From aaecbd4e4fd882f21f45db56ea03b09ccb23ae49 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 27 May 2026 00:58:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: second-state/Zephyr-7B-Alpha-GGUF Source: Original Platform --- .gitattributes | 36 +++++++++++++++ README.md | 92 +++++++++++++++++++++++++++++++++++++ config.json | 26 +++++++++++ configuration.json | 1 + zephyr-7b-alpha-Q2_K.gguf | 3 ++ zephyr-7b-alpha-Q3_K_L.gguf | 3 ++ zephyr-7b-alpha-Q3_K_M.gguf | 3 ++ zephyr-7b-alpha-Q3_K_S.gguf | 3 ++ zephyr-7b-alpha-Q4_0.gguf | 3 ++ zephyr-7b-alpha-Q4_K_M.gguf | 3 ++ zephyr-7b-alpha-Q4_K_S.gguf | 3 ++ zephyr-7b-alpha-Q5_0.gguf | 3 ++ zephyr-7b-alpha-Q5_K_M.gguf | 3 ++ zephyr-7b-alpha-Q5_K_S.gguf | 3 ++ zephyr-7b-alpha-Q6_K.gguf | 3 ++ zephyr-7b-alpha-Q8_0.gguf | 3 ++ 16 files changed, 191 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 zephyr-7b-alpha-Q2_K.gguf create mode 100644 zephyr-7b-alpha-Q3_K_L.gguf create mode 100644 zephyr-7b-alpha-Q3_K_M.gguf create mode 100644 zephyr-7b-alpha-Q3_K_S.gguf create mode 100644 zephyr-7b-alpha-Q4_0.gguf create mode 100644 zephyr-7b-alpha-Q4_K_M.gguf create mode 100644 zephyr-7b-alpha-Q4_K_S.gguf create mode 100644 zephyr-7b-alpha-Q5_0.gguf create mode 100644 zephyr-7b-alpha-Q5_K_M.gguf create mode 100644 zephyr-7b-alpha-Q5_K_S.gguf create mode 100644 zephyr-7b-alpha-Q6_K.gguf create mode 100644 zephyr-7b-alpha-Q8_0.gguf 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..247b527 --- /dev/null +++ b/README.md @@ -0,0 +1,92 @@ +--- +base_model: HuggingFaceH4/zephyr-7b-alpha +datasets: +- stingning/ultrachat +- openbmb/UltraFeedback +inference: false +license: mit +model-index: +- name: zephyr-7b-alpha + results: [] +model_creator: Hugging Face H4 +model_name: Zephyr 7B Alpha +model_type: mistral +quantized_by: Second State Inc. +language: +- en +--- + + + +
+ +
+
+ + +# Zephyr-7B-Alpha-GGUF + +## Original Model + +[HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) + +## 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-alpha-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-alpha-Q5_K_M.gguf llama-chat.wasm -p zephyr -r '' + ``` + +## Prompt Template + +```text +<|system|> +{system_prompt} +<|user|> +{prompt} +<|assistant|> +``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [zephyr-7b-alpha-Q2_K.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q2_K.gguf) | Q2_K | 2 | 2.7 GB| smallest, significant quality loss - not recommended for most purposes | +| [zephyr-7b-alpha-Q3_K_L.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss | +| [zephyr-7b-alpha-Q3_K_M.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss | +| [zephyr-7b-alpha-Q3_K_S.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss | +| [zephyr-7b-alpha-Q4_0.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [zephyr-7b-alpha-Q4_K_M.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended | +| [zephyr-7b-alpha-Q4_K_S.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss | +| [zephyr-7b-alpha-Q5_0.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [zephyr-7b-alpha-Q5_K_M.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended | +| [zephyr-7b-alpha-Q5_K_S.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended | +| [zephyr-7b-alpha-Q6_K.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss | +| [zephyr-7b-alpha-Q8_0.gguf](https://huggingface.co/second-state/Zephyr-7B-Alpha-GGUF/blob/main/zephyr-7b-alpha-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..0d8f4f6 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "./zephyr-7b-alpha/", + "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": "4.34.0", + "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-alpha-Q2_K.gguf b/zephyr-7b-alpha-Q2_K.gguf new file mode 100644 index 0000000..fa9bae4 --- /dev/null +++ b/zephyr-7b-alpha-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23cb1aa3edf2997af1fda518e1348dffc048d307a1ca060dadaba01ccfd1ba52 +size 2701416544 diff --git a/zephyr-7b-alpha-Q3_K_L.gguf b/zephyr-7b-alpha-Q3_K_L.gguf new file mode 100644 index 0000000..bd2761d --- /dev/null +++ b/zephyr-7b-alpha-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27907713cc210878b9b4e4887520c7f3fa860bd52a7b2add6b24027d7826977a +size 3822024800 diff --git a/zephyr-7b-alpha-Q3_K_M.gguf b/zephyr-7b-alpha-Q3_K_M.gguf new file mode 100644 index 0000000..898298c --- /dev/null +++ b/zephyr-7b-alpha-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4101fb76a49b0df23fe3e32d2ef6c314d272d61b883c6149db54c89c55aa368 +size 3518986336 diff --git a/zephyr-7b-alpha-Q3_K_S.gguf b/zephyr-7b-alpha-Q3_K_S.gguf new file mode 100644 index 0000000..947aa8e --- /dev/null +++ b/zephyr-7b-alpha-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141acd410a36fe305f01975dde46ebf507e69b69a704f311c24c33f9fef949de +size 3164567648 diff --git a/zephyr-7b-alpha-Q4_0.gguf b/zephyr-7b-alpha-Q4_0.gguf new file mode 100644 index 0000000..3c8dffb --- /dev/null +++ b/zephyr-7b-alpha-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b3db978dacb3ba2d0ac8651ec046b6d507c16090abbadf991fe013537b08d8d +size 4108916832 diff --git a/zephyr-7b-alpha-Q4_K_M.gguf b/zephyr-7b-alpha-Q4_K_M.gguf new file mode 100644 index 0000000..f223e2a --- /dev/null +++ b/zephyr-7b-alpha-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2da80630ae4bb5cbc56561bf830b92d6e2d629e6b4783801f06a6bf9423efb +size 4368439392 diff --git a/zephyr-7b-alpha-Q4_K_S.gguf b/zephyr-7b-alpha-Q4_K_S.gguf new file mode 100644 index 0000000..d852e53 --- /dev/null +++ b/zephyr-7b-alpha-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c3f815825c405ada3f1ffe1f8f524d91a6631eb53789b1874b84f942de48158 +size 4140374112 diff --git a/zephyr-7b-alpha-Q5_0.gguf b/zephyr-7b-alpha-Q5_0.gguf new file mode 100644 index 0000000..b2fd5b8 --- /dev/null +++ b/zephyr-7b-alpha-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d356cdbd474fcb14f562545f5d3875e50682e161cfeb6dd638db8ceb30ea8f +size 4997716064 diff --git a/zephyr-7b-alpha-Q5_K_M.gguf b/zephyr-7b-alpha-Q5_K_M.gguf new file mode 100644 index 0000000..8a59304 --- /dev/null +++ b/zephyr-7b-alpha-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd035904c4b16904049c2ba7e45f1b34ad2868af3ecbe51d8c77daa371b96245 +size 5131409504 diff --git a/zephyr-7b-alpha-Q5_K_S.gguf b/zephyr-7b-alpha-Q5_K_S.gguf new file mode 100644 index 0000000..834f3f5 --- /dev/null +++ b/zephyr-7b-alpha-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97b801e611b194a9ecdbae5727cb0b7d082ba84575d421343e07a0c645f1427 +size 4997716064 diff --git a/zephyr-7b-alpha-Q6_K.gguf b/zephyr-7b-alpha-Q6_K.gguf new file mode 100644 index 0000000..faf1a42 --- /dev/null +++ b/zephyr-7b-alpha-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:708fe0ba2fe5e63f5d08e932332b0c854ed33065b407f88bdbdb0533d5a66f1c +size 5942065248 diff --git a/zephyr-7b-alpha-Q8_0.gguf b/zephyr-7b-alpha-Q8_0.gguf new file mode 100644 index 0000000..1184a6b --- /dev/null +++ b/zephyr-7b-alpha-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f11eb54abbd2413d6c3d257a6ebd71e2db8109911fbb8ad7fc9b55f8c965f8d +size 7695857760