commit 7482333e37ec5c7b7dc98d076843aa54a8859203 Author: ModelHub XC Date: Wed Jun 3 10:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KernelGen-LM-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..012df84 --- /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 +KernelGen-LM-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KernelGen-LM-8B.IQ4_XS.gguf b/KernelGen-LM-8B.IQ4_XS.gguf new file mode 100644 index 0000000..fc5e9bb --- /dev/null +++ b/KernelGen-LM-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e189b991a207b86164582f0497e9e7a0019e2d55a7ee92b0ac41f7f7f31c18bd +size 4593296768 diff --git a/KernelGen-LM-8B.Q2_K.gguf b/KernelGen-LM-8B.Q2_K.gguf new file mode 100644 index 0000000..4cec688 --- /dev/null +++ b/KernelGen-LM-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9551fb9ff421866b5a37fa9c08951544118d84d2d2d84295162331e9c530f8 +size 3281732992 diff --git a/KernelGen-LM-8B.Q3_K_L.gguf b/KernelGen-LM-8B.Q3_K_L.gguf new file mode 100644 index 0000000..47f2c9f --- /dev/null +++ b/KernelGen-LM-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc977248f3afa556d8c11b57a0107539e6e17a27c7559549249062fcba26df9 +size 4431394176 diff --git a/KernelGen-LM-8B.Q3_K_M.gguf b/KernelGen-LM-8B.Q3_K_M.gguf new file mode 100644 index 0000000..8945228 --- /dev/null +++ b/KernelGen-LM-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48cb589579daa06db82a7e539223876f8bcbb8b2453830ceacd2ecf37c50a892 +size 4124161408 diff --git a/KernelGen-LM-8B.Q3_K_S.gguf b/KernelGen-LM-8B.Q3_K_S.gguf new file mode 100644 index 0000000..7246205 --- /dev/null +++ b/KernelGen-LM-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668c0fab4c2dd2f30830914337775e2b996a3cd3fb3f38de842ac58b9471d5f1 +size 3769611648 diff --git a/KernelGen-LM-8B.Q4_K_M.gguf b/KernelGen-LM-8B.Q4_K_M.gguf new file mode 100644 index 0000000..157b789 --- /dev/null +++ b/KernelGen-LM-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de955f04e4a5d7ed60f150f60b007168c21ed9801c1c41a8ec7fd954b1571e5e +size 5027784064 diff --git a/KernelGen-LM-8B.Q4_K_S.gguf b/KernelGen-LM-8B.Q4_K_S.gguf new file mode 100644 index 0000000..9ab1f46 --- /dev/null +++ b/KernelGen-LM-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1226d9d93fc59ba496e84100970604b959ab6a08963a244f830cf642e10ac72 +size 4802012544 diff --git a/KernelGen-LM-8B.Q5_K_M.gguf b/KernelGen-LM-8B.Q5_K_M.gguf new file mode 100644 index 0000000..70f09f9 --- /dev/null +++ b/KernelGen-LM-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7035fb00da3e184bfe50450a8afc5ed3c0b290bee21a827c4123149790c02b +size 5851112832 diff --git a/KernelGen-LM-8B.Q5_K_S.gguf b/KernelGen-LM-8B.Q5_K_S.gguf new file mode 100644 index 0000000..72d8d65 --- /dev/null +++ b/KernelGen-LM-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342d5107202274015670f42e81d1c1cbf89358e1d43b04dc5a8e834e1f7b6c83 +size 5720761728 diff --git a/KernelGen-LM-8B.Q6_K.gguf b/KernelGen-LM-8B.Q6_K.gguf new file mode 100644 index 0000000..e5fdb82 --- /dev/null +++ b/KernelGen-LM-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd26dec3725ed76bfbf1057d97948f46866c4400df23d23d129f50bfbcd2f43b +size 6725899648 diff --git a/KernelGen-LM-8B.Q8_0.gguf b/KernelGen-LM-8B.Q8_0.gguf new file mode 100644 index 0000000..cce9d72 --- /dev/null +++ b/KernelGen-LM-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49910d650606e9d7b7a313a7567b01bec140facb817b8280155c32ac8bec929f +size 8709518720 diff --git a/KernelGen-LM-8B.f16.gguf b/KernelGen-LM-8B.f16.gguf new file mode 100644 index 0000000..4b6746d --- /dev/null +++ b/KernelGen-LM-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:178eb2fb63ede0586ebfe53bac6b2ddb65c77018f239d4cb2cbedcdbf297d7a5 +size 16388044160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d532ab8 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: AscendKernelGen/KernelGen-LM-8B +datasets: +- AscendKernelGen/Ascend-COT-v2-packed +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- code-generation +- npu +- ascend +- chain-of-thought +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AscendKernelGen/KernelGen-LM-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KernelGen-LM-8B-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/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-8B-GGUF/resolve/main/KernelGen-LM-8B.f16.gguf) | f16 | 16.5 | 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. + +