commit 77765b25ba738dc23a3fbaa98dea3d1b60d67ee2 Author: ModelHub XC Date: Wed Jun 3 09:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KernelGen-LM-1.7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86d43b5 --- /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-1.7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KernelGen-LM-1.7B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KernelGen-LM-1.7B.IQ4_XS.gguf b/KernelGen-LM-1.7B.IQ4_XS.gguf new file mode 100644 index 0000000..ea5ef93 --- /dev/null +++ b/KernelGen-LM-1.7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72392b4f14ea6baa71dbbae5f9e12fdb76211fc488d22f2cba116aee0727167e +size 1016281312 diff --git a/KernelGen-LM-1.7B.Q2_K.gguf b/KernelGen-LM-1.7B.Q2_K.gguf new file mode 100644 index 0000000..ff48982 --- /dev/null +++ b/KernelGen-LM-1.7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13dbf891a1daf5cd2c36aa0d8bace96ec45984135b9494087c44e8808d93a684 +size 777795808 diff --git a/KernelGen-LM-1.7B.Q3_K_L.gguf b/KernelGen-LM-1.7B.Q3_K_L.gguf new file mode 100644 index 0000000..53d5eb2 --- /dev/null +++ b/KernelGen-LM-1.7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8cbfc24102a8060b304a2c39916fed3faded57673acc7d9b4688832aa1d806d +size 1003501792 diff --git a/KernelGen-LM-1.7B.Q3_K_M.gguf b/KernelGen-LM-1.7B.Q3_K_M.gguf new file mode 100644 index 0000000..8e65f81 --- /dev/null +++ b/KernelGen-LM-1.7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9abf0eea9bb28950ef3f81667afeb939edc856f6201faea483269c5b78a61705 +size 939538656 diff --git a/KernelGen-LM-1.7B.Q3_K_S.gguf b/KernelGen-LM-1.7B.Q3_K_S.gguf new file mode 100644 index 0000000..e81c162 --- /dev/null +++ b/KernelGen-LM-1.7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513f799f9b96179c2f2525275d7d9361f81d659b55bf971b05892a302fc12a92 +size 867252448 diff --git a/KernelGen-LM-1.7B.Q4_K_M.gguf b/KernelGen-LM-1.7B.Q4_K_M.gguf new file mode 100644 index 0000000..8a3be98 --- /dev/null +++ b/KernelGen-LM-1.7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9219c14d8476ecf2e32bb989984bc55d848d910654598a88d85d8636bdcabd5 +size 1107409120 diff --git a/KernelGen-LM-1.7B.Q4_K_S.gguf b/KernelGen-LM-1.7B.Q4_K_S.gguf new file mode 100644 index 0000000..3a16056 --- /dev/null +++ b/KernelGen-LM-1.7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f87f7a520467f4c6b261b83e1ba086990f8dd037cc6a9397ca2429eda880aff4 +size 1060190432 diff --git a/KernelGen-LM-1.7B.Q5_K_M.gguf b/KernelGen-LM-1.7B.Q5_K_M.gguf new file mode 100644 index 0000000..83e38c0 --- /dev/null +++ b/KernelGen-LM-1.7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f899d968aa5da94c0dd54e04d2cb8e5f28fda84eaab4f79b0d6b2d488e9afb +size 1257879776 diff --git a/KernelGen-LM-1.7B.Q5_K_S.gguf b/KernelGen-LM-1.7B.Q5_K_S.gguf new file mode 100644 index 0000000..9779602 --- /dev/null +++ b/KernelGen-LM-1.7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:037c59d4e68cd61d2bb16ad050948d259ea1b4e3b9af15d4d11dfad83a21ec5b +size 1230584032 diff --git a/KernelGen-LM-1.7B.Q6_K.gguf b/KernelGen-LM-1.7B.Q6_K.gguf new file mode 100644 index 0000000..786adcd --- /dev/null +++ b/KernelGen-LM-1.7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd1d9d09dbcb0161ef70df70f6ba776b7493de425b78bd1f3141c2c0d274aaa +size 1417754848 diff --git a/KernelGen-LM-1.7B.Q8_0.gguf b/KernelGen-LM-1.7B.Q8_0.gguf new file mode 100644 index 0000000..f87df96 --- /dev/null +++ b/KernelGen-LM-1.7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e94cf057d71e3d8a34207b3b2cc10f5e07c5aa21c3fe8ab8ba5219585bddfbe +size 1834426592 diff --git a/KernelGen-LM-1.7B.f16.gguf b/KernelGen-LM-1.7B.f16.gguf new file mode 100644 index 0000000..26bd157 --- /dev/null +++ b/KernelGen-LM-1.7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542b8465672924239f379adebdd8075829659436831d1218077d5678fe11434f +size 3447349472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a64ce6a --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: AscendKernelGen/KernelGen-LM-1.7B +datasets: +- AscendKernelGen/Ascend-COT-v2-packed +language: +- en +- zh +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-1.7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KernelGen-LM-1.7B-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-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KernelGen-LM-1.7B-GGUF/resolve/main/KernelGen-LM-1.7B.f16.gguf) | f16 | 3.5 | 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. + +