commit 7a64af0000a8637705ee802820b79e0fcbd42816 Author: ModelHub XC Date: Fri Sep 18 18:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7b4e670 --- /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-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-11-rafathenev2-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..283b54c --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: shisa-ai/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6 +datasets: +- shisa-ai/shisa-v1-athenev2-reannotated-filtered +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-11-rafathenev2-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-11-rafathenev2-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-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6-GGUF/resolve/main/ablation-11-rafathenev2-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-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf new file mode 100644 index 0000000..89240b4 --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eaa97e7be8fdfef42958c7770e0485f1b0a699d32b39dcbde5f5e6b15a94b49 +size 4484364448 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf new file mode 100644 index 0000000..5f664d1 --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f24397110d3dad9e0e212ec807ee24e1bf45b76819e3ed8939d4d88ce9ba92d +size 3179133088 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf new file mode 100644 index 0000000..bed49cc --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90b1be85e13d71eec3cc7d36e3a234fe47a372507528da4af5fb615452b02406 +size 4321958048 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf new file mode 100644 index 0000000..f0704ea --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61e3e90b4b0f856a3a9ac49b61ba474e85d6f031d852b3f28d78f903bbd30e12 +size 4018919584 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf new file mode 100644 index 0000000..560b315 --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35031b2b382a63a3224e5b71c081ce0898dbcbc06916fb161fac3ff3de865ad2 +size 3664500896 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_M.gguf new file mode 100644 index 0000000..5a55a20 --- /dev/null +++ b/ablation-11-rafathenev2-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:cb00a226ad1aa622a7ad116df61591bca0ebcde6c9edf2b0f6753448e8fe73f9 +size 4920735904 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q4_K_S.gguf new file mode 100644 index 0000000..ae1ef90 --- /dev/null +++ b/ablation-11-rafathenev2-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:f18103fb301822373a496f1e8350c46aee7ffe3cc4a32fe4f85ff00a1427ccba +size 4692670624 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_M.gguf new file mode 100644 index 0000000..f0ec5cb --- /dev/null +++ b/ablation-11-rafathenev2-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:d89d9a7571d3e369df42c8372eb61335846dbae02ec834afe5fbd54dac33a1a8 +size 5732989088 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf new file mode 100644 index 0000000..3047852 --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc09dac3c6dbca4b4447cafb9131b7dfecd5fb10e812b963fda9f93eaa600ca +size 5599295648 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf new file mode 100644 index 0000000..ad02081 --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c0127f075c3ca29f97515e7e7a55271d1376e62d24c08dabec988768a8e389 +size 6596008096 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf new file mode 100644 index 0000000..0b1d999 --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3c525dd8d9baa7ff567c39e41f82172c887e5b62f0f134a8caa697a4b028d95 +size 8540772512 diff --git a/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf new file mode 100644 index 0000000..d45f89b --- /dev/null +++ b/ablation-11-rafathenev2-shisa-v2-llama-3.1-8b-lr8e6.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c13b87e6df901b87d40dd2a1b22c07d8c590a7b0061150e96d604db385479a +size 16068892832