commit 7ccba763f1c8cefc1bd4d0adc58d75faaf2b150b Author: ModelHub XC Date: Fri May 29 13:33:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Zephyr-7B-Beta-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/README.md b/README.md new file mode 100644 index 0000000..afa9c28 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: HuggingFaceH4/zephyr-7b-beta +inference: false +license: mit +model_creator: Hugging Face H4 +model_name: Zephyr 7B Beta +model_type: mistral +pipeline_tag: text-generation +quantized_by: Second State Inc. +tags: +- generated_from_trainer +datasets: +- HuggingFaceH4/ultrachat_200k +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +--- + + + +
+ +
+
+ + +# Zephyr-7B-Beta-GGUF + +## Original Model + +[HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above + +- Prompt template + + - Prompt type: `zephyr` + + - Prompt string + + ```text + <|system|> + {system_prompt} + <|user|> + {prompt} + <|assistant|> + ``` + + - Reverse prompt: `` + +- Context size: `4096` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:zephyr-7b-beta-Q5_K_M.gguf llama-api-server.wasm -p zephyr -r '' + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:zephyr-7b-beta-Q5_K_M.gguf llama-chat.wasm -p zephyr -r '' + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [zephyr-7b-beta-Q2_K.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q2_K.gguf) | Q2_K | 2 | 3.08 GB| smallest, significant quality loss - not recommended for most purposes | +| [zephyr-7b-beta-Q3_K_L.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss | +| [zephyr-7b-beta-Q3_K_M.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss | +| [zephyr-7b-beta-Q3_K_S.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss | +| [zephyr-7b-beta-Q4_0.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [zephyr-7b-beta-Q4_K_M.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended | +| [zephyr-7b-beta-Q4_K_S.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss | +| [zephyr-7b-beta-Q5_0.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [zephyr-7b-beta-Q5_K_M.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended | +| [zephyr-7b-beta-Q5_K_S.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended | +| [zephyr-7b-beta-Q6_K.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss | +| [zephyr-7b-beta-Q8_0.gguf](https://huggingface.co/second-state/Zephyr-7B-Beta-GGUF/blob/main/zephyr-7b-beta-Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| very large, extremely low quality loss - not recommended | diff --git a/config.json b/config.json new file mode 100644 index 0000000..c3c550a --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "HuggingFaceH4/zephyr-7b-beta", + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.35.0", + "use_cache": true, + "vocab_size": 32000 +} 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 diff --git a/zephyr-7b-beta-Q2_K.gguf b/zephyr-7b-beta-Q2_K.gguf new file mode 100644 index 0000000..6aba2a7 --- /dev/null +++ b/zephyr-7b-beta-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c020e52cabc84af032a1e1ac842d27c5c1362a2add77dbb65b05f269d0c90a42 +size 3083098208 diff --git a/zephyr-7b-beta-Q3_K_L.gguf b/zephyr-7b-beta-Q3_K_L.gguf new file mode 100644 index 0000000..302f561 --- /dev/null +++ b/zephyr-7b-beta-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579523641e01b9473675e5c372ed01f11967298fa982b1a179a1f909a4591504 +size 3822024800 diff --git a/zephyr-7b-beta-Q3_K_M.gguf b/zephyr-7b-beta-Q3_K_M.gguf new file mode 100644 index 0000000..7d9fe5b --- /dev/null +++ b/zephyr-7b-beta-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244731b1010e59ebd57aee4f0a0991ab6d817b9a2957e393b5a3821baa33bd80 +size 3518986336 diff --git a/zephyr-7b-beta-Q3_K_S.gguf b/zephyr-7b-beta-Q3_K_S.gguf new file mode 100644 index 0000000..7e5de5e --- /dev/null +++ b/zephyr-7b-beta-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7ba70672ed7cdcf3ce53e93f891a292c210633563f2b7df3b0e78d4cd6d08c7 +size 3164567648 diff --git a/zephyr-7b-beta-Q4_0.gguf b/zephyr-7b-beta-Q4_0.gguf new file mode 100644 index 0000000..e756641 --- /dev/null +++ b/zephyr-7b-beta-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f01f378c85edb7832fbbbc9933594df503e34c1b0ca086cc184a633929fae3 +size 4108916832 diff --git a/zephyr-7b-beta-Q4_K_M.gguf b/zephyr-7b-beta-Q4_K_M.gguf new file mode 100644 index 0000000..3d15d89 --- /dev/null +++ b/zephyr-7b-beta-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6ae8f4312acfa39fa6a47e07c65fd2c73d213b6ae95c36f37ed4415ca3dfb13 +size 4368439392 diff --git a/zephyr-7b-beta-Q4_K_S.gguf b/zephyr-7b-beta-Q4_K_S.gguf new file mode 100644 index 0000000..e8ab300 --- /dev/null +++ b/zephyr-7b-beta-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3869b5216ce604ea60ca3e4f61c3a7844ea525c0196fc78bcfaf15fee082f4e +size 4140374112 diff --git a/zephyr-7b-beta-Q5_0.gguf b/zephyr-7b-beta-Q5_0.gguf new file mode 100644 index 0000000..e5bb6a9 --- /dev/null +++ b/zephyr-7b-beta-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca8c67b59585024e1302502e3414c90cd052aeffb3b18b89c98dac3aa59a4e92 +size 4997716064 diff --git a/zephyr-7b-beta-Q5_K_M.gguf b/zephyr-7b-beta-Q5_K_M.gguf new file mode 100644 index 0000000..3fcd81c --- /dev/null +++ b/zephyr-7b-beta-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef317faf382c2eb6a34a50f5e95300f108dd188264df00767cf555df7d05c74 +size 5131409504 diff --git a/zephyr-7b-beta-Q5_K_S.gguf b/zephyr-7b-beta-Q5_K_S.gguf new file mode 100644 index 0000000..e113ca7 --- /dev/null +++ b/zephyr-7b-beta-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79bebf283f88a20195532426e710ed97ba0b7c2f8e45e83d1e6bcfbafe2a77ca +size 4997716064 diff --git a/zephyr-7b-beta-Q6_K.gguf b/zephyr-7b-beta-Q6_K.gguf new file mode 100644 index 0000000..b5edd0d --- /dev/null +++ b/zephyr-7b-beta-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab1bf526440b1e3582ce3bf702c2ec7039620f7ca2c78ce1a4c98ea7159dc2c2 +size 5942065248 diff --git a/zephyr-7b-beta-Q8_0.gguf b/zephyr-7b-beta-Q8_0.gguf new file mode 100644 index 0000000..01b9af4 --- /dev/null +++ b/zephyr-7b-beta-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e2d6d76b1b0ec96c5c30c223cb4eeb0ebf98517fea4a38238c504369135a8f +size 7695857760