commit 62ec1a70284a6850d3450a737bec4a217987055d Author: ModelHub XC Date: Sun Sep 20 04:36:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8b-finetomed-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cd16fa9 --- /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 +llama-3.1-8b-finetomed.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-finetomed.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b468c98 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Mkk2283/llama-3.1-8b-finetomed +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Mkk2283/llama-3.1-8b-finetomed + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-8b-finetomed-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/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-finetomed-GGUF/resolve/main/llama-3.1-8b-finetomed.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/llama-3.1-8b-finetomed.IQ4_XS.gguf b/llama-3.1-8b-finetomed.IQ4_XS.gguf new file mode 100644 index 0000000..474a6c6 --- /dev/null +++ b/llama-3.1-8b-finetomed.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd152c58c2b457003d473d6843bf27f4ead8c633721e58a90428261d416040f +size 4484368448 diff --git a/llama-3.1-8b-finetomed.Q2_K.gguf b/llama-3.1-8b-finetomed.Q2_K.gguf new file mode 100644 index 0000000..46cf122 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:559376a5fc055851cd789bb2aac0fd300b4008ba35f05f56ef3f0faebe65cdcb +size 3179137088 diff --git a/llama-3.1-8b-finetomed.Q3_K_L.gguf b/llama-3.1-8b-finetomed.Q3_K_L.gguf new file mode 100644 index 0000000..c63a5c7 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6044e2f2e5499d060cafb547d66c15a77891405d0ea7319e664cc33382358c88 +size 4321962048 diff --git a/llama-3.1-8b-finetomed.Q3_K_M.gguf b/llama-3.1-8b-finetomed.Q3_K_M.gguf new file mode 100644 index 0000000..3077e5a --- /dev/null +++ b/llama-3.1-8b-finetomed.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd90d5829574e0487752680b44ba49bdcfe41781738c56cfe62d57ff226183e +size 4018923584 diff --git a/llama-3.1-8b-finetomed.Q3_K_S.gguf b/llama-3.1-8b-finetomed.Q3_K_S.gguf new file mode 100644 index 0000000..82a4399 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d8be01540d8fa695d179bce6172da95ac1451114fd23352f54af26cff2e17f +size 3664504896 diff --git a/llama-3.1-8b-finetomed.Q4_K_M.gguf b/llama-3.1-8b-finetomed.Q4_K_M.gguf new file mode 100644 index 0000000..43799b8 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:637b47a2bbcd9c0cb32f6a2f638c86a9f75f52eabdf3c3f359e9c86ea5285863 +size 4920739904 diff --git a/llama-3.1-8b-finetomed.Q4_K_S.gguf b/llama-3.1-8b-finetomed.Q4_K_S.gguf new file mode 100644 index 0000000..ac96ba9 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0942fdbb805a5c0b885994e11d464c4ed91188c90dd95aa403687bab60119946 +size 4692674624 diff --git a/llama-3.1-8b-finetomed.Q5_K_M.gguf b/llama-3.1-8b-finetomed.Q5_K_M.gguf new file mode 100644 index 0000000..6dd2572 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a8d38c542a2c256b9402d042ee1f919005b6d45a8b464f38ad062d75c5cc66 +size 5732993088 diff --git a/llama-3.1-8b-finetomed.Q5_K_S.gguf b/llama-3.1-8b-finetomed.Q5_K_S.gguf new file mode 100644 index 0000000..a74f253 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32baf27bbfe0e29e56f72110f87b141fbef9a2bce85fcb6ef854498917aa5005 +size 5599299648 diff --git a/llama-3.1-8b-finetomed.Q6_K.gguf b/llama-3.1-8b-finetomed.Q6_K.gguf new file mode 100644 index 0000000..9c1eb48 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8bed5cc6c1470de4749b4433a76c32cab264447a15bf338a79e3c945cd771a +size 6596012096 diff --git a/llama-3.1-8b-finetomed.Q8_0.gguf b/llama-3.1-8b-finetomed.Q8_0.gguf new file mode 100644 index 0000000..d835636 --- /dev/null +++ b/llama-3.1-8b-finetomed.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec195e1df5b7d1797af875277fecc7a2e7cdf2279821e481b3ea257691ff6b9f +size 8540776512 diff --git a/llama-3.1-8b-finetomed.f16.gguf b/llama-3.1-8b-finetomed.f16.gguf new file mode 100644 index 0000000..fa85c62 --- /dev/null +++ b/llama-3.1-8b-finetomed.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f940e2185d7ea2b70bd6a3f31f931da6302c226253164c9a560d381c06dd6d9e +size 16068896832