Update README.md

.gitattributes

@@ -1,38 +1,48 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin 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
-*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
-*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
-*.db* filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
-*.ark* filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
-*.gguf* filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
-*.ggml filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
-*.llamafile* filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
-*.pt2 filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.2-3B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f355e9b1a6c69ee7ea297f8b3bb38c44ab00ad7bc9f699babe0a02eae61cf276
+size 1363935520

Llama-3.2-3B-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f778dda3fa1dd1c34747038221113b7940b3b26645e50775bbc8b4a8997040c6
+size 1815347488

Llama-3.2-3B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c7b1e2c11ce80e0de67c3b6aeace40edf6cd0c6606d3c0085117b9c8951669
+size 1687159072

Llama-3.2-3B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f06a24cf262e93c9c25dea3f207593e23293df4732a49cdc887bbf3d145e14
+size 1542848800

Llama-3.2-3B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec4181a9debbcd9213f4c8e6b4b33bd24181feb373332d904839492a8b4169b
+size 1917190432

Llama-3.2-3B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f1a04d927b09ec18eb2f233d85ecd760fc2d35cec97e37f8604d3632210d9a
+size 2019377440

Llama-3.2-3B-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3e5cc3cb1d83b9b9b2876250db8703d93eb23803598eafd3aafe5b5da99d1f
+size 1928200480

Llama-3.2-3B-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c112217953cbe9e97e03ac9e459d1629cf939ccaf669bde8250901cf2277ef4c
+size 2269511968

Llama-3.2-3B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fcbaeaa8e8cd835fd38f2d1daccd58816ba79af262d2335b7454cf0bd21d7cf
+size 2322153760

Llama-3.2-3B-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47518afcfee91bf0b4a6da63ad87774b9dc403a643f3450fb1761fd5a03b59d
+size 2269511968

Llama-3.2-3B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccc943ca31e72526a309b319b15d1ec453cd1c01e27aea4731ccc6a3bfab264
+size 2643853600

Llama-3.2-3B-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f22b7231df5cd1907ff48dba54497b2d7912a4ce60d914f3dcfc0347fa8f21
+size 3421899040

Llama-3.2-3B-Instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ebe8fbb5ab5f05aaa056948668c5f7443df9d0883497f1d9c05f57fb8ea6cd
+size 6433687840

README.md

@@ -1,47 +1,99 @@
 ---
-license: Apache License 2.0
+base_model: meta-llama/Llama-3.2-3B-Instruct
-
+license: llama3.2
-#model-type:
+model_creator: meta
-##如 gpt、phi、llama、chatglm、baichuan 等
+model_name: Llama-3.2-3B-Instruct
-#- gpt
+quantized_by: Second State Inc.
-
+language:
-#domain:
+- en
-##如 nlp、cv、audio、multi-modal
+- de
-#- nlp
+- fr
-
+- it
-#language:
+- pt
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
+- hi
-#- cn 
+- es
-
+- th
-#metrics:
+library_name: transformers
-##如 CIDEr、Blue、ROUGE 等
+pipeline_tag: text-generation
-#- CIDEr
+tags:
-
+- chat
-#tags:
+- llama
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
+- llama-3
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
 
-SDK下载
+<!-- header start -->
-```bash
+<!-- 200823 -->
-#安装ModelScope
+<div style="width: auto; margin-left: auto; margin-right: auto">
-pip install modelscope
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
-```
+</div>
-```python
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
-#SDK模型下载
+<!-- header end -->
-from modelscope import snapshot_download
-model_dir = snapshot_download('second-state/Llama-3.2-3B-Instruct-GGUF')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/second-state/Llama-3.2-3B-Instruct-GGUF.git
-```
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+# Llama-3.2-3B-Instruct-GGUF
+
+## Original Model
+
+[meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.14.5](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.5) and above
+
+- Prompt template
+
+  - Prompt type: `llama-3-chat`
+
+  - Prompt string
+
+    ```text
+    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+    ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template llama-3-chat \
+      --ctx-size 128000 \
+      --model-name Llama-3.2-3b
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Llama-3.2-3B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 581 MB| smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3.2-3B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 733 MB| small, substantial quality loss |
+| [Llama-3.2-3B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 691 MB| very small, high quality loss |
+| [Llama-3.2-3B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 642 MB| very small, high quality loss |
+| [Llama-3.2-3B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 771 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3.2-3B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 808 MB| medium, balanced quality - recommended |
+| [Llama-3.2-3B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 776 MB| small, greater quality loss |
+| [Llama-3.2-3B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 893 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3.2-3B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 912 MB| large, very low quality loss - recommended |
+| [Llama-3.2-3B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 893 MB| large, low quality loss - recommended |
+| [Llama-3.2-3B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 1.02 GB| very large, extremely low quality loss |
+| [Llama-3.2-3B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 1.32 GB| very large, extremely low quality loss - not recommended |
+| [Llama-3.2-3B-Instruct-f16.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-f16.gguf)       | f16    | 16 | 2.48 GB| |
+
+*Quantized with llama.cpp b3807*

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

configuration.json

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