commit 2e18bf717ec9922e4ec048e3ccd21f255bece4f0 Author: ModelHub XC Date: Fri May 29 13:14:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Qwen2-1.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce9e323 --- /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 +Qwen2-1.5B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-1.5B-Instruct-Q2_K.gguf b/Qwen2-1.5B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..33c27a2 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88847ac80f954dd4cc2ff4011b1cfe1a47e5f67d6df7366b7988f356bd55867d +size 676301920 diff --git a/Qwen2-1.5B-Instruct-Q3_K_L.gguf b/Qwen2-1.5B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..d8af4c3 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6144ec975a1c744c9e335987a18cdd0906bcb6aca77bcd27bb994aa938ffc18e +size 880159840 diff --git a/Qwen2-1.5B-Instruct-Q3_K_M.gguf b/Qwen2-1.5B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..8403862 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b15dbf9eac4d525d208e28798b23867f7794a908686505d536601bc67151cd7 +size 824175712 diff --git a/Qwen2-1.5B-Instruct-Q3_K_S.gguf b/Qwen2-1.5B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..ca0f74f --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6195792c2a60198a7709594be682d3fbf2f949abb4c502ca32436d55003752 +size 760941664 diff --git a/Qwen2-1.5B-Instruct-Q4_0.gguf b/Qwen2-1.5B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..72afa6f --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9ff67ff4f9b870c3da39355326d6bcf2c2a0dc45eb4f4d322f97537ede6cf2 +size 934952032 diff --git a/Qwen2-1.5B-Instruct-Q4_K_M.gguf b/Qwen2-1.5B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..e43feb9 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c7a0a246cb52da4cdd289966fd6db7d193361c6e990af20a67de759d30bf48b +size 986045536 diff --git a/Qwen2-1.5B-Instruct-Q4_K_S.gguf b/Qwen2-1.5B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..0d544dc --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2f74e84e55b4780c5fd8fe26df72afd31a343b7af2735cd07a8719b2f117d3 +size 940309600 diff --git a/Qwen2-1.5B-Instruct-Q5_0.gguf b/Qwen2-1.5B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..df1be21 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816f93be1e8551137d0d9705d49a1cf331e06e23169b7a83b4eebd047e365650 +size 1098726496 diff --git a/Qwen2-1.5B-Instruct-Q5_K_M.gguf b/Qwen2-1.5B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..4f58da3 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a44ea39745a64b6f789425cfb38c0ddc8dc9cb81823533b14b9ae8c1bd30527 +size 1125047392 diff --git a/Qwen2-1.5B-Instruct-Q5_K_S.gguf b/Qwen2-1.5B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..dd700a8 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e374ffb77e1d5c48622f783d89266393a528b65620b90541af903e4e9e92a7 +size 1098726496 diff --git a/Qwen2-1.5B-Instruct-Q6_K.gguf b/Qwen2-1.5B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..9dd79b9 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ac778aae8560788916c37055f2fa8d550e5655081ba28fcfd1339ddba3106e +size 1272736864 diff --git a/Qwen2-1.5B-Instruct-Q8_0.gguf b/Qwen2-1.5B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..4706791 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b8cc447dcb63faa971b3098ad286e946858dde23cf5bee8984752093dbf712 +size 1646570080 diff --git a/Qwen2-1.5B-Instruct-f16.gguf b/Qwen2-1.5B-Instruct-f16.gguf new file mode 100644 index 0000000..a2fb0f2 --- /dev/null +++ b/Qwen2-1.5B-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a79e0e0407877562e18e681c07ba5742ca5010a59e8dd067f2db7ea1aec406f +size 3093666400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ea58dcc --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: Qwen/Qwen2-1.5B-Instruct +license: apache-2.0 +model_creator: Qwen +model_name: Qwen2-1.5B-Instruct +quantized_by: Second State Inc. +language: +- en +pipeline_tag: text-generation +tags: +- chat +--- + + + +
+ +
+
+ + +# Qwen2-1.5B-Instruct-GGUF + +## Original Model + +[Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) + +## 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:Qwen2-1.5B-Instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --model-name Qwen2-1.5B-Instruct \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2-1.5B-Instruct-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Qwen2-1.5B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q2_K.gguf) | Q2_K | 2 | 676 MB| smallest, significant quality loss - not recommended for most purposes | +| [Qwen2-1.5B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 880 MB| small, substantial quality loss | +| [Qwen2-1.5B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 824 MB| very small, high quality loss | +| [Qwen2-1.5B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 761 MB| very small, high quality loss | +| [Qwen2-1.5B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 935 MB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Qwen2-1.5B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 986 MB| medium, balanced quality - recommended | +| [Qwen2-1.5B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 940 MB| small, greater quality loss | +| [Qwen2-1.5B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 1.1 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Qwen2-1.5B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 1.13 GB| large, very low quality loss - recommended | +| [Qwen2-1.5B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 1.1 GB| large, low quality loss - recommended | +| [Qwen2-1.5B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q6_K.gguf) | Q6_K | 6 | 1.27 GB| very large, extremely low quality loss | +| [Qwen2-1.5B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 1.65 GB| very large, extremely low quality loss - not recommended | +| [Qwen2-1.5B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/blob/main/Qwen2-1.5B-Instruct-f16.gguf) | f16 | 16 | 3.09 GB| | + +*Quantized with llama.cpp b3705* diff --git a/config.json b/config.json new file mode 100644 index 0000000..f48f003 --- /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": 28, + "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": "4.40.1", + "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