commit a869490724b664c3ede0779ce3757eeca6550ee7 Author: ModelHub XC Date: Sat Jun 13 04:44:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/chandra-FP8-Latest-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8abffb9 --- /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 +chandra-FP8-Latest.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.f16.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chandra-FP8-Latest.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bcc91fc --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: prithivMLmods/chandra-FP8-Latest +language: +- en +library_name: transformers +license: openrail +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- vllm +- fp8 +- quantized +- llm-compressor +- ocr +- vlm +--- +## About + + + + + + + + + +static quants of https://huggingface.co/prithivMLmods/chandra-FP8-Latest + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#chandra-FP8-Latest-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/chandra-FP8-Latest-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/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/chandra-FP8-Latest-GGUF/resolve/main/chandra-FP8-Latest.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. + + diff --git a/chandra-FP8-Latest.IQ4_XS.gguf b/chandra-FP8-Latest.IQ4_XS.gguf new file mode 100644 index 0000000..a77a4d0 --- /dev/null +++ b/chandra-FP8-Latest.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8137fa4ec5c3a4587d9ce8b3ba209411081ffe18b7ea34225881ecd2855bef8a +size 4593298496 diff --git a/chandra-FP8-Latest.Q2_K.gguf b/chandra-FP8-Latest.Q2_K.gguf new file mode 100644 index 0000000..7028c69 --- /dev/null +++ b/chandra-FP8-Latest.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43da883ede11f5dc453be1591ff0387d6e7a256780fd5ba825ca677a7dacb471 +size 3281734720 diff --git a/chandra-FP8-Latest.Q3_K_L.gguf b/chandra-FP8-Latest.Q3_K_L.gguf new file mode 100644 index 0000000..3b7991a --- /dev/null +++ b/chandra-FP8-Latest.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f5fa931b77bbb83fc673b6aaff6aded346af66b872ef19d5ef27025e540c56 +size 4431395904 diff --git a/chandra-FP8-Latest.Q3_K_M.gguf b/chandra-FP8-Latest.Q3_K_M.gguf new file mode 100644 index 0000000..99ac826 --- /dev/null +++ b/chandra-FP8-Latest.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e8600e3b57d116dce29809047175c34af5b800f6723ff1a28bbfc998f989b6c +size 4124163136 diff --git a/chandra-FP8-Latest.Q3_K_S.gguf b/chandra-FP8-Latest.Q3_K_S.gguf new file mode 100644 index 0000000..9b808ef --- /dev/null +++ b/chandra-FP8-Latest.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a479ec1197860e3e4a7abbea75f7dd198e191728f5691ec37a1b8ded61b7bbf1 +size 3769613376 diff --git a/chandra-FP8-Latest.Q4_K_M.gguf b/chandra-FP8-Latest.Q4_K_M.gguf new file mode 100644 index 0000000..af95b38 --- /dev/null +++ b/chandra-FP8-Latest.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e1ed48ea062db9c60f7fd7519e5e2e134008e1390f6e261cf6f3b283934fd99 +size 5027785792 diff --git a/chandra-FP8-Latest.Q4_K_S.gguf b/chandra-FP8-Latest.Q4_K_S.gguf new file mode 100644 index 0000000..802a9f8 --- /dev/null +++ b/chandra-FP8-Latest.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ee7ef8a022f971e97bd03666016e75957b4e0173477e2849d5be1904dab4df +size 4802014272 diff --git a/chandra-FP8-Latest.Q5_K_M.gguf b/chandra-FP8-Latest.Q5_K_M.gguf new file mode 100644 index 0000000..2dd7bd5 --- /dev/null +++ b/chandra-FP8-Latest.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6982f084005d9f1b1d463387d56f334f9cc6f757bd32b006e4f5e1f89cfbf354 +size 5851114560 diff --git a/chandra-FP8-Latest.Q5_K_S.gguf b/chandra-FP8-Latest.Q5_K_S.gguf new file mode 100644 index 0000000..89e0ba8 --- /dev/null +++ b/chandra-FP8-Latest.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75218dc2128d24fc2fc90033e132f605662b7ed175596838b965dfbf8fb373e7 +size 5720763456 diff --git a/chandra-FP8-Latest.Q6_K.gguf b/chandra-FP8-Latest.Q6_K.gguf new file mode 100644 index 0000000..7e35205 --- /dev/null +++ b/chandra-FP8-Latest.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595b6f065bc2a04b05b1b1686da297d0474afb5d6c1a59f814b2699b9c0ba733 +size 6725901376 diff --git a/chandra-FP8-Latest.Q8_0.gguf b/chandra-FP8-Latest.Q8_0.gguf new file mode 100644 index 0000000..6ce6d0e --- /dev/null +++ b/chandra-FP8-Latest.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f690265145e6a8722283ceda197bf081d390c904341cbc9c21999ef7fcdc55e4 +size 8709520448 diff --git a/chandra-FP8-Latest.f16.gguf b/chandra-FP8-Latest.f16.gguf new file mode 100644 index 0000000..f3a8595 --- /dev/null +++ b/chandra-FP8-Latest.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:265d16680d287a17a12e49ac7ed0e862207204bd47899b2dfce07b00bd947249 +size 16388045888 diff --git a/chandra-FP8-Latest.mmproj-Q8_0.gguf b/chandra-FP8-Latest.mmproj-Q8_0.gguf new file mode 100644 index 0000000..360dbf5 --- /dev/null +++ b/chandra-FP8-Latest.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe767a208ed69e77b9ed74505c32838917dbd7f7c9238af67fe51b39408e482 +size 752290272 diff --git a/chandra-FP8-Latest.mmproj-f16.gguf b/chandra-FP8-Latest.mmproj-f16.gguf new file mode 100644 index 0000000..948e94f --- /dev/null +++ b/chandra-FP8-Latest.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df0c5aaf482e6228362c36d9f1360d7351fbafe0c93427cdd23cd315749aa3a3 +size 1159030368