commit b8e076145ccee2c0b0a59ef7d3c3e2e1ef06bc11 Author: ModelHub XC Date: Sat Jun 13 14:30:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6f0927d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-81-bestofn.athenev2-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..d7686d1 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: shisa-ai/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6 +datasets: +- shisa-ai/shisa-v2-best-of-n-athenev2-only +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-81-bestofn.athenev2-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-81-bestofn.athenev2-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-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-81-bestofn.athenev2-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-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf new file mode 100644 index 0000000..9e9c251 --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8bebf9a93f7341b859e08970afbfe3dbf35388c35c56ba11026bd9531143d4 +size 4484364448 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf new file mode 100644 index 0000000..ff7f22a --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1616bc49df49c2d17c7532ca7d1ab9e64ab2167e8113a1bf1e8835d0ee54af85 +size 3179133088 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf new file mode 100644 index 0000000..3c361c8 --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c497281caf437847def70d2e008d3e41298856214f796d0bcdaac0f14a51145 +size 4321958048 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf new file mode 100644 index 0000000..1f8f403 --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c77d712af703962185c177c7f67dc2eb814aef4e8890ad373b75cdcc5d72906 +size 4018919584 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf new file mode 100644 index 0000000..a045a76 --- /dev/null +++ b/ablation-81-bestofn.athenev2-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:ba973d19921374e5159344d0fec8d7c13f11883923de1d59e7600af15d4291fc +size 3664500896 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf new file mode 100644 index 0000000..e31f347 --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232f298795177c1efae7413d42946370442062c421c32ad33855dc5398e9f85d +size 4920735904 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf new file mode 100644 index 0000000..b1b6337 --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5884c1f3bc009ec1a815d0d4dfcd12bbadcb5eb4662f2380c41b372f7acf5807 +size 4692670624 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf new file mode 100644 index 0000000..faa25bb --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ece8b77861ad0f383323da9eeb4e92733e3b106aa917671ec6fb84074d913f9 +size 5732989088 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf new file mode 100644 index 0000000..52034e8 --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a21e9439fbf4ba1c7bbbb154135d6eb6e4b0f4bcedcbcb1b33a779463dd26b +size 5599295648 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf new file mode 100644 index 0000000..6a9514b --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2155c2645c20db0de4bdb0bd5dd98fb0a98a0e5ad52f8fd3bf412e72c6755154 +size 6596008096 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf new file mode 100644 index 0000000..a0d6852 --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:602c310d576c3e0f279c2c7af8a6188ed62d3e79f2ea2b2df23386139229889f +size 8540772512 diff --git a/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf new file mode 100644 index 0000000..157e3cc --- /dev/null +++ b/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0410a33b37c3bf2b343c10ea66e5367ac51983b78393cd78825f8a9bd455c256 +size 16068892832