commit 73de92f5cd710e73c64545ee7aac7c218540ed65 Author: ModelHub XC Date: Sat Jul 18 09:47:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5579c73 --- /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 +Qwen3-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Q2_K.gguf b/Qwen3-4B-Q2_K.gguf new file mode 100644 index 0000000..43dacfb --- /dev/null +++ b/Qwen3-4B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4137b8e36be72a8fc23071a0d6ee074c139962f1766124e3b33b0f803cd8ea8a +size 1669499072 diff --git a/Qwen3-4B-Q3_K_L.gguf b/Qwen3-4B-Q3_K_L.gguf new file mode 100644 index 0000000..b4e8ad4 --- /dev/null +++ b/Qwen3-4B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c8c8be9614857d606481f2b27a2ce1f03b466d3e7e3b289ad8777a3b75c717 +size 2239785152 diff --git a/Qwen3-4B-Q3_K_M.gguf b/Qwen3-4B-Q3_K_M.gguf new file mode 100644 index 0000000..e7d3634 --- /dev/null +++ b/Qwen3-4B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce9e04b4d275a36942656ce33e6e197be2fb501d70d935b3ecc85c47f36898b +size 2075617472 diff --git a/Qwen3-4B-Q3_K_S.gguf b/Qwen3-4B-Q3_K_S.gguf new file mode 100644 index 0000000..fd1c888 --- /dev/null +++ b/Qwen3-4B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48550febf50d478fedd3e719cb5b037eee3ac016c9bf7fd8cfaef62c08b37737 +size 1886996672 diff --git a/Qwen3-4B-Q4_0.gguf b/Qwen3-4B-Q4_0.gguf new file mode 100644 index 0000000..3f9767e --- /dev/null +++ b/Qwen3-4B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e452384b46da669745e1b3c96d60766209d6ce7f8980b09d869cf8f471f340 +size 2369546432 diff --git a/Qwen3-4B-Q4_K_M.gguf b/Qwen3-4B-Q4_K_M.gguf new file mode 100644 index 0000000..192bea2 --- /dev/null +++ b/Qwen3-4B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d65a858f9d257bb930a37d460ec1d3d8e7d4330173cc601dfc2053a5379ee6c +size 2497280192 diff --git a/Qwen3-4B-Q4_K_S.gguf b/Qwen3-4B-Q4_K_S.gguf new file mode 100644 index 0000000..fd10cff --- /dev/null +++ b/Qwen3-4B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e8d5cee60a9c23bd9f79ea8fc304b2edb9c6bd71e700604a53e76370577fcd2 +size 2383308992 diff --git a/Qwen3-4B-Q5_0.gguf b/Qwen3-4B-Q5_0.gguf new file mode 100644 index 0000000..813a1ea --- /dev/null +++ b/Qwen3-4B-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabdcf5d8879ba4598bd06064796b84c788aab87bd71e3f2d6b51b61bff25e4a +size 2823710912 diff --git a/Qwen3-4B-Q5_K_M.gguf b/Qwen3-4B-Q5_K_M.gguf new file mode 100644 index 0000000..49e2971 --- /dev/null +++ b/Qwen3-4B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0f6ab85a4244cc359d28190bf2718b2bbafc1fdc1a233a38c7aa01f2ab09ee +size 2889513152 diff --git a/Qwen3-4B-Q5_K_S.gguf b/Qwen3-4B-Q5_K_S.gguf new file mode 100644 index 0000000..618eee4 --- /dev/null +++ b/Qwen3-4B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbbfdb762bba9a2946036e8777c7e74fdd4648499e26cd76ed2d4003add08e9 +size 2823710912 diff --git a/Qwen3-4B-Q6_K.gguf b/Qwen3-4B-Q6_K.gguf new file mode 100644 index 0000000..1c9f87f --- /dev/null +++ b/Qwen3-4B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20db9333940a1f59aeb84be20bf99fe5aab23124cd030f96c9db980cda3ef25 +size 3306260672 diff --git a/Qwen3-4B-Q8_0.gguf b/Qwen3-4B-Q8_0.gguf new file mode 100644 index 0000000..96eab13 --- /dev/null +++ b/Qwen3-4B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a3c23ddd75ff5648f753549a71a75184fbf94cffe30feff2bd3c6ea673dc7d +size 4280404672 diff --git a/Qwen3-4B-f16.gguf b/Qwen3-4B-f16.gguf new file mode 100644 index 0000000..1286146 --- /dev/null +++ b/Qwen3-4B-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954dd741fedcd7ca7fb9ec1133fc610906ad7e554c8609c7b43f9ace5c6e452e +size 8051284672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..de82dfc --- /dev/null +++ b/README.md @@ -0,0 +1,109 @@ +--- +base_model: Qwen/Qwen3-4B +license: other +license_name: qwen-research +license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE +model_creator: Qwen +model_name: Qwen3-4B +quantized_by: Second State Inc. +language: +- en +pipeline_tag: text-generation +tags: +- chat +--- + + + +
