初始化项目，由ModelHub XC社区提供模型

Model: ModelCloud/Qwen1.5-1.8B-Chat-GPTQ-4bits-dynamic-cfg-with-lm_head-symTrue
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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,66 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "/root/.cache/huggingface/hub/models--Qwen--Qwen1.5-1.8B-Chat/snapshots/e482ee3f73c375a627a16fdf66fd0c8279743ca6",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": true,
+    "dynamic": {
+      "-:model\\.layers\\.([2-9]\\d*|[1-9]\\d+)\\..*": {},
+      ".*\\.1\\..*": {
+        "bits": 8,
+        "desc_act": false,
+        "group_size": 32
+      },
+      "lm_head": {
+        "bits": 8,
+        "desc_act": false,
+        "group_size": 32,
+        "mse": 2.4,
+        "sym": true
+      }
+    },
+    "group_size": 128,
+    "lm_head": true,
+    "meta": {
+      "damp_auto_increment": 0.0025,
+      "damp_percent": 0.01,
+      "mse": 0.0,
+      "quantizer": [
+        "gptqmodel:1.8.0-dev"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel"
+    },
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26554734410865a68f3771a55ca6b89c2c4321cacc79125336b3392638aa1835
+size 3271099656

quant_log.csv

@@ -0,0 +1,16 @@
+layer,module,loss,damp,time
+0,self_attn.k_proj,0.38340,0.01000,0.985
+0,self_attn.v_proj,0.00899,0.01000,0.332
+0,self_attn.q_proj,0.52614,0.01000,0.327
+0,self_attn.o_proj,0.00033,0.01000,0.326
+0,mlp.up_proj,1.90171,0.01000,0.348
+0,mlp.gate_proj,1.81718,0.01000,0.366
+0,mlp.down_proj,0.04200,0.01000,0.950
+1,self_attn.k_proj,0.00821,0.01000,0.338
+1,self_attn.v_proj,0.00108,0.01000,0.329
+1,self_attn.q_proj,0.00811,0.01000,0.329
+1,self_attn.o_proj,0.00003,0.01000,0.347
+1,mlp.up_proj,0.00614,0.01000,0.370
+1,mlp.gate_proj,0.00698,0.01000,0.383
+1,mlp.down_proj,0.00040,0.01000,0.944
+24,lm_head,23.30706,0.01000,4.334

quantize_config.json

@@ -0,0 +1,36 @@
+{
+  "bits": 4,
+  "dynamic": {
+    "-:model\\.layers\\.([2-9]\\d*|[1-9]\\d+)\\..*": {},
+    ".*\\.1\\..*": {
+      "bits": 8,
+      "desc_act": false,
+      "group_size": 32
+    },
+    "lm_head": {
+      "bits": 8,
+      "group_size": 32,
+      "sym": true,
+      "desc_act": false,
+      "mse": 2.4
+    }
+  },
+  "group_size": 128,
+  "desc_act": true,
+  "sym": true,
+  "lm_head": true,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:1.8.0-dev"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.01,
+    "damp_auto_increment": 0.0025,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0
+  }
+}

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "unk_token": null,
+  "_commit_hash": null
+}