commit ce5289a13b61123d9abe08affdc5db88d33b4643 Author: ModelHub XC Date: Fri Apr 10 22:34:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Fett-uccine-11B-Experiment-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e295b1f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Fett-uccine-11B-Experiment.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.f16.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Fett-uccine-11B-Experiment.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Fett-uccine-11B-Experiment.IQ4_XS.gguf b/Fett-uccine-11B-Experiment.IQ4_XS.gguf new file mode 100644 index 0000000..6431775 --- /dev/null +++ b/Fett-uccine-11B-Experiment.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd9818d2ed976668f226f47ffdd0024cac78da269408d42af6beb58daabe40c +size 5827640928 diff --git a/Fett-uccine-11B-Experiment.Q2_K.gguf b/Fett-uccine-11B-Experiment.Q2_K.gguf new file mode 100644 index 0000000..5b2f69d --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3437b5a90954ecadb8306b8af3fc31758024a088f66bf684450fdaeeaac79e +size 4003233376 diff --git a/Fett-uccine-11B-Experiment.Q3_K_L.gguf b/Fett-uccine-11B-Experiment.Q3_K_L.gguf new file mode 100644 index 0000000..b9a2b0d --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5ad4678c6b78d09513e2c140f2ac119d3fbe59d6a6d8a3916fd4ff19d6b400 +size 5650751072 diff --git a/Fett-uccine-11B-Experiment.Q3_K_M.gguf b/Fett-uccine-11B-Experiment.Q3_K_M.gguf new file mode 100644 index 0000000..c487fe1 --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7448e14f09d58dc058d28aca01acde621a641f83a4d5ba8d4014d41f8c511862 +size 5195669088 diff --git a/Fett-uccine-11B-Experiment.Q3_K_S.gguf b/Fett-uccine-11B-Experiment.Q3_K_S.gguf new file mode 100644 index 0000000..d50a625 --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36df4f40cf43db2e517fd9ccc4a626609f66497b64980a9bf5d43f20fd2a464c +size 4664565344 diff --git a/Fett-uccine-11B-Experiment.Q4_0_4_4.gguf b/Fett-uccine-11B-Experiment.Q4_0_4_4.gguf new file mode 100644 index 0000000..44a3e80 --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b76f1780983746f050db941fe2f955aefa7c3a0382b69632a6667d1a293001 +size 6072385120 diff --git a/Fett-uccine-11B-Experiment.Q4_K_M.gguf b/Fett-uccine-11B-Experiment.Q4_K_M.gguf new file mode 100644 index 0000000..6c3b75a --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86eefe5c489a2460cf5172fedbea72c72367ccf5a4881e5573a8b7a902a134d +size 6461668960 diff --git a/Fett-uccine-11B-Experiment.Q4_K_S.gguf b/Fett-uccine-11B-Experiment.Q4_K_S.gguf new file mode 100644 index 0000000..6f98408 --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c32331589b1ffa89427d9639eaf45391eeb26983b12817450545f157e9d92ab1 +size 6118522464 diff --git a/Fett-uccine-11B-Experiment.Q5_K_M.gguf b/Fett-uccine-11B-Experiment.Q5_K_M.gguf new file mode 100644 index 0000000..af28d09 --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9bcd8bd715db90d370b02d2f605cae8bbc4540a26ed5e28a018ff81d749e865 +size 7597932128 diff --git a/Fett-uccine-11B-Experiment.Q5_K_S.gguf b/Fett-uccine-11B-Experiment.Q5_K_S.gguf new file mode 100644 index 0000000..5149aea --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d7ac92a8a38c5398a80e574e9ff3de9ea49911a43e5f1592a79116998991436 +size 7397391968 diff --git a/Fett-uccine-11B-Experiment.Q6_K.gguf b/Fett-uccine-11B-Experiment.Q6_K.gguf new file mode 100644 index 0000000..18edd5d --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e35911167c5c54659b61df84768338b1d6e51fe4222ec57bc964f26022255d +size 8805211744 diff --git a/Fett-uccine-11B-Experiment.Q8_0.gguf b/Fett-uccine-11B-Experiment.Q8_0.gguf new file mode 100644 index 0000000..e338089 --- /dev/null +++ b/Fett-uccine-11B-Experiment.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d5a79998ffb39927ec550b189386c2c2fc4fb872325db5e7525444e6cb2574 +size 11404156512 diff --git a/Fett-uccine-11B-Experiment.f16.gguf b/Fett-uccine-11B-Experiment.f16.gguf new file mode 100644 index 0000000..c0e13d7 --- /dev/null +++ b/Fett-uccine-11B-Experiment.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b33ab806dac780aa281d7f13c8a5689bb15364f12749e71b3e07b94bf1f8cd +size 21464587872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00c6e10 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: saishf/Fett-uccine-11B-Experiment +language: +- en +library_name: transformers +license: agpl-3.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/saishf/Fett-uccine-11B-Experiment + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-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/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q2_K.gguf) | Q2_K | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q3_K_S.gguf) | Q3_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q3_K_L.gguf) | Q3_K_L | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.IQ4_XS.gguf) | IQ4_XS | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q4_0_4_4.gguf) | Q4_0_4_4 | 6.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q5_K_S.gguf) | Q5_K_S | 7.5 | | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q5_K_M.gguf) | Q5_K_M | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q6_K.gguf) | Q6_K | 8.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.Q8_0.gguf) | Q8_0 | 11.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Fett-uccine-11B-Experiment-GGUF/resolve/main/Fett-uccine-11B-Experiment.f16.gguf) | f16 | 21.6 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +