Simple Qwen2.5-0.5-Instruct-GGUF

.gitattributes

@@ -0,0 +1 @@
+Qwen2.5-0.5B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750f8f144f0504208add7897f01c7d2350a7363d8855eab59e137a1041e90394
+size 397807936

README.md

@@ -0,0 +1,86 @@
+---
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE
+model_creator: Qwen
+model_name: Qwen2.5-0.5B-Instruct
+quantized_by: Second State Inc.
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+
+<!-- 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 -->
+
+# Qwen2.5-0.5B-Instruct-GGUF
+
+## Original Model
+
+[Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3)
+
+- 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:Qwen2.5-0.5B-Instruct-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name Qwen2.5-0.5B-Instruct \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-0.5B-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Qwen2.5-0.5B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 339 MB| smallest, significant quality loss - not recommended for most purposes |
+| [Qwen2.5-0.5B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 369 MB| small, substantial quality loss |
+| [Qwen2.5-0.5B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 355 MB| very small, high quality loss |
+| [Qwen2.5-0.5B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 338 MB| very small, high quality loss |
+| [Qwen2.5-0.5B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 352 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Qwen2.5-0.5B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 398 MB| medium, balanced quality - recommended |
+| [Qwen2.5-0.5B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 385 MB| small, greater quality loss |
+| [Qwen2.5-0.5B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 397 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Qwen2.5-0.5B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 420 MB| large, very low quality loss - recommended |
+| [Qwen2.5-0.5B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 413 MB| large, low quality loss - recommended |
+| [Qwen2.5-0.5B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 506 MB| very large, extremely low quality loss |
+| [Qwen2.5-0.5B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 531 MB| very large, extremely low quality loss - not recommended |
+| [Qwen2.5-0.5B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-f16.gguf)       | f16    | 16 | 994 MB| |
+
+*Quantized with llama.cpp b4466*

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
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"other","task":"text-generation"}