commit cbbe07ba3a02599030687b8c964c8d17ff4a5347 Author: ModelHub XC Date: Mon Jul 6 12:21:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/35b-beta-long-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fae1708 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +35b-beta-long.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/35b-beta-long.i1-IQ1_M.gguf b/35b-beta-long.i1-IQ1_M.gguf new file mode 100644 index 0000000..a74e524 --- /dev/null +++ b/35b-beta-long.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a0fb17585f0a7fd8c7e7e445c8f2a953b11e5c1cb2b60b1e32ead09d391806d +size 9146637856 diff --git a/35b-beta-long.i1-IQ1_S.gguf b/35b-beta-long.i1-IQ1_S.gguf new file mode 100644 index 0000000..7335650 --- /dev/null +++ b/35b-beta-long.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3b1a12521066828a985797cbabd24c5a46e4fb8fca625a2766e1ddf63bbb79 +size 8523390496 diff --git a/35b-beta-long.i1-IQ2_M.gguf b/35b-beta-long.i1-IQ2_M.gguf new file mode 100644 index 0000000..e6a9708 --- /dev/null +++ b/35b-beta-long.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bdeb1659157eb53a933643c1281ce703678488cfeab3d21f99cdf047d6a3d2e +size 12675096096 diff --git a/35b-beta-long.i1-IQ2_S.gguf b/35b-beta-long.i1-IQ2_S.gguf new file mode 100644 index 0000000..2db701a --- /dev/null +++ b/35b-beta-long.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38dea4ce76bec493a9b614a2c63608b9573f759ac3ae592424888dceea4c8087 +size 11844099616 diff --git a/35b-beta-long.i1-IQ2_XS.gguf b/35b-beta-long.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6fc8256 --- /dev/null +++ b/35b-beta-long.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35a014344b5d9de2b2ff6239835b7558b4eadcf8d35f99c8cd2973b43fb59eb +size 11100266016 diff --git a/35b-beta-long.i1-IQ2_XXS.gguf b/35b-beta-long.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..81eabb2 --- /dev/null +++ b/35b-beta-long.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09001c43ab5a36ccd617663d5bc124d6bac8dc3a414e8d94170f417732249c97 +size 10185383456 diff --git a/35b-beta-long.i1-IQ3_M.gguf b/35b-beta-long.i1-IQ3_M.gguf new file mode 100644 index 0000000..93cd6fc --- /dev/null +++ b/35b-beta-long.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed2e66e07cd40b10b2ae1b4e0a96a242266655750f51fcf2bbc5489f897acffc +size 16697695776 diff --git a/35b-beta-long.i1-IQ3_S.gguf b/35b-beta-long.i1-IQ3_S.gguf new file mode 100644 index 0000000..82a63e7 --- /dev/null +++ b/35b-beta-long.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2376861db4d92e82d80203a1112977df2a9a1394376d05d0c98456f9874311e +size 15862111776 diff --git a/35b-beta-long.i1-IQ3_XS.gguf b/35b-beta-long.i1-IQ3_XS.gguf new file mode 100644 index 0000000..80e8aa2 --- /dev/null +++ b/35b-beta-long.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b665393fdc466905f935c4b8f326fbeb60a97a5147ab318e82db70706a8a4b15 +size 15091408416 diff --git a/35b-beta-long.i1-IQ3_XXS.gguf b/35b-beta-long.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c440a32 --- /dev/null +++ b/35b-beta-long.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aefb5a45c743087b90c8e3b0cd86e46f8a1003edb6c1fc9e52cf9aa10becf3d +size 13832461856 diff --git a/35b-beta-long.i1-IQ4_XS.gguf b/35b-beta-long.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b41696c --- /dev/null +++ b/35b-beta-long.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0e7e2bd73146fe763cdb86f8fd159376f81756c1b9987c389f18bfc2f69d30 +size 19201826336 diff --git a/35b-beta-long.i1-Q2_K.gguf b/35b-beta-long.i1-Q2_K.gguf new file mode 100644 index 0000000..e86e616 --- /dev/null +++ b/35b-beta-long.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b91bf2a051b5a5638fef7c3faa0473026a0d697cb613229b4d23498c97e049 +size 13817388576 diff --git a/35b-beta-long.i1-Q3_K_L.gguf b/35b-beta-long.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9be2d12 --- /dev/null +++ b/35b-beta-long.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b8dc573b8c8e82afe998852e4a906b90b65e7c31ae8aaa682156d30bbd607c2 +size 19149397536 diff --git a/35b-beta-long.i1-Q3_K_M.gguf b/35b-beta-long.i1-Q3_K_M.gguf new file mode 100644 index 0000000..bd4e792 --- /dev/null +++ b/35b-beta-long.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd70c3deed80b202b6dcacff58fa185674490ce0dc98581209ba898f145ba6fa +size 17618476576 diff --git a/35b-beta-long.i1-Q3_K_S.gguf b/35b-beta-long.i1-Q3_K_S.gguf new file mode 100644 index 0000000..678d9de --- /dev/null +++ b/35b-beta-long.