commit 89a7e15b337e5db165c80c0c709206862812a8e0 Author: ModelHub XC Date: Wed Oct 7 14:27:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Qwen2.5-0.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86affa1 --- /dev/null +++ b/.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 +Qwen2.5-0.5B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-0.5B-Instruct-Q2_K.gguf b/Qwen2.5-0.5B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..4a91fa1 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0183050b0aa6a58c451fb558d3fdfa550c3dd6ba835561805778d30bdd79e44a +size 338607424 diff --git a/Qwen2.5-0.5B-Instruct-Q3_K_L.gguf b/Qwen2.5-0.5B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..b294a4b --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acefd39598b7d1e91c7ac2ee9ae0fa1fc3efde0045d6c6f5371163b4653ed145 +size 369358144 diff --git a/Qwen2.5-0.5B-Instruct-Q3_K_M.gguf b/Qwen2.5-0.5B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..4fa30db --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0865856b69d39ef0aa29024e6ceef97799aeba3fc72d8bdc5cd363017fc2b444 +size 355466560 diff --git a/Qwen2.5-0.5B-Instruct-Q3_K_S.gguf b/Qwen2.5-0.5B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..0ed9b04 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3c2f18a215e8b0dcdbd975d672bd9c2c052281c7767feb0f6cc1b389757788 +size 338263360 diff --git a/Qwen2.5-0.5B-Instruct-Q4_0.gguf b/Qwen2.5-0.5B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..a0a2135 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8c81c78cc8ce6e7bf2bd34b87dd86ab9e929a1bb7ce907c41ee5014fdb4451 +size 352154944 diff --git a/Qwen2.5-0.5B-Instruct-Q4_K_M.gguf b/Qwen2.5-0.5B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..8b00053 --- /dev/null +++ b/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 diff --git a/Qwen2.5-0.5B-Instruct-Q4_K_S.gguf b/Qwen2.5-0.5B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..37ea349 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c51f95d2a1dc8a196faf41bc0a1952b1a49e92e9476afe8b131086954faf1b +size 385471808 diff --git a/Qwen2.5-0.5B-Instruct-Q5_0.gguf b/Qwen2.5-0.5B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..f22a35c --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4367efbfe662893372a747982d7fdfcf03907780efbc56ce85405fdd69a7236 +size 396883264 diff --git a/Qwen2.5-0.5B-Instruct-Q5_K_M.gguf b/Qwen2.5-0.5B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..6f1edd8 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3450d966e73cd5ae9c92f493ed56fb60b5d6dbed0f945652e6cc6ce54ea143d3 +size 420086080 diff --git a/Qwen2.5-0.5B-Instruct-Q5_K_S.gguf b/Qwen2.5-0.5B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..45dc703 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2036737cc5df9574995375559c760d4e731885fe7fa8f4d12670a6aadd33e929 +size 412710208 diff --git a/Qwen2.5-0.5B-Instruct-Q6_K.gguf b/Qwen2.5-0.5B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..aea5515 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c7b83b92ade06829df7abc0d85161240f51b008da377482ba411307602ca0e +size 505736512 diff --git a/Qwen2.5-0.5B-Instruct-Q8_0.gguf b/Qwen2.5-0.5B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..23ccd73 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:673eb9fba744c9686488be1ddbb0fbe07b9cf18373bc87c4b1fcab063a7d2aae +size 531068224 diff --git a/Qwen2.5-0.5B-Instruct-f16.gguf b/Qwen2.5-0.5B-Instruct-f16.gguf new file mode 100644 index 0000000..c1b6247 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ad9d1174ce6ab47b584d522634c47e411b75bffdffd9a4e106e21e882392e5 +size 994156864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..db3d10a --- /dev/null +++ b/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 +--- + + + +
+ +
+
+ + +# 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* \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..0dbb161 --- /dev/null +++ b/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 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..09d65e5 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"other","task":"text-generation"} \ No newline at end of file