commit 287f2640f76efcf7b49e34853d76910e03b7f74c Author: ModelHub XC Date: Thu Aug 13 00:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Quelix-8B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0698fbc --- /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 +Quelix-8B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quelix-8B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Quelix-8B-v0.1.IQ4_XS.gguf b/Quelix-8B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..485ebf3 --- /dev/null +++ b/Quelix-8B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:941b624ba40c612ff35e437977f11dcb5d35000283061a0d58f3bec3ae09c9c3 +size 4250299232 diff --git a/Quelix-8B-v0.1.Q2_K.gguf b/Quelix-8B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..eae0c1a --- /dev/null +++ b/Quelix-8B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b45bd3b4503a3b03cbff9f180a663af680cfbc003346eaeeec6200d9ea99534 +size 3015940960 diff --git a/Quelix-8B-v0.1.Q3_K_L.gguf b/Quelix-8B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..f166f0a --- /dev/null +++ b/Quelix-8B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445a68c2feb84f7ba867c5f8847ca7ffb257943afae72c90e8f5b208d67aa58f +size 4088460128 diff --git a/Quelix-8B-v0.1.Q3_K_M.gguf b/Quelix-8B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..94beead --- /dev/null +++ b/Quelix-8B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0cb52dc7aa17ce5b973b22ff8ae8deb4a97e086a2d0f1ac2d0ff80d4e4ce355 +size 3808392032 diff --git a/Quelix-8B-v0.1.Q3_K_S.gguf b/Quelix-8B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..18f09e8 --- /dev/null +++ b/Quelix-8B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e0fe8e08d37c0b02b23ff3a70367bacd83f72d420e7d2b2d8da3bfed7b2868 +size 3492369248 diff --git a/Quelix-8B-v0.1.Q4_K_M.gguf b/Quelix-8B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..c0e9622 --- /dev/null +++ b/Quelix-8B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4ce25c497ca04d9cd4abac6015699bde42825a203e7e49720c20e5bf096254 +size 4683074400 diff --git a/Quelix-8B-v0.1.Q4_K_S.gguf b/Quelix-8B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..184616b --- /dev/null +++ b/Quelix-8B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdca3f1df7f68c2f3b285d2a145d5de1fec489ca742bd1f5f0376ce6797ec262 +size 4457769824 diff --git a/Quelix-8B-v0.1.Q5_K_M.gguf b/Quelix-8B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..2753701 --- /dev/null +++ b/Quelix-8B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18749d1f3df1d1dcdf670df8f9c790f4e5a3e9ab887a721e896e77f8fac509d7 +size 5444832096 diff --git a/Quelix-8B-v0.1.Q5_K_S.gguf b/Quelix-8B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..c6f5030 --- /dev/null +++ b/Quelix-8B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ae02c9e0bd5bbdcbe0769a6852fbd96e12afbc2d1974d96af528ffb60d68e1a +size 5315177312 diff --git a/Quelix-8B-v0.1.Q6_K.gguf b/Quelix-8B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..c79dcf7 --- /dev/null +++ b/Quelix-8B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e27a38d797838f256a753fd328a863d8ab80c72dea87f4056c858b798b23fea +size 6254199648 diff --git a/Quelix-8B-v0.1.Q8_0.gguf b/Quelix-8B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..8380847 --- /dev/null +++ b/Quelix-8B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5be6123c9b4e48f4928962e9f5220f82f9630c8ed70c21fcdcfe4e7f3cfa0a +size 8098526048 diff --git a/Quelix-8B-v0.1.f16.gguf b/Quelix-8B-v0.1.f16.gguf new file mode 100644 index 0000000..b03d104 --- /dev/null +++ b/Quelix-8B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55bc718f8d8fde3e23e6a515f97bfe62b91b7c65683fdefd428f4439363293d7 +size 15237854048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ac4141c --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: KenjiOU/Quelix-8B-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/KenjiOU/Quelix-8B-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Quelix-8B-v0.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Quelix-8B-v0.1-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/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Quelix-8B-v0.1-GGUF/resolve/main/Quelix-8B-v0.1.f16.gguf) | f16 | 15.3 | 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. + +