初始化项目，由ModelHub XC社区提供模型

Model: second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +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
+*.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
+Qwen2.5-Coder-0.5B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-0.5B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

Qwen2.5-Coder-0.5B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a7a3370a5ff5412ee2c1a91cbbd9d2e6b072d411ba767e8242747553c5b58d
+size 338607488

Qwen2.5-Coder-0.5B-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbce8e1c400730a703648f5fa3da7e7a5b77efbe7d321e184f8cc1608326f65
+size 369358208

Qwen2.5-Coder-0.5B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecdca13d5c05edfddc23b7920e5b5fb4665d357431438a246d1b0d2b58958483
+size 355466624

Qwen2.5-Coder-0.5B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8ce86fbc87c52a8d6cd264104b13d21b783c8cf67680bf417bda8664f69741
+size 338263424

Qwen2.5-Coder-0.5B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12fe9e369bd976e9a3d4bda7ad61995c1c5cc793023a483d1115216a8f8a038b
+size 352155008

Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0bf6ffd20ed4f72a3a56edf8e6f7337eb0d09166d9ed3a7da6b87d27ad5812
+size 397808000

Qwen2.5-Coder-0.5B-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80bcd0b3fc9c464b0f7a48b2b8b5ea17925670077056b3aa494c373c9683a0c
+size 385471872

Qwen2.5-Coder-0.5B-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ab0a8ea7d14be4082bed59aeaf8f99c131ea59576959b9ea7c746a05f1dfcb
+size 396883328

Qwen2.5-Coder-0.5B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596a7ded4269d30f909397e3809e6869e337b7e17a79ec240ab75d8696b80c7b
+size 420086144

Qwen2.5-Coder-0.5B-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b788c5dff45df65d90d9008587fd71a0097f80a7ad2aaf887938f1cb4bd64e5
+size 412710272

Qwen2.5-Coder-0.5B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d630bdef5309911491d7833b8a7f643e52ccf716a1d3e289376cdcf051dc313f
+size 505736576

Qwen2.5-Coder-0.5B-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0bc8b468ee0e9c7918273e89d056ec2e583a3d0a5f7308215b33762e63af26
+size 531068288

Qwen2.5-Coder-0.5B-Instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44732b10856f1137245774806a1ba1d762cd4ae6bd559aabe9e6503cad0b466
+size 994156928

README.md

@@ -0,0 +1,91 @@
+---
+base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct/blob/main/LICENSE
+model_creator: Qwen
+model_name: Qwen2.5-Coder-0.5B-Instruct
+quantized_by: Second State Inc.
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- code
+- codeqwen
+- chat
+- qwen
+- qwen-coder
+language:
+- en
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Qwen2.5-Coder-0.5B-Instruct-GGUF
+
+## Original Model
+
+[Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.14.14](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.14) and above
+
+- Prompt template
+
+  - Prompt type: `chatml`
+
+  - Prompt string
+
+    ```text
+    <|im_start|>system
+    {system_message}<|im_end|>
+    <|im_start|>user
+    {prompt}<|im_end|>
+    <|im_start|>assistant
+    ```
+
+- Context size: `32000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Coder-0.5B-Instruct-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name Qwen2.5-Coder-0.5B-Instruct \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Coder-0.5B-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Qwen2.5-Coder-0.5B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 339 MB| smallest, significant quality loss - not recommended for most purposes |
+| [Qwen2.5-Coder-0.5B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 369 MB| small, substantial quality loss |
+| [Qwen2.5-Coder-0.5B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 355 MB| very small, high quality loss |
+| [Qwen2.5-Coder-0.5B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 338 MB| very small, high quality loss |
+| [Qwen2.5-Coder-0.5B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 352 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 398 MB| medium, balanced quality - recommended |
+| [Qwen2.5-Coder-0.5B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 385 MB| small, greater quality loss |
+| [Qwen2.5-Coder-0.5B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 397 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Qwen2.5-Coder-0.5B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 420 MB| large, very low quality loss - recommended |
+| [Qwen2.5-Coder-0.5B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 413 MB| large, low quality loss - recommended |
+| [Qwen2.5-Coder-0.5B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 506 MB| very large, extremely low quality loss |
+| [Qwen2.5-Coder-0.5B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 531 MB| very large, extremely low quality loss - not recommended |
+| [Qwen2.5-Coder-0.5B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF/blob/main/Qwen2.5-Coder-0.5B-Instruct-f16.gguf)       | f16    | 16 | 994 MB| |
+
+*Quantized with llama.cpp b4033*

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}