commit fe510ec77bc86570f6d0aad09b06cfaf69154cb7 Author: ModelHub XC Date: Fri Jun 5 17:43:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CHAI_SFT_model_8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..820f209 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +CHAI_SFT_model_8b.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CHAI_SFT_model_8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CHAI_SFT_model_8b.IQ4_XS.gguf b/CHAI_SFT_model_8b.IQ4_XS.gguf new file mode 100644 index 0000000..2c49044 --- /dev/null +++ b/CHAI_SFT_model_8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b24c934dd74980fd5b6b3c14d66a83e8ea6dde7fd8be154037e2d99f14e7320 +size 4593298464 diff --git a/CHAI_SFT_model_8b.Q2_K.gguf b/CHAI_SFT_model_8b.Q2_K.gguf new file mode 100644 index 0000000..85bbec9 --- /dev/null +++ b/CHAI_SFT_model_8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dca6ed0bcdf83324a08f42cebdf1fe6cfbcc3deb4bce2d3cc8c5853f3ace158 +size 3281734688 diff --git a/CHAI_SFT_model_8b.Q3_K_L.gguf b/CHAI_SFT_model_8b.Q3_K_L.gguf new file mode 100644 index 0000000..f84da66 --- /dev/null +++ b/CHAI_SFT_model_8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59512a05e062b8ad20cdbb88cf51bbb69ad5020b18a6344dbba6e7e928a648dd +size 4431395872 diff --git a/CHAI_SFT_model_8b.Q3_K_M.gguf b/CHAI_SFT_model_8b.Q3_K_M.gguf new file mode 100644 index 0000000..2aedcad --- /dev/null +++ b/CHAI_SFT_model_8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d23fc4bc439e1c294ae5be5631ac04395b1ac2d4861b0e2e8fc77ecf3038e0 +size 4124163104 diff --git a/CHAI_SFT_model_8b.Q3_K_S.gguf b/CHAI_SFT_model_8b.Q3_K_S.gguf new file mode 100644 index 0000000..06b406c --- /dev/null +++ b/CHAI_SFT_model_8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d150627b10f45df0e9fa7875c313a79e7b57ce88b50400ab76de6adbc31c0e48 +size 3769613344 diff --git a/CHAI_SFT_model_8b.Q4_K_M.gguf b/CHAI_SFT_model_8b.Q4_K_M.gguf new file mode 100644 index 0000000..c83defa --- /dev/null +++ b/CHAI_SFT_model_8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4658d40c1d03a994e9c96ab2dba344746af24f315e7e6cdb94221189fef2e3 +size 5027785760 diff --git a/CHAI_SFT_model_8b.Q4_K_S.gguf b/CHAI_SFT_model_8b.Q4_K_S.gguf new file mode 100644 index 0000000..357172d --- /dev/null +++ b/CHAI_SFT_model_8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2559529d930bf976de090c1bd6bfff8b11c905e8e12a1296b82400eada49e54b +size 4802014240 diff --git a/CHAI_SFT_model_8b.Q5_K_M.gguf b/CHAI_SFT_model_8b.Q5_K_M.gguf new file mode 100644 index 0000000..6c57869 --- /dev/null +++ b/CHAI_SFT_model_8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2171650642c42e3874f24b7e8b2a06dc2902f6350d494a8e4c4139ee72b78d +size 5851114528 diff --git a/CHAI_SFT_model_8b.Q5_K_S.gguf b/CHAI_SFT_model_8b.Q5_K_S.gguf new file mode 100644 index 0000000..3ae7eeb --- /dev/null +++ b/CHAI_SFT_model_8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92166e0ed5464b726fc3631c5a642c13bc38a59b9f5ba11a0b6bbafc82b3b755 +size 5720763424 diff --git a/CHAI_SFT_model_8b.Q6_K.gguf b/CHAI_SFT_model_8b.Q6_K.gguf new file mode 100644 index 0000000..1cffb82 --- /dev/null +++ b/CHAI_SFT_model_8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbccd8f66832a943ecbe48e4745b1cc154084cdc47fd059c3ff332f7d21a1150 +size 6725901344 diff --git a/CHAI_SFT_model_8b.Q8_0.gguf b/CHAI_SFT_model_8b.Q8_0.gguf new file mode 100644 index 0000000..dc67c3f --- /dev/null +++ b/CHAI_SFT_model_8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4dfae333d822ae89f53c1c07caf155c631369c050efbc868609ac75ec0c26d3 +size 8709520416 diff --git a/CHAI_SFT_model_8b.f16.gguf b/CHAI_SFT_model_8b.f16.gguf new file mode 100644 index 0000000..40982a3 --- /dev/null +++ b/CHAI_SFT_model_8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d602b60097fd95827c0ddfa51b21781c956fea410134e305351cdc1303e223b1 +size 16388045856 diff --git a/CHAI_SFT_model_8b.mmproj-Q8_0.gguf b/CHAI_SFT_model_8b.mmproj-Q8_0.gguf new file mode 100644 index 0000000..bae0748 --- /dev/null +++ b/CHAI_SFT_model_8b.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e96aff4ac3dfdfa96faedff2b4773cba42c025f341b63752b8498d2a1ac857 +size 752290240 diff --git a/CHAI_SFT_model_8b.mmproj-f16.gguf b/CHAI_SFT_model_8b.mmproj-f16.gguf new file mode 100644 index 0000000..84903d0 --- /dev/null +++ b/CHAI_SFT_model_8b.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e348e3b7eaf3d8a9ea3c81d21a19efe80b0e06de0f88e2a0b0c64e6888b9e1 +size 1159030336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a142d1 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: chancharikm/CHAI_SFT_model_8b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +- video-language-model +- video-captioning +--- +## About + + + + + + + + + +static quants of https://huggingface.co/chancharikm/CHAI_SFT_model_8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CHAI_SFT_model_8b-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CHAI_SFT_model_8b-GGUF/resolve/main/CHAI_SFT_model_8b.f16.gguf) | f16 | 16.5 | 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. + +