commit b67bc15ce2679e67b15e6341a6621e9059bdea71 Author: ModelHub XC Date: Mon Jun 15 19:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hunyuan-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c37124b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Hunyuan-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hunyuan-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hunyuan-7B-Instruct.IQ4_XS.gguf b/Hunyuan-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..1e6b537 --- /dev/null +++ b/Hunyuan-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6bca2b3888a2eea3ef74544b3115820a77497b64b516ba56c539974241efe91 +size 4202038432 diff --git a/Hunyuan-7B-Instruct.Q2_K.gguf b/Hunyuan-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..25bc14b --- /dev/null +++ b/Hunyuan-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3f3721e55e0bde3f9a5a0bc5e4e4bc9d9cd706f3c63c66b6f07eb343f192ace +size 3003516064 diff --git a/Hunyuan-7B-Instruct.Q3_K_L.gguf b/Hunyuan-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..d3fb038 --- /dev/null +++ b/Hunyuan-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433568d79a546dd83308b21951d78766107acd06de539024d3cea8094ac4e942 +size 4092986528 diff --git a/Hunyuan-7B-Instruct.Q3_K_M.gguf b/Hunyuan-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e354d7f --- /dev/null +++ b/Hunyuan-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c978354ad3afd53baf5740c911b437ec4628f10496f6a3ab18d6e6940bf7846 +size 3789948064 diff --git a/Hunyuan-7B-Instruct.Q3_K_S.gguf b/Hunyuan-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..5bf53b9 --- /dev/null +++ b/Hunyuan-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e24f46cbffc6b6e28970de575fd0a03ed26d10b3b93c4884dae8b1e102740fb2 +size 3435529376 diff --git a/Hunyuan-7B-Instruct.Q4_K_M.gguf b/Hunyuan-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f9d415b --- /dev/null +++ b/Hunyuan-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec56ed457e7619943f525ce91c07a025f7ad6095e1957559ef9b8c51917ec9b1 +size 4621993120 diff --git a/Hunyuan-7B-Instruct.Q4_K_S.gguf b/Hunyuan-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..3612948 --- /dev/null +++ b/Hunyuan-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e517b7dac4bc0af4889304d58b196eb3af0e2701efc9cb320adf25eca4d5c7 +size 4393927840 diff --git a/Hunyuan-7B-Instruct.Q5_K_M.gguf b/Hunyuan-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..dbba36a --- /dev/null +++ b/Hunyuan-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0327b9ebd5940fe894a8d2afe3778001ef7a4b89dee7f73c95e86689f6c3c541 +size 5368579232 diff --git a/Hunyuan-7B-Instruct.Q5_K_S.gguf b/Hunyuan-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..401edfc --- /dev/null +++ b/Hunyuan-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0b3f89a65111846fdb079fbd8c1541523dd59f74d70ad35411ff9d4e283ddeb +size 5234885792 diff --git a/Hunyuan-7B-Instruct.Q6_K.gguf b/Hunyuan-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..1a7436f --- /dev/null +++ b/Hunyuan-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924b1c741decb415e8ffdef2be3002b6f09ce0a4c856a208e34e5f8c976a8280 +size 6161826976 diff --git a/Hunyuan-7B-Instruct.Q8_0.gguf b/Hunyuan-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..9536272 --- /dev/null +++ b/Hunyuan-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde045c621018e69d74e54e5fe71bcf8e6735077efda774b6fa5704c72f323d1 +size 7979273152 diff --git a/Hunyuan-7B-Instruct.f16.gguf b/Hunyuan-7B-Instruct.f16.gguf new file mode 100644 index 0000000..bd273dd --- /dev/null +++ b/Hunyuan-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97acb8450924083f0102ff91f77e47ab074471d298f7419c18ad1c4ecfbe34f3 +size 15014548672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..566284a --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: tencent/Hunyuan-7B-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/tencent/Hunyuan-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hunyuan-7B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q6_K.gguf) | Q6_K | 6.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hunyuan-7B-Instruct-GGUF/resolve/main/Hunyuan-7B-Instruct.f16.gguf) | f16 | 15.1 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +