commit c29b76c8a4693432a2593791781f35020a7e7dd0 Author: ModelHub XC Date: Wed Jul 8 00:46:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eeb79c1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v3.0-Instruct-gptq-marlin.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.IQ4_XS.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.IQ4_XS.gguf new file mode 100644 index 0000000..e88bf0e --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:311438bae14cfa8e90dff9e05c312978b067fa4ce3cb7156ce112e53d45f5bbe +size 6061465728 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q2_K.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q2_K.gguf new file mode 100644 index 0000000..673f6f1 --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f89992662fce713d15b45e8dd770ab455ad49feeb078ef37872560b228cfff3 +size 4164337792 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_L.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_L.gguf new file mode 100644 index 0000000..3ec0678 --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10f2e5cdc0748b5c29779a4b4cecc3a5b5dffb31715ed393363868f05fc2c19 +size 5880000640 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_M.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_M.gguf new file mode 100644 index 0000000..3bfd4e6 --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b856b2708725ce4ed69100ea1de6538b495e3e4ad154d51e6c36bfb9d45017a +size 5404995712 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_S.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_S.gguf new file mode 100644 index 0000000..d10afd8 --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352ba19494b80b6fa697cc4ca6ef82f4870cd1060278b09005bd68a237474731 +size 4852723840 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_M.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_M.gguf new file mode 100644 index 0000000..1d3b3fb --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b220f221023fd259d3b162b0013bd8b8924c604c375fef2c8948aec84008e4 +size 6724051072 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_S.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_S.gguf new file mode 100644 index 0000000..7af1fa3 --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27af272279a2dfd71a252c78faea26f267466e6d2137bc5133f32d4a626a4062 +size 6364684416 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_M.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_M.gguf new file mode 100644 index 0000000..d0ab530 --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c312a76854b0bf909047812058e2b7cafad9db5163eddb5bab0a6e64d2d1334b +size 7907041408 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_S.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_S.gguf new file mode 100644 index 0000000..98346d6 --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfd340ff442852ef5a0ff4d8dbec59e45f19b8c3a82594fe63cfbf1395c11837 +size 7698145408 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q6_K.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q6_K.gguf new file mode 100644 index 0000000..f37c85f --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a3dfa58d1f61ab16314f6352d42fbaf24ae0e4e2aa9eaee82cf87915dc96ee3 +size 9163968640 diff --git a/Bielik-11B-v3.0-Instruct-gptq-marlin.Q8_0.gguf b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q8_0.gguf new file mode 100644 index 0000000..4994f16 --- /dev/null +++ b/Bielik-11B-v3.0-Instruct-gptq-marlin.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce6bb170f510debb74aabafa89e7a27c314df8e0d734ff35f82ebecf2e5c0cd +size 11868811392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..99363d3 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: wizardeur/Bielik-11B-v3.0-Instruct-gptq-marlin +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/wizardeur/Bielik-11B-v3.0-Instruct-gptq-marlin + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Bielik-11B-v3.0-Instruct-gptq-marlin-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/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q2_K.gguf) | Q2_K | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_S.gguf) | Q3_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_M.gguf) | Q3_K_M | 5.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q3_K_L.gguf) | Q3_K_L | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.IQ4_XS.gguf) | IQ4_XS | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_S.gguf) | Q4_K_S | 6.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q4_K_M.gguf) | Q4_K_M | 6.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_S.gguf) | Q5_K_S | 7.8 | | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q5_K_M.gguf) | Q5_K_M | 8.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q6_K.gguf) | Q6_K | 9.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Bielik-11B-v3.0-Instruct-gptq-marlin-GGUF/resolve/main/Bielik-11B-v3.0-Instruct-gptq-marlin.Q8_0.gguf) | Q8_0 | 12.0 | fast, best quality | + +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. + +