commit 17247316ac286c3a405d1bd284f0ffdc8969b244 Author: ModelHub XC Date: Tue May 26 23:22:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/CodeQwen1.5-7B-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/CodeQwen1.5-7B-Chat-Q2_K.gguf b/CodeQwen1.5-7B-Chat-Q2_K.gguf new file mode 100644 index 0000000..5babf7d --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e608a8653950aae75508fc80e47f09ab72a0de6850d0f8eb2d643e578e46852e +size 3052103456 diff --git a/CodeQwen1.5-7B-Chat-Q3_K_L.gguf b/CodeQwen1.5-7B-Chat-Q3_K_L.gguf new file mode 100644 index 0000000..eec3d37 --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2559cab20893dfd04e75068be0abbb3e5ce2327b5e38932c46792db23a79b8c5 +size 3986818848 diff --git a/CodeQwen1.5-7B-Chat-Q3_K_M.gguf b/CodeQwen1.5-7B-Chat-Q3_K_M.gguf new file mode 100644 index 0000000..960ff8d --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd46a9f87cd82b70397f109ca9491dc778e436be0e6848e5d76427aa0adc6691 +size 3808626464 diff --git a/CodeQwen1.5-7B-Chat-Q3_K_S.gguf b/CodeQwen1.5-7B-Chat-Q3_K_S.gguf new file mode 100644 index 0000000..b339e05 --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b2ce2ab45555e204371edc622e52a70f83f8a5b53adeb403a175feaebdd0920 +size 3500803872 diff --git a/CodeQwen1.5-7B-Chat-Q4_0.gguf b/CodeQwen1.5-7B-Chat-Q4_0.gguf new file mode 100644 index 0000000..78cea44 --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe2f7514a218350732dbfcfc5e78f75d9221ac70270298aa2643233b91eeab9 +size 4179437344 diff --git a/CodeQwen1.5-7B-Chat-Q4_K_M.gguf b/CodeQwen1.5-7B-Chat-Q4_K_M.gguf new file mode 100644 index 0000000..32364b8 --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944cc3d2184d478350aa4185e46e4f6eff9ca0a53ffacc2c0c3f8a2b70b9cd28 +size 4738590496 diff --git a/CodeQwen1.5-7B-Chat-Q4_K_S.gguf b/CodeQwen1.5-7B-Chat-Q4_K_S.gguf new file mode 100644 index 0000000..b4cb64b --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81bb08532e2b70e707a9af213717f1f7a73f11ab37ab30cbfec05859e37631dd +size 4414449440 diff --git a/CodeQwen1.5-7B-Chat-Q5_0.gguf b/CodeQwen1.5-7B-Chat-Q5_0.gguf new file mode 100644 index 0000000..12e444f --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70bea3cf6a48625022e46df57077145f1f7c992ec75bed0edca3fadcddc25603 +size 5038352160 diff --git a/CodeQwen1.5-7B-Chat-Q5_K_M.gguf b/CodeQwen1.5-7B-Chat-Q5_K_M.gguf new file mode 100644 index 0000000..5d45ff2 --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:191a6d0f470f97eca44150a9cb52360c77b6e4396fb1d081d36fd68e636a9b91 +size 5428160288 diff --git a/CodeQwen1.5-7B-Chat-Q5_K_S.gguf b/CodeQwen1.5-7B-Chat-Q5_K_S.gguf new file mode 100644 index 0000000..71e9a4b --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75630e1e108e7ff83ca60259a2125acb56df99e3730139901bb3b420b3ce34f2 +size 5148452640 diff --git a/CodeQwen1.5-7B-Chat-Q6_K.gguf b/CodeQwen1.5-7B-Chat-Q6_K.gguf new file mode 100644 index 0000000..ccb88ca --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:012abfe19f0127b7070ac2294ee5ba150e813677e8a6be1b01bd6c8d189d0dc2 +size 6377588512 diff --git a/CodeQwen1.5-7B-Chat-Q8_0.gguf b/CodeQwen1.5-7B-Chat-Q8_0.gguf new file mode 100644 index 0000000..c696bf6 --- /dev/null +++ b/CodeQwen1.5-7B-Chat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c334852cd793e1a204a2b633f706f8f54a912055ed831cba73296ba8f30cee +size 7706773280 diff --git a/CodeQwen1.5-7B-Chat-f16.gguf b/CodeQwen1.5-7B-Chat-f16.gguf new file mode 100644 index 0000000..7373751 --- /dev/null +++ b/CodeQwen1.5-7B-Chat-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2077bf8b73ba4af777ff5130c3cb301c7d0593e9519467c5ce1e6c390b98ad7b +size 14503511808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8f0ca64 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: Qwen/CodeQwen1.5-7B-Chat +inference: false +library_name: transformers +license: other +license_name: tongyi-qianwen +model_creator: Qwen +model_name: Openchat 3.5 0106 +model_type: mistral +pipeline_tag: text-generation +quantized_by: Second State Inc. +language: +- en +tags: +- chat +--- + + + +
+ +
+
+ + +# CodeQwen1.5-7B-Chat-GGUF + +## Original Model + +[Qwen/CodeQwen1.5-7B-Chat](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.9.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.9.1) 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: `64000` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:CodeQwen1.5-7B-Chat-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template chatml + --context-size 64000 + --model-name CodeQwen1.5-7B-Chat + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:CodeQwen1.5-7B-Chat-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --ctx-size 64000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [CodeQwen1.5-7B-Chat-Q2_K.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q2_K.gguf) | Q2_K | 2 | 3.05 GB| smallest, significant quality loss - not recommended for most purposes | +| [CodeQwen1.5-7B-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 3.99 GB| small, substantial quality loss | +| [CodeQwen1.5-7B-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 3.81 GB| very small, high quality loss | +| [CodeQwen1.5-7B-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 3.5 GB| very small, high quality loss | +| [CodeQwen1.5-7B-Chat-Q4_0.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q4_0.gguf) | Q4_0 | 4 | 4.18 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [CodeQwen1.5-7B-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 4.74 GB| medium, balanced quality - recommended | +| [CodeQwen1.5-7B-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 4.41 GB| small, greater quality loss | +| [CodeQwen1.5-7B-Chat-Q5_0.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q5_0.gguf) | Q5_0 | 5 | 5.04 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [CodeQwen1.5-7B-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 5.43 GB| large, very low quality loss - recommended | +| [CodeQwen1.5-7B-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 5.15 GB| large, low quality loss - recommended | +| [CodeQwen1.5-7B-Chat-Q6_K.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q6_K.gguf) | Q6_K | 6 | 6.38 GB| very large, extremely low quality loss | +| [CodeQwen1.5-7B-Chat-Q8_0.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-Q8_0.gguf) | Q8_0 | 8 | 7.71 GB| very large, extremely low quality loss - not recommended | +| [CodeQwen1.5-7B-Chat-f16.gguf](https://huggingface.co/second-state/CodeQwen1.5-7B-Chat-GGUF/blob/main/CodeQwen1.5-7B-Chat-f16.gguf) | f16 | 16 | 14.5 GB| | + +*Quantized with llama.cpp b2781* diff --git a/config.json b/config.json new file mode 100644 index 0000000..6fc8ffd --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 2, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 13440, + "max_position_embeddings": 65536, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000, + "rotary_emb_base": 1000000, + "seq_length": 65536, + "sliding_window": 65536, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.39.3", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 92416 +} \ No newline at end of file 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