commit 59082598e4562560766e9818449b6272753f3c89 Author: ModelHub XC Date: Sat Sep 12 18:32:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Qwen2-0.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aee2bfe --- /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-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-0.5B-Q2_K.gguf b/Qwen2-0.5B-Q2_K.gguf new file mode 100644 index 0000000..eeb1b63 --- /dev/null +++ b/Qwen2-0.5B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1d4199c0cc03a82ba8093eecb2bd0ed04138250c8d3b0f373d16c0d91e166db +size 338604736 diff --git a/Qwen2-0.5B-Q3_K_L.gguf b/Qwen2-0.5B-Q3_K_L.gguf new file mode 100644 index 0000000..88805c2 --- /dev/null +++ b/Qwen2-0.5B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fff7f6f725ca9d520beb49296be61871f4c5a26537d1dc6ea538349e9d1794c +size 369355456 diff --git a/Qwen2-0.5B-Q3_K_M.gguf b/Qwen2-0.5B-Q3_K_M.gguf new file mode 100644 index 0000000..d644fb4 --- /dev/null +++ b/Qwen2-0.5B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6324909054af5abbcde6bb40ceabe665beaa2be9e556ee078707f25171c4a3d +size 355463872 diff --git a/Qwen2-0.5B-Q3_K_S.gguf b/Qwen2-0.5B-Q3_K_S.gguf new file mode 100644 index 0000000..683cd7b --- /dev/null +++ b/Qwen2-0.5B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c555b30647f92523951e54d5e1ea6f7472df08f631f926fab4cc628a3fd9eb9 +size 338260672 diff --git a/Qwen2-0.5B-Q4_0.gguf b/Qwen2-0.5B-Q4_0.gguf new file mode 100644 index 0000000..b1ac7df --- /dev/null +++ b/Qwen2-0.5B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb734ad0e1cc7da1e033ba3c5497aad307e19966a2b46c16115e0dcfae7384e6 +size 352152256 diff --git a/Qwen2-0.5B-Q4_K_M.gguf b/Qwen2-0.5B-Q4_K_M.gguf new file mode 100644 index 0000000..093d66e --- /dev/null +++ b/Qwen2-0.5B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ed2c733dd53eb7eec69ec7698ce6f2597475120a7d6d160957fa1e0ba70801 +size 397805248 diff --git a/Qwen2-0.5B-Q4_K_S.gguf b/Qwen2-0.5B-Q4_K_S.gguf new file mode 100644 index 0000000..27efcd0 --- /dev/null +++ b/Qwen2-0.5B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cafb18261a5eb2c3ac310892224f86d58c311c9660e21d0e3dfa5a06e758b66 +size 385469120 diff --git a/Qwen2-0.5B-Q5_0.gguf b/Qwen2-0.5B-Q5_0.gguf new file mode 100644 index 0000000..7bacc02 --- /dev/null +++ b/Qwen2-0.5B-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee19748abb98ffd41163e72758b6c5c04d60c6b8fe4714d076f1d3fb4b9797a +size 396880576 diff --git a/Qwen2-0.5B-Q5_K_M.gguf b/Qwen2-0.5B-Q5_K_M.gguf new file mode 100644 index 0000000..783bcde --- /dev/null +++ b/Qwen2-0.5B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b526151d3df4697947e5df89117ed622f6dffbece3956cf4e53379d5a16a3728 +size 420083392 diff --git a/Qwen2-0.5B-Q5_K_S.gguf b/Qwen2-0.5B-Q5_K_S.gguf new file mode 100644 index 0000000..824d693 --- /dev/null +++ b/Qwen2-0.5B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb1d2366dad55349b0bc88c9aec83afcd59d26f5469799810a7baba6e3b18e0 +size 412707520 diff --git a/Qwen2-0.5B-Q6_K.gguf b/Qwen2-0.5B-Q6_K.gguf new file mode 100644 index 0000000..a524d3b --- /dev/null +++ b/Qwen2-0.5B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f90c078586d76b034050d636ec78c2b53f7b9d6cbe954ffc0c8e873c9071c6f0 +size 505733824 diff --git a/Qwen2-0.5B-Q8_0.gguf b/Qwen2-0.5B-Q8_0.gguf new file mode 100644 index 0000000..0d05243 --- /dev/null +++ b/Qwen2-0.5B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a2174342f3c31658535f63fdf03fb811d0a6e4773acef42b32a8d6ca4e9e1b +size 531065536 diff --git a/Qwen2-0.5B-f16.gguf b/Qwen2-0.5B-f16.gguf new file mode 100644 index 0000000..26a2570 --- /dev/null +++ b/Qwen2-0.5B-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3d181cfc7514cc1dc74fe94bbd1a6fe5e4c4ac584aa7ae914542f539fe9cf6c +size 994154176 diff --git a/README.md b/README.md new file mode 100644 index 0000000..24d95cb --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: Qwen/Qwen2-0.5B +license: apache-2.0 +model_creator: Qwen +model_name: Qwen2-0.5B +quantized_by: Second State Inc. +language: +- en +pipeline_tag: text-generation +--- + + + +
+ +
+
+ + +# Qwen2-0.5B-GGUF + +## Original Model + +[Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.14.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.2) + +- 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-Q5_K_M.gguf \ + llama-api-server.wasm \ + --model-name Qwen2-0.5B \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2-0.5B-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-Q2_K.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q2_K.gguf) | Q2_K | 2 | 339 MB| smallest, significant quality loss - not recommended for most purposes | +| [Qwen2-0.5B-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q3_K_L.gguf) | Q3_K_L | 3 | 369 MB| small, substantial quality loss | +| [Qwen2-0.5B-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q3_K_M.gguf) | Q3_K_M | 3 | 355 MB| very small, high quality loss | +| [Qwen2-0.5B-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q3_K_S.gguf) | Q3_K_S | 3 | 338 MB| very small, high quality loss | +| [Qwen2-0.5B-Q4_0.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q4_0.gguf) | Q4_0 | 4 | 352 MB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Qwen2-0.5B-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q4_K_M.gguf) | Q4_K_M | 4 | 398 MB| medium, balanced quality - recommended | +| [Qwen2-0.5B-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q4_K_S.gguf) | Q4_K_S | 4 | 385 MB| small, greater quality loss | +| [Qwen2-0.5B-Q5_0.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q5_0.gguf) | Q5_0 | 5 | 397 MB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Qwen2-0.5B-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q5_K_M.gguf) | Q5_K_M | 5 | 420 MB| large, very low quality loss - recommended | +| [Qwen2-0.5B-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q5_K_S.gguf) | Q5_K_S | 5 | 413 MB| large, low quality loss - recommended | +| [Qwen2-0.5B-Q6_K.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q6_K.gguf) | Q6_K | 6 | 506 MB| very large, extremely low quality loss | +| [Qwen2-0.5B-Q8_0.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-Q8_0.gguf) | Q8_0 | 8 | 531 MB| very large, extremely low quality loss - not recommended | +| [Qwen2-0.5B-f16.gguf](https://huggingface.co/second-state/Qwen2-0.5B-GGUF/blob/main/Qwen2-0.5B-f16.gguf) | f16 | 16 | 994 MB| | + +*Quantized with llama.cpp b3613* \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..6411736 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 131072, + "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": 131072, + "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