commit 9c570bb358f90919c551736ece2828d667d02f8b Author: ModelHub XC Date: Fri Jun 12 04:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9c686c3 --- /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 +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d0840fc --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: shisa-ai/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6 +datasets: +- shisa-ai/shisa-v2-code-math-reasoning-sft-mix +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/shisa-ai/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-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/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.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. + + diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf new file mode 100644 index 0000000..66a936a --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eddf33969f264dd068b0dd486842b1a68a272c27adef6cf62a288cf00c08993d +size 4484364416 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf new file mode 100644 index 0000000..d824ed4 --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebafb808d4d4dada39da8f1d1cac1012543c82963c76e6f3d4f6a9cdb8a5688d +size 3179133056 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf new file mode 100644 index 0000000..a0fda93 --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36346f0a31bda61244771b005c5b8be703bff459c18de773732d6aa5d74b92aa +size 4321958016 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf new file mode 100644 index 0000000..57c0e93 --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d6185f2915409d6c6648ebd38512646edd5554d514dbcbe7c631bb7c42e68de +size 4018919552 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf new file mode 100644 index 0000000..59f9e6b --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda88b8cc77e9b3a05c87531fb6cbb346b594f863ee34906e25e6f25cf1f700f +size 3664500864 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf new file mode 100644 index 0000000..b063784 --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc3431031bd8a731331189743cce7868989991c466637ce5f86f202370a1a76 +size 4920735872 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf new file mode 100644 index 0000000..f4818c6 --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db35ac1d4f999185ebfbfb13b09ae122d471514ffa7c87b0050c6ff4dd7604f +size 4692670592 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf new file mode 100644 index 0000000..44279c5 --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8913d0bd06e0b877f3496f21bf01464a878237b7fee390dd8bab340316845a68 +size 5732989056 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf new file mode 100644 index 0000000..c17c884 --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c270570fd27bc0e6a4b44ca91874a08823f4ea33d89ab65e27193b1fa361eae8 +size 5599295616 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf new file mode 100644 index 0000000..0c1b38d --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d946d018dd700d7de9cd161467b4691cd6797e6d94433b1838283269c91a6a +size 6596008064 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf new file mode 100644 index 0000000..2625ef4 --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:973c5a2662a35a2163c1ed3e3b2afd9b49f21da4a3669b2296335fd7469fc5c6 +size 8540772480 diff --git a/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf new file mode 100644 index 0000000..8f11fef --- /dev/null +++ b/ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5cfa8f62a9aeef3c13b53be2015b35a619303fea0bbf114092b3d4a60f8d050 +size 16068892800