commit dfb83cc2da40c74af50e9e45adf001a16f7508d7 Author: ModelHub XC Date: Fri May 29 10:10:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Qwen2-0.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1941c9 --- /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 +Qwen2-0.5B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-0.5B-Instruct-Q2_K.gguf b/Qwen2-0.5B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..e1df7b5 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3000fc3c69fd3c99722ad4e3113e3ba18bcb4335699c5be9f6fb0a567c416a23 +size 338604448 diff --git a/Qwen2-0.5B-Instruct-Q3_K_L.gguf b/Qwen2-0.5B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..34d3d0d --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:966cb6b543c3f6a4126c3b09e2972112d5c3dce9c176eea7d74a58737f5f9cdd +size 369355168 diff --git a/Qwen2-0.5B-Instruct-Q3_K_M.gguf b/Qwen2-0.5B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..27ea787 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cd8353e85bdb5085879f2080885a8ffe397c9335c63523a86785c8dc42a1c3 +size 355463584 diff --git a/Qwen2-0.5B-Instruct-Q3_K_S.gguf b/Qwen2-0.5B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..4d91f70 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16cadcfd71015377232c03990ed14ca62021bb2fe8d7fd549f3126cf778157cc +size 338260384 diff --git a/Qwen2-0.5B-Instruct-Q4_0.gguf b/Qwen2-0.5B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..4fe4442 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9373c66a6959f443e0f972fea89660ee5b3fdca2a62ec21026213b58c33e447 +size 352151968 diff --git a/Qwen2-0.5B-Instruct-Q4_K_M.gguf b/Qwen2-0.5B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..bcaec0e --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb5f495a0ef110a480e08da05552abb86daddae561f7fa806a97ae31120694b +size 397804960 diff --git a/Qwen2-0.5B-Instruct-Q4_K_S.gguf b/Qwen2-0.5B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..03cd233 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3764dae384628ec9327db15a84e7ebab473d180a170454d6a4529b9fa8e76a +size 385468832 diff --git a/Qwen2-0.5B-Instruct-Q5_0.gguf b/Qwen2-0.5B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..8c04cdb --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbf462b3ca65685e3075fee1d35b5183f7630e27ef75addd15851b0c1dd9927 +size 396880288 diff --git a/Qwen2-0.5B-Instruct-Q5_K_M.gguf b/Qwen2-0.5B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..959fda3 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c08198a2ac03049b310e6f9b204fdfd726527ae502e55443e028a084ab9de0 +size 420083104 diff --git a/Qwen2-0.5B-Instruct-Q5_K_S.gguf b/Qwen2-0.5B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..8a2db90 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cebd32cf89327174d9acce3da7c4c40153b4476324bf13428242b03528919774 +size 412707232 diff --git a/Qwen2-0.5B-Instruct-Q6_K.gguf b/Qwen2-0.5B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..7e5c191 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:357a1e8ed8927bd08c7c89e8cd8ad61fe5a6e880467e06e4416611f669bfba49 +size 505733536 diff --git a/Qwen2-0.5B-Instruct-Q8_0.gguf b/Qwen2-0.5B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..46e1871 --- /dev/null +++ b/Qwen2-0.5B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da8296aa74aced58f4df45b611683a55e96b598b706db04ab96c7201478dc0e6 +size 531065248 diff --git a/Qwen2-0.5B-Instruct-f16.gguf b/Qwen2-0.5B-Instruct-f16.gguf new file mode 100644 index 0000000..ecfb27b --- /dev/null +++ b/Qwen2-0.5B-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07de5ee9a80150a00b07de2b47003a2312296338296ad3d24766effbafdb4b9 +size 994153888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ede18e1 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: Qwen/Qwen2-0.5B-Instruct +license: apache-2.0 +model_creator: Qwen +model_name: Qwen2-0.5B-Instruct +quantized_by: Second State Inc. +language: +- en +pipeline_tag: text-generation +tags: +- chat +--- + + + +
+ +
+
+ + +# Qwen2-0.5B-Instruct-GGUF + +## Original Model + +[Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.11.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.11.2) + +- 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:Qwen2-0.5B-Instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --model-name Qwen2-0.5B-Instruct \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2-0.5B-Instruct-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Qwen2-0.5B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q2_K.gguf) | Q2_K | 2 | 339 MB| smallest, significant quality loss - not recommended for most purposes | +| [Qwen2-0.5B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 369 MB| small, substantial quality loss | +| [Qwen2-0.5B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 355 MB| very small, high quality loss | +| [Qwen2-0.5B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 338 MB| very small, high quality loss | +| [Qwen2-0.5B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 352 MB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Qwen2-0.5B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 398 MB| medium, balanced quality - recommended | +| [Qwen2-0.5B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 385 MB| small, greater quality loss | +| [Qwen2-0.5B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 397 MB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Qwen2-0.5B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 420 MB| large, very low quality loss - recommended | +| [Qwen2-0.5B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 413 MB| large, low quality loss - recommended | +| [Qwen2-0.5B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q6_K.gguf) | Q6_K | 6 | 506 MB| very large, extremely low quality loss | +| [Qwen2-0.5B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 531 MB| very large, extremely low quality loss - not recommended | +| [Qwen2-0.5B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2-0.5B-Instruct-GGUF/blob/main/Qwen2-0.5B-Instruct-f16.gguf) | f16 | 16 | 994 MB| | + +*Quantized with llama.cpp b3705* diff --git a/config.json b/config.json new file mode 100644 index 0000000..463b055 --- /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": 24, + "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": "4.40.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file