloud/GPTQModel).
+
+- **bits**: 4
+- **group_size**: 128
+- **desc_act**: true
+- **static_groups**: false
+- **sym**: true
+- **lm_head**: false
+- **damp_percent**: 0.01
+- **true_sequential**: true
+- **model_name_or_path**: ""
+- **model_file_base_name**: "model"
+- **quant_method**: "gptq"
+- **checkpoint_format**: "gptq"
+- **meta**：
+  - **quantizer**: "gptqmodel:0.9.9-dev0"
+
+**Here is an example:**
+```python
+import torch
+from transformers import AutoTokenizer
+from gptqmodel import GPTQModel
+
+device = torch.device("cuda:0")
+
+model_name = "ModelCloud/Meta-Llama-3.1-8B-gptq-4bit"
+
+prompt = "I am in Shanghai, preparing to visit the natural history museum. Can you tell me the best way to"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+model = GPTQModel.from_quantized(model_name)
+
+inputs = tokenizer(prompt, return_tensors="pt").to(device)
+res = model.generate(**inputs, num_beams=1, min_new_tokens=1, max_new_tokens=512)
+print(tokenizer.decode(res[0]))
+```

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "/model/Meta-Llama-3.1-8B/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "quantizer": "gptqmodel:0.9.9-dev0"
+    },
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86186c3c932e2134efd3495d9ebb5ed4a5c9fb7e9484cfb0719ff06b366e038
+size 5732943672

quantize_config.json

@@ -0,0 +1,17 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "lm_head": false,
+  "damp_percent": 0.01,
+  "true_sequential": true,
+  "model_name_or_path": "",
+  "model_file_base_name": "",
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "meta": {
+    "quantizer": "gptqmodel:0.9.9-dev0"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}