commit fa9d76d30c5c3631cf33f7f0eed0710623aa8e42 Author: ModelHub XC Date: Fri Jun 12 02:34:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d4823e2 --- /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-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.f16.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-00-baseline-shisa-v2-llama3-8b-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..3a9fcb0 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: shisa-ai/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6 +datasets: +- augmxnt/ultra-orca-boros-en-ja-v1 +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/shisa-ai/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ablation-00-baseline-shisa-v2-llama3-8b-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-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6-GGUF/resolve/main/ablation-00-baseline-shisa-v2-llama3-8b-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-00-baseline-shisa-v2-llama3-8b-lr8e6.IQ4_XS.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.IQ4_XS.gguf new file mode 100644 index 0000000..2915b7e --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:311a8ca049d81e6de730fcfe904a2519006b2e5a7e7e9d66c082ba1cf9dac94a +size 4484364160 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q2_K.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q2_K.gguf new file mode 100644 index 0000000..cc47000 --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6796a593edcd17d4c795d81d512e6cad43f29aa3721c7112b95664b5546a15cc +size 3179132800 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_L.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_L.gguf new file mode 100644 index 0000000..df2ba38 --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2de56e61915b70bc55ce49fe5c978e8247b0ab5e8a4ec354367fd4960c0360 +size 4321957760 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_M.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_M.gguf new file mode 100644 index 0000000..b7c878d --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d10f10e306d6d9d6f5846d657875fb47a23d6fb581cd694ca0e983512142b174 +size 4018919296 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_S.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_S.gguf new file mode 100644 index 0000000..dc81c30 --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d5f01ee6f14bafa192803241a61fbeed3d23a1b8ec7457ec112e90a05956c7 +size 3664500608 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_M.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_M.gguf new file mode 100644 index 0000000..3d46317 --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5814faaf915fd6a576a3f10f414f933eb45502f35ab3bf76360543afed8f3560 +size 4920735616 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_S.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_S.gguf new file mode 100644 index 0000000..78e3150 --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f21bae6c613682e4d2a833418e88c771e9388eb2b24eff3e7721d63ced9267d7 +size 4692670336 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_M.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_M.gguf new file mode 100644 index 0000000..d637a3d --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8b07f0dee5e2c14df71862d0c727e04d350f73541987b5df450dd62d7d1e28 +size 5732988800 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_S.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_S.gguf new file mode 100644 index 0000000..104fff7 --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b64450eb6c4ed0012d537688c83b6d4efb4024e18f2ae9c86b4f9d52fb20f10 +size 5599295360 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q6_K.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q6_K.gguf new file mode 100644 index 0000000..9a32417 --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a1368e343d92e8d474808e5195131ea7c11cc397856140c34cad2371e976f7 +size 6596007808 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q8_0.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q8_0.gguf new file mode 100644 index 0000000..cb02d1d --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a640c055b32bdf0b1aad55652d95b457b0787b22596a8a2e8916d5acbd9b355 +size 8540772224 diff --git a/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.f16.gguf b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.f16.gguf new file mode 100644 index 0000000..b1c0f19 --- /dev/null +++ b/ablation-00-baseline-shisa-v2-llama3-8b-lr8e6.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e81ba7638d3bf41de876f807209d3472694e9a327607da371de875095612f0 +size 16068892544