+ +
+
+ + +# Qwen3-4B-GGUF + +## Original Model + +[Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) + +## Run with LlamaEdge + +- LlamaEdge version: + + - Thinking: [v0.17.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.17.0) and above + - No Thinking: [v0.18.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.18.2) + +- Prompt template + + - Prompt type: `chatml` (for thinking) + + - Prompt string + + ```text + <|im_start|>system + {system_message}<|im_end|> + <|im_start|>user + {prompt}<|im_end|> + <|im_start|>assistant + ``` + + - Prompt type: `qwen3-no-think` (for no thinking) + + - Prompt string + + ```text + <|im_start|>system + {system_message}<|im_end|> + <|im_start|>user + {user_message_1}<|im_end|> + <|im_start|>assistant + {assistant_message_1}<|im_end|> + <|im_start|>user + {user_message_2}<|im_end|> + <|im_start|>assistant + + + + ``` + +- Context size: `128000` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-4B-Q5_K_M.gguf \ + llama-api-server.wasm \ + --model-name Qwen3-4B \ + --prompt-template chatml \ + --ctx-size 128000 + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-4B-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --ctx-size 128000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Qwen3-4B-Q2_K.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q2_K.gguf) | Q2_K | 2 | 1.67 GB| smallest, significant quality loss - not recommended for most purposes | +| [Qwen3-4B-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q3_K_L.gguf) | Q3_K_L | 3 | 2.24 GB| small, substantial quality loss | +| [Qwen3-4B-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q3_K_M.gguf) | Q3_K_M | 3 | 2.08 GB| very small, high quality loss | +| [Qwen3-4B-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q3_K_S.gguf) | Q3_K_S | 3 | 1.89 GB| very small, high quality loss | +| [Qwen3-4B-Q4_0.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q4_0.gguf) | Q4_0 | 4 | 2.37 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Qwen3-4B-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q4_K_M.gguf) | Q4_K_M | 4 | 2.50 GB| medium, balanced quality - recommended | +| [Qwen3-4B-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q4_K_S.gguf) | Q4_K_S | 4 | 2.38 GB| small, greater quality loss | +| [Qwen3-4B-Q5_0.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q5_0.gguf) | Q5_0 | 5 | 2.82 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Qwen3-4B-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q5_K_M.gguf) | Q5_K_M | 5 | 2.89 GB| large, very low quality loss - recommended | +| [Qwen3-4B-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q5_K_S.gguf) | Q5_K_S | 5 | 2.82 GB| large, low quality loss - recommended | +| [Qwen3-4B-Q6_K.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q6_K.gguf) | Q6_K | 6 | 3.31 GB| very large, extremely low quality loss | +| [Qwen3-4B-Q8_0.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q8_0.gguf) | Q8_0 | 8 | 4.28 GB| very large, extremely low quality loss - not recommended | +| [Qwen3-4B-f16.gguf](https://huggingface.co/second-state/Qwen3-4B-GGUF/blob/main/Qwen3-4B-f16.gguf) | f16 | 16 | 8.05 GB| | + +*Quantized with llama.cpp b5097* diff --git a/config.json b/config.json new file mode 100644 index 0000000..e49eccd --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file