commit a8149fe8292b45782426bcba0e09a4f69359c229 Author: ModelHub XC Date: Fri Sep 18 09:31:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0e58cc2 --- /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-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-26-reasoning.inputs-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..d12ab0c --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: shisa-ai/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6 +datasets: +- shisa-ai/s1K-1.1-translated-sharegpt +- shisa-ai/s1K-1.1-translated-sharegpt +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-26-reasoning.inputs-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-26-reasoning.inputs-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-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-26-reasoning.inputs-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-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf new file mode 100644 index 0000000..4cc48da --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7935a9430e4c2b15ef6012205d38abfc253857017f6f111f1053d3b5c80061b0 +size 4484364672 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf new file mode 100644 index 0000000..8fd2162 --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e215013df79e65d131f962875793d9bb7966c9eeff1d67fe0af88d1d5b5a9b +size 3179133312 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf new file mode 100644 index 0000000..12d1ba1 --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:889f59bf83a34bbf4045033ef545b5c2396b85a8ecceabbcdeb7887347240b25 +size 4321958272 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf new file mode 100644 index 0000000..586d5b1 --- /dev/null +++ b/ablation-26-reasoning.inputs-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:b43a21958918d3386ca2d7f5d06ec27186d805b1bc2f2531ea1685f81e6f1f4f +size 4018919808 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf new file mode 100644 index 0000000..93b96e5 --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78646d3e81513a2524e9d003565ac797a30caedd4a242ca165693bb573e8eefb +size 3664501120 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf new file mode 100644 index 0000000..5d6b817 --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc3dc9c2965d09cfb409eb647933ed8f690e6bb27655470daa7dc6ae5abaa0b +size 4920736128 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf new file mode 100644 index 0000000..0651aec --- /dev/null +++ b/ablation-26-reasoning.inputs-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:a8a9f8a4b34eb20acd77f9bde9d6850e7d918d209039e5e70b68081ce99fbd7c +size 4692670848 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf new file mode 100644 index 0000000..597762c --- /dev/null +++ b/ablation-26-reasoning.inputs-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:e9e56b2a64d8bf0f36a22c733d33f3df2393f4d70477cde616707e8bce5de8cb +size 5732989312 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf new file mode 100644 index 0000000..076b06a --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61db9864b8c8f90d946c81e5a7fe39c33bbb4d2b163264cefaaec92aee5eb5ab +size 5599295872 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf new file mode 100644 index 0000000..65f1daf --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac31a4da8018bfb7784719e536a84cdb99ee01d3607f6cfea84170a6217017fd +size 6596008320 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf new file mode 100644 index 0000000..91c533d --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1dedf8ab715152bb8299fe0a7e1fccd0ea2fcbe1d5c834a06ab372f9eee2f2e +size 8540772736 diff --git a/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf new file mode 100644 index 0000000..b4b31da --- /dev/null +++ b/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d06b35036cbc274de3b4956eb5af1fc22d6b9285abffa24185609db12a71d3c +size 16068893056