commit 95a53631bda2906fc4a6e29cf58918236852bd1e Author: ModelHub XC Date: Tue Jun 23 03:45:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Qwen2.5-1.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3fbd013 --- /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 +Qwen2.5-1.5B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Instruct-Q2_K.gguf b/Qwen2.5-1.5B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..6fba112 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3d8542182ba31d4a1a5b8c4ff7d0488b7798deb71b5fa51cb728021b84ddbc +size 676304896 diff --git a/Qwen2.5-1.5B-Instruct-Q3_K_L.gguf b/Qwen2.5-1.5B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..c632c14 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce2be6e4a9c3e3501a2f41e884c33b6a119c446250d050f2746a264920b8c59 +size 880162816 diff --git a/Qwen2.5-1.5B-Instruct-Q3_K_M.gguf b/Qwen2.5-1.5B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..2ff1e57 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc118d0949407aaf662c95e5895c1f7801b2050f40e83e7d06e798817017ce07 +size 824178688 diff --git a/Qwen2.5-1.5B-Instruct-Q3_K_S.gguf b/Qwen2.5-1.5B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..52fd863 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e056ca0b802d5412c40432821c201e4f4d5ed9518d69cfeb6a994a2eb438676c +size 760944640 diff --git a/Qwen2.5-1.5B-Instruct-Q4_0.gguf b/Qwen2.5-1.5B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..c3bca78 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2887331c6e01f2a0fd7163daa5062353fe8939844d83aee69847d4fc842dfe7e +size 934955008 diff --git a/Qwen2.5-1.5B-Instruct-Q4_K_M.gguf b/Qwen2.5-1.5B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..756fb9c --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ffcf166d3467df1c38991fa6196c8798b7e2bb9101d8fa34f6cd3c186913f14 +size 986048512 diff --git a/Qwen2.5-1.5B-Instruct-Q4_K_S.gguf b/Qwen2.5-1.5B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..f3542c7 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5d2141a8fdd863c78cf19ac448a78ad972bfa54c989cd35c845cf032483b06 +size 940312576 diff --git a/Qwen2.5-1.5B-Instruct-Q5_0.gguf b/Qwen2.5-1.5B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..2ec4cbe --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ddd7e4215aa4e812831791d13df4b4a2260278ae2cc222acb03f098c773e9a +size 1098729472 diff --git a/Qwen2.5-1.5B-Instruct-Q5_K_M.gguf b/Qwen2.5-1.5B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..65710a6 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084ad34e9cf4b51db0daa3355f81872f2ae1221cdfe0eb9bcc020a9f311c5660 +size 1125050368 diff --git a/Qwen2.5-1.5B-Instruct-Q5_K_S.gguf b/Qwen2.5-1.5B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..06a76d7 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20c4b91eedc93c1343d1038e5d581cc256b1cac3d03171ec9c66ab525f83a94 +size 1098729472 diff --git a/Qwen2.5-1.5B-Instruct-Q6_K.gguf b/Qwen2.5-1.5B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..7d54f1b --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46baaa4173a5cf6be8f9b0851afc9756da163253fa6da1b413f4db189827df57 +size 1272739840 diff --git a/Qwen2.5-1.5B-Instruct-Q8_0.gguf b/Qwen2.5-1.5B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..48c99d3 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:144ea9981a90447fb1dbbd8f0a872e3dea0f6eed3db2adde402f22b752ea1caa +size 1646573056 diff --git a/Qwen2.5-1.5B-Instruct-f16.gguf b/Qwen2.5-1.5B-Instruct-f16.gguf new file mode 100644 index 0000000..23596c8 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b9e80eacde5690a3a3cf6afcf44a3d53cdab6e0b777552fb64f055efc658956 +size 3093669376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3b1109 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: Qwen/Qwen2.5-1.5B-Instruct +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE +model_creator: Qwen +model_name: Qwen2.5-1.5B-Instruct +quantized_by: Second State Inc. +language: +- en +pipeline_tag: text-generation +tags: +- chat +--- + + + +
+ +
+
+ + +# Qwen2.5-1.5B-Instruct-GGUF + +## Original Model + +[Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) 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:Qwen2.5-1.5B-Instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --model-name Qwen2.5-1.5B-Instruct \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-1.5B-Instruct-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Qwen2.5-1.5B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q2_K.gguf) | Q2_K | 2 | 676 MB| smallest, significant quality loss - not recommended for most purposes | +| [Qwen2.5-1.5B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 880 MB| small, substantial quality loss | +| [Qwen2.5-1.5B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 824 MB| very small, high quality loss | +| [Qwen2.5-1.5B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 761 MB| very small, high quality loss | +| [Qwen2.5-1.5B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 935 MB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Qwen2.5-1.5B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 986 MB| medium, balanced quality - recommended | +| [Qwen2.5-1.5B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 940 MB| small, greater quality loss | +| [Qwen2.5-1.5B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 1.1 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Qwen2.5-1.5B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 1.13 GB| large, very low quality loss - recommended | +| [Qwen2.5-1.5B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 1.1 GB| large, low quality loss - recommended | +| [Qwen2.5-1.5B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q6_K.gguf) | Q6_K | 6 | 1.27 GB| very large, extremely low quality loss | +| [Qwen2.5-1.5B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 1.65 GB| very large, extremely low quality loss - not recommended | +| [Qwen2.5-1.5B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-1.5B-Instruct-GGUF/blob/main/Qwen2.5-1.5B-Instruct-f16.gguf) | f16 | 16 | 3.09 GB| | + +*Quantized with llama.cpp b3751* diff --git a/config.json b/config.json new file mode 100644 index 0000000..f81ead1 --- /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": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "max_position_embeddings": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "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..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file