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed687efeb43c7f1378eca39a38d7310edadc1a63fdc908d17ca344b3f4c0907 +size 15862111776 diff --git a/35b-beta-long.i1-Q4_0.gguf b/35b-beta-long.i1-Q4_0.gguf new file mode 100644 index 0000000..1e979e7 --- /dev/null +++ b/35b-beta-long.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4c012ce81c571c65137b017e8d81ea6d34fd6776650cb82f17c61b6190d691 +size 20287102496 diff --git a/35b-beta-long.i1-Q4_K_M.gguf b/35b-beta-long.i1-Q4_K_M.gguf new file mode 100644 index 0000000..dc6f585 --- /dev/null +++ b/35b-beta-long.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f42ee1c36176c20509e2bd06ff20a6ec8c8b3a78fc59fdae4e709d5e544ed59e +size 21527043616 diff --git a/35b-beta-long.i1-Q4_K_S.gguf b/35b-beta-long.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6bd6082 --- /dev/null +++ b/35b-beta-long.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4445d793f7b969dc0e95616d2f73c2ee391e7ff16292fa427e3fcbeeddc802 +size 20378328608 diff --git a/35b-beta-long.i1-Q5_K_M.gguf b/35b-beta-long.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f602264 --- /dev/null +++ b/35b-beta-long.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350a5c6634f4811e6f6c4d5eb342873dccb1898c75f0ec8b2c7bc8d0d24d5c7c +size 25008315936 diff --git a/35b-beta-long.i1-Q5_K_S.gguf b/35b-beta-long.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b305084 --- /dev/null +++ b/35b-beta-long.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b57773c8f98dda6fa62ea6e6e38079cdccd86c4a8c5fd1b9a872506f94036e8f +size 24339848736 diff --git a/35b-beta-long.i1-Q6_K.gguf b/35b-beta-long.i1-Q6_K.gguf new file mode 100644 index 0000000..dc952e5 --- /dev/null +++ b/35b-beta-long.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c9190502e59a4cd0884392235aabe0657c50433eda7bc554192cfd944885a72 +size 28707167776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c3cfdd1 --- /dev/null +++ b/README.md @@ -0,0 +1,95 @@ +--- +base_model: CausalLM/35b-beta-long +datasets: +- JosephusCheung/GuanacoDataset +- meta-math/MetaMathQA +- jondurbin/airoboros-3.1 +- WizardLM/WizardLM_evol_instruct_V2_196k +- RyokoAI/ShareGPT52K +- RyokoAI/Fandom23K +- milashkaarshif/MoeGirlPedia_wikitext_raw_archive +- wikipedia +- wiki_lingua +- garage-bAInd/Open-Platypus +- LDJnr/Puffin +- BAAI/COIG +- TigerResearch/tigerbot-zhihu-zh-10k +- liwu/MNBVC +- teknium/openhermes +- CausalLM/Refined-Anime-Text +- microsoft/orca-math-word-problems-200k +- m-a-p/CodeFeedback-Filtered-Instruction +language: +- en +- zh +- ja +- de +library_name: transformers +license: wtfpl +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/CausalLM/35b-beta-long + + +static quants are available at https://huggingface.co/mradermacher/35b-beta-long-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/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ1_S.gguf) | i1-IQ1_S | 8.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ1_M.gguf) | i1-IQ1_M | 9.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 10.3 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ2_XS.gguf) | i1-IQ2_XS | 11.2 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ2_S.gguf) | i1-IQ2_S | 11.9 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ2_M.gguf) | i1-IQ2_M | 12.8 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q2_K.gguf) | i1-Q2_K | 13.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ3_XS.gguf) | i1-IQ3_XS | 15.2 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ3_S.gguf) | i1-IQ3_S | 16.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q3_K_S.gguf) | i1-Q3_K_S | 16.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ3_M.gguf) | i1-IQ3_M | 16.8 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q3_K_L.gguf) | i1-Q3_K_L | 19.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-IQ4_XS.gguf) | i1-IQ4_XS | 19.3 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q4_0.gguf) | i1-Q4_0 | 20.4 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q5_K_S.gguf) | i1-Q5_K_S | 24.4 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.1 | | +| [GGUF](https://huggingface.co/mradermacher/35b-beta-long-i1-GGUF/resolve/main/35b-beta-long.i1-Q6_K.gguf) | i1-Q6_K | 28.8 | practically like static Q6_K | + +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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..9599234 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9df0a0184c92d8ce742aa345e9fe8fead561dd28ccfb1496f5d736f0fac45f8 +size 11478085