commit 228e4528e50f2ff55230f921c4025e80fe322c62 Author: ModelHub XC Date: Fri Jul 10 02:21:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Multi_SFT_8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..91a555d --- /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 +Multi_SFT_8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Multi_SFT_8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Multi_SFT_8B.IQ4_XS.gguf b/Multi_SFT_8B.IQ4_XS.gguf new file mode 100644 index 0000000..a0d8d6a --- /dev/null +++ b/Multi_SFT_8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1037ba9bac9bcd4daa87dd8d2fe0d54466717f05a671645b39468a57e1482cd +size 4484367648 diff --git a/Multi_SFT_8B.Q2_K.gguf b/Multi_SFT_8B.Q2_K.gguf new file mode 100644 index 0000000..6f361dd --- /dev/null +++ b/Multi_SFT_8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f149a7d21bbf020998342790915a7d5dd9f8c742f87d58f7bffce80e69cd2c1 +size 3179136288 diff --git a/Multi_SFT_8B.Q3_K_L.gguf b/Multi_SFT_8B.Q3_K_L.gguf new file mode 100644 index 0000000..7c01d6c --- /dev/null +++ b/Multi_SFT_8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b6a6007699f0c3c860290377993bdaf51c4667b6df5d3d2714da0e2b6d685e +size 4321961248 diff --git a/Multi_SFT_8B.Q3_K_M.gguf b/Multi_SFT_8B.Q3_K_M.gguf new file mode 100644 index 0000000..790597c --- /dev/null +++ b/Multi_SFT_8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0916e682d979e2a0bd5b33bcb5c40406541ec7ed384fb446d57249d6b96cf0 +size 4018922784 diff --git a/Multi_SFT_8B.Q3_K_S.gguf b/Multi_SFT_8B.Q3_K_S.gguf new file mode 100644 index 0000000..84fb233 --- /dev/null +++ b/Multi_SFT_8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b39f511270f31584ae832d7631a6b8c358f23740da3456bc619e31010b3d33f +size 3664504096 diff --git a/Multi_SFT_8B.Q4_K_M.gguf b/Multi_SFT_8B.Q4_K_M.gguf new file mode 100644 index 0000000..4735ce4 --- /dev/null +++ b/Multi_SFT_8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3b8342306b43e879844d510a7604e4aee801a3b52cb421c1c17958c24c2d47 +size 4920739104 diff --git a/Multi_SFT_8B.Q4_K_S.gguf b/Multi_SFT_8B.Q4_K_S.gguf new file mode 100644 index 0000000..868da0a --- /dev/null +++ b/Multi_SFT_8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c3cc27f1ebafc0696a05b9e9f09aa5350ac7b993021309a602495bbb9041e4e +size 4692673824 diff --git a/Multi_SFT_8B.Q5_K_M.gguf b/Multi_SFT_8B.Q5_K_M.gguf new file mode 100644 index 0000000..c2df02b --- /dev/null +++ b/Multi_SFT_8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6e03883fbd0b71c8ef2e4a9130325769f017ba8c0289d5f0081f86ee1d9d86 +size 5732992288 diff --git a/Multi_SFT_8B.Q5_K_S.gguf b/Multi_SFT_8B.Q5_K_S.gguf new file mode 100644 index 0000000..4dce1e4 --- /dev/null +++ b/Multi_SFT_8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e647928130512fcea782ec0042ed88f4bcccbb5edbbe18c4330a0edd868c6f45 +size 5599298848 diff --git a/Multi_SFT_8B.Q6_K.gguf b/Multi_SFT_8B.Q6_K.gguf new file mode 100644 index 0000000..135a8b2 --- /dev/null +++ b/Multi_SFT_8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8df24b6aad64d36b90aae2abddbf15730cf33c9c55829d3400747923f6fbd32 +size 6596011296 diff --git a/Multi_SFT_8B.Q8_0.gguf b/Multi_SFT_8B.Q8_0.gguf new file mode 100644 index 0000000..2fd77ae --- /dev/null +++ b/Multi_SFT_8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88756e7f98f9ba3c4bf4dc285157dfd1f204bb30708c872868ba2658927b9fce +size 8540775712 diff --git a/Multi_SFT_8B.f16.gguf b/Multi_SFT_8B.f16.gguf new file mode 100644 index 0000000..8f640d7 --- /dev/null +++ b/Multi_SFT_8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401307dc534852540ef96709e640022f698538a00ddaa30c7842725916640321 +size 16068896032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae65065 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: rl-llm-coders/Multi_SFT_8B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/rl-llm-coders/Multi_SFT_8B + + +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/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Multi_SFT_8B-GGUF/resolve/main/Multi_SFT_8B.f16.gguf) | f16 | 16.2 | 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. + +