commit 430bdff488762b9f07f9b18054ff08e2a579ab36 Author: ModelHub XC Date: Tue May 26 23:24:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Qwen1.5-4B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f15b49c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +*.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-4B-Chat-Q2_K.gguf b/Qwen1.5-4B-Chat-Q2_K.gguf new file mode 100644 index 0000000..e311a97 --- /dev/null +++ b/Qwen1.5-4B-Chat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c28627bf7a840d9a094c8c9cecc6fc5d62ad927cd04b62653931d91a12d57bde +size 1620632608 diff --git a/Qwen1.5-4B-Chat-Q3_K_L.gguf b/Qwen1.5-4B-Chat-Q3_K_L.gguf new file mode 100644 index 0000000..0cd45f9 --- /dev/null +++ b/Qwen1.5-4B-Chat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597df628a380c1d1fbf2b8ac2e12db29b9ff906bb9d83efbbb22db29c3ee6239 +size 2174798368 diff --git a/Qwen1.5-4B-Chat-Q3_K_M.gguf b/Qwen1.5-4B-Chat-Q3_K_M.gguf new file mode 100644 index 0000000..2134c2c --- /dev/null +++ b/Qwen1.5-4B-Chat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d939712dd6f1c0dfc7e023d37a5d48326051617e4c607f196ae0513078a1822 +size 2026850848 diff --git a/Qwen1.5-4B-Chat-Q3_K_S.gguf b/Qwen1.5-4B-Chat-Q3_K_S.gguf new file mode 100644 index 0000000..2e772bb --- /dev/null +++ b/Qwen1.5-4B-Chat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5501324e8aa4dd623b4f27eaf38c72ec1aa8984e0f7c25336a930f98ab8e1db3 +size 1857153568 diff --git a/Qwen1.5-4B-Chat-Q4_0.gguf b/Qwen1.5-4B-Chat-Q4_0.gguf new file mode 100644 index 0000000..985f83a --- /dev/null +++ b/Qwen1.5-4B-Chat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3826c9a08ae4b37b8c076031052db8f50150e46e5210c83471fe3c08b41b8f77 +size 2330085408 diff --git a/Qwen1.5-4B-Chat-Q4_K_M.gguf b/Qwen1.5-4B-Chat-Q4_K_M.gguf new file mode 100644 index 0000000..b4f0ee0 --- /dev/null +++ b/Qwen1.5-4B-Chat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c4900818f8419cf6a071309059275deb8466898f8f16693f955ba5dab52cf67 +size 2455115808 diff --git a/Qwen1.5-4B-Chat-Q4_K_S.gguf b/Qwen1.5-4B-Chat-Q4_K_S.gguf new file mode 100644 index 0000000..6bbbf6e --- /dev/null +++ b/Qwen1.5-4B-Chat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db00ef89021ea33c13313c3292b1a63c62ca471dd4ac8a1868013ff28ecf313 +size 2344421408 diff --git a/Qwen1.5-4B-Chat-Q5_0.gguf b/Qwen1.5-4B-Chat-Q5_0.gguf new file mode 100644 index 0000000..183865e --- /dev/null +++ b/Qwen1.5-4B-Chat-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f67ce7f191685c9e206ab9ce5cc58f34e05e194bc36aa27751b90257a59132c +size 2775197728 diff --git a/Qwen1.5-4B-Chat-Q5_K_M.gguf b/Qwen1.5-4B-Chat-Q5_K_M.gguf new file mode 100644 index 0000000..5c7eee3 --- /dev/null +++ b/Qwen1.5-4B-Chat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96aba89e7251b9724fdacfdaec8ec1be36e25a4d6ff3fb5072dd59aa7738df8a +size 2839607328 diff --git a/Qwen1.5-4B-Chat-Q5_K_S.gguf b/Qwen1.5-4B-Chat-Q5_K_S.gguf new file mode 100644 index 0000000..457a652 --- /dev/null +++ b/Qwen1.5-4B-Chat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f1d9f356c7beec20fbe4c634a7fc9077e22093cfc011b35779366f1a5943d7 +size 2775197728 diff --git a/Qwen1.5-4B-Chat-Q6_K.gguf b/Qwen1.5-4B-Chat-Q6_K.gguf new file mode 100644 index 0000000..721c51e --- /dev/null +++ b/Qwen1.5-4B-Chat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656172e925f4579416de2c7cb7e08edfc27701235f357ca34d0db18ce0eecf69 +size 3248129568 diff --git a/Qwen1.5-4B-Chat-Q8_0.gguf b/Qwen1.5-4B-Chat-Q8_0.gguf new file mode 100644 index 0000000..45015e6 --- /dev/null +++ b/Qwen1.5-4B-Chat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb921eb87e9892abb77cc350d69fd77fff1e98b1bd8c6f2f0aa3e12b3ddb70d +size 4204735008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c68f06d --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Qwen/Qwen1.5-4B-Chat +license: other +license_name: tongyi-qianwen-research +license_link: >- + https://huggingface.co/Qwen/Qwen1.5-4B-Chat/blob/main/LICENSE +model_creator: Qwen +model_name: Qwen1.5 4B Chat +quantized_by: Second State Inc. +language: +- en +pipeline_tag: text-generation +tags: +- chat +--- + + + +
+ +
+
+ + +# Qwen1.5-4B-Chat-GGUF + +## Original Model + +[Qwen/Qwen1.5-4B-Chat](https://huggingface.co/Qwen/Qwen1.5-4B-Chat) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.15](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.15) 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:Qwen1.5-4B-Chat-Q5_K_M.gguf llama-api-server.wasm -p chatml + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-4B-Chat-Q5_K_M.gguf llama-chat.wasm -p chatml + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Qwen1.5-4B-Chat-Q2_K.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q2_K.gguf) | Q2_K | 2 | 1.62 GB| smallest, significant quality loss - not recommended for most purposes | +| [Qwen1.5-4B-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 2.17 GB| small, substantial quality loss | +| [Qwen1.5-4B-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 2.03 GB| very small, high quality loss | +| [Qwen1.5-4B-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 1.86 GB| very small, high quality loss | +| [Qwen1.5-4B-Chat-Q4_0.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q4_0.gguf) | Q4_0 | 4 | 2.33 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Qwen1.5-4B-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 2.46 GB| medium, balanced quality - recommended | +| [Qwen1.5-4B-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 2.34 GB| small, greater quality loss | +| [Qwen1.5-4B-Chat-Q5_0.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q5_0.gguf) | Q5_0 | 5 | 2.78 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Qwen1.5-4B-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 2.84 GB| large, very low quality loss - recommended | +| [Qwen1.5-4B-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 2.78 GB| large, low quality loss - recommended | +| [Qwen1.5-4B-Chat-Q6_K.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q6_K.gguf) | Q6_K | 6 | 3.25 GB| very large, extremely low quality loss | +| [Qwen1.5-4B-Chat-Q8_0.gguf](https://huggingface.co/second-state/Qwen1.5-4B-Chat-GGUF/blob/main/Qwen1.5-4B-Chat-Q8_0.gguf) | Q8_0 | 8 | 4.2 GB| very large, extremely low quality loss - not recommended | diff --git a/config.json b/config.json new file mode 100644 index 0000000..2d4480c --- /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": 2560, + "initializer_range": 0.02, + "intermediate_size": 6912, + "max_position_embeddings": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 20, + "num_hidden_layers": 40, + "num_key_value_heads": 20, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000.0, + "sliding_window": 32768, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.0", + "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