commit 4bd624fa5879a3f96418f22981bd30d14c1623cd Author: ModelHub XC Date: Fri Sep 25 11:05:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2867728 --- /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-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..431a2f4 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: shisa-ai/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b +datasets: +- shisa-ai/shisa-v2-best-of-n-athenev2-tulu70b-llama33-only +- shisa-ai/shisa-v2-roleplaying +- shisa-ai/translation-master-set +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-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-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/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b-GGUF/resolve/main/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.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-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.IQ4_XS.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.IQ4_XS.gguf new file mode 100644 index 0000000..03db651 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2366b2ca0ad5758463a0416ed82c50d6ecc3b09869fb6706b54a0f01a00c0c28 +size 4484364896 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q2_K.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..5e76644 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984f4711ad6553e17e78f8ec65c3ebadbf8784b2302cff8d956edd19ae532212 +size 3179133536 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_L.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..a5551fb --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51a5cad06c08e5bce1f9da4b4f7391e6c1ce704bc378464f698a9ae1ab1d6853 +size 4321958496 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_M.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..6b20042 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04fbb3aa2bb297f996d1494a212f234384019417b4332d8a903f391fe04b9a6 +size 4018920032 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_S.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..c466d6e --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:391b16c7c9cf6ed871a302342a63fcb5e89eb72a11688e3de4174237452be493 +size 3664501344 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_M.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..92973d4 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e172fbedc5e4fba0dfdfea2245aac003e42a9469c2dfc4e72d7d5486fc29f99 +size 4920736352 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_S.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..fc0a9e7 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b636909942aeaf1c81f6b72066fba76b67abbbd36ad0b776f78b33a0c2beacb +size 4692671072 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_M.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..0214b25 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ada9f10e53f4668885b3af1935fc2f5ad3b635d8e0941f82b584f759beae629 +size 5732989536 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_S.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..8611f7a --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ec0125ad693ff07b2cb567c2ef3834fa21719c6d7f6615ea505ea82646cf8d +size 5599296096 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q6_K.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..435fa21 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f034aaa406936c18b87f63ac3d2aa8693d5c4bb75849cf53a8388fdc1a3ace1 +size 6596008544 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q8_0.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..b82c8c4 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:421c0e632f9d3f60969be2b00f26200ecf226e6fff8699dc83861aaf2cdb198d +size 8540772960 diff --git a/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.f16.gguf b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.f16.gguf new file mode 100644 index 0000000..157dc69 --- /dev/null +++ b/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5bde1d7f0b699f1ab197153fb4adb8012118443a17f9232fc8d0fe810dbbdf +size 16068893280