first

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

.gitignore

@@ -0,0 +1 @@
+*.bin

README.md

@@ -0,0 +1,21 @@
+# 经过本人合成及量化的 7B/13B 模型
+<hr>
+
+> #### 开这个仓，主要是为了给大家讲述使用方法，这玩意儿真得自己摸索啊。
+
+### 直接使用方法
+
+移动本仓库中的`llama-7b-hf`和`llama-13b-hf`两个文件夹，到你项目的`./models`文件下即可。该文件夹同时适用于`llama.cpp`和`text-generation-webui`。
+
+### DIY 使用方法
+
+以 7B 为例：
+
+1. 在 models 文件下新建名为`llama-7b-hf`的文件夹，注意，此名字不可以随意修改
+2. `llama-7b-hf`下只需要有两个文件：`config.json`和`ggml-model-q4_0.bin`
+3. `config.json`大家可以到基础库里面下载
+4. `ggml-model-q4_0.bin`就是你按照[教程](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki/llama.cpp%E9%87%8F%E5%8C%96%E9%83%A8%E7%BD%B2#step-2-%E7%94%9F%E6%88%90%E9%87%8F%E5%8C%96%E7%89%88%E6%9C%AC%E6%A8%A1%E5%9E%8B)合成出来的最终文件
+
+### 资料来源
+
+7b 为我自己合成，13b 是从 https://huggingface.co/minlik/chinese-alpaca-13b-quantized 仓库里下载的。

llama-13b-hf/config.json

@@ -0,0 +1 @@
+{"architectures": ["LLaMAForCausalLM"], "bos_token_id": 0, "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 4096, "intermediate_size": 11008, "initializer_range": 0.02, "max_sequence_length": 2048, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "pad_token_id": -1, "rms_norm_eps": 1e-06, "torch_dtype": "float16", "transformers_version": "4.27.0.dev0", "use_cache": true, "vocab_size": 32000}

llama-7b-hf/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "decapoda-research/llama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 49954
+}