commit fc49909147956cb76610d108fd5e937473ae9c85 Author: ModelHub XC Date: Fri Jul 31 10:53:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-UA-GEC-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..51f7cbe --- /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-UA-GEC.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UA-GEC.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-UA-GEC.IQ4_XS.gguf b/Llama-3.1-8B-UA-GEC.IQ4_XS.gguf new file mode 100644 index 0000000..0f918d2 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895454576b21f55a21b01caf8b30ff8b811be5fe1aa1ab03146415fda1e1eb44 +size 4484368448 diff --git a/Llama-3.1-8B-UA-GEC.Q2_K.gguf b/Llama-3.1-8B-UA-GEC.Q2_K.gguf new file mode 100644 index 0000000..8827ff3 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579c2c6152c7b885d1ff97f1f32ba1fa55d71faddeaf1a0af0a26e22d7c27fa9 +size 3179137088 diff --git a/Llama-3.1-8B-UA-GEC.Q3_K_L.gguf b/Llama-3.1-8B-UA-GEC.Q3_K_L.gguf new file mode 100644 index 0000000..ab69cf6 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf516194fde084139e8157b16065545baa510723011144a41cb0cce6e318138 +size 4321962048 diff --git a/Llama-3.1-8B-UA-GEC.Q3_K_M.gguf b/Llama-3.1-8B-UA-GEC.Q3_K_M.gguf new file mode 100644 index 0000000..49d0771 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74015043b40602dbf7bc58e3725e231068e0369b4498bae779ae8caf219cba0 +size 4018923584 diff --git a/Llama-3.1-8B-UA-GEC.Q3_K_S.gguf b/Llama-3.1-8B-UA-GEC.Q3_K_S.gguf new file mode 100644 index 0000000..6a96881 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cba1ac8b359c85942f2b667a4e7e4fb41dea7695e42a17aa38ed289433a7c7b +size 3664504896 diff --git a/Llama-3.1-8B-UA-GEC.Q4_K_M.gguf b/Llama-3.1-8B-UA-GEC.Q4_K_M.gguf new file mode 100644 index 0000000..377379b --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ebf9ec887d456737b4cfa7a5e465540cf17d93d8959cc9d23e3dec2a8c096d4 +size 4920739904 diff --git a/Llama-3.1-8B-UA-GEC.Q4_K_S.gguf b/Llama-3.1-8B-UA-GEC.Q4_K_S.gguf new file mode 100644 index 0000000..1be2cf1 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27a2eb3571e4a032496a1be4229edcc0e6cff84b97387e62bac47ca678437bcd +size 4692674624 diff --git a/Llama-3.1-8B-UA-GEC.Q5_K_M.gguf b/Llama-3.1-8B-UA-GEC.Q5_K_M.gguf new file mode 100644 index 0000000..46ddb49 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f60094b3ddb74f46a013e07773efac9af9eaf19d9c5c13bd563b3b0e53050a +size 5732993088 diff --git a/Llama-3.1-8B-UA-GEC.Q5_K_S.gguf b/Llama-3.1-8B-UA-GEC.Q5_K_S.gguf new file mode 100644 index 0000000..0d96e17 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff7383f4cf9682ab7aa0aef1762460b693e66142eb63425f685a5bfc5df2ba39 +size 5599299648 diff --git a/Llama-3.1-8B-UA-GEC.Q6_K.gguf b/Llama-3.1-8B-UA-GEC.Q6_K.gguf new file mode 100644 index 0000000..0dcf3ba --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380ef7aded59c242a96e512dbdbbad342bfaff2e0bf2ae8e010f5d82ce29eb89 +size 6596012096 diff --git a/Llama-3.1-8B-UA-GEC.Q8_0.gguf b/Llama-3.1-8B-UA-GEC.Q8_0.gguf new file mode 100644 index 0000000..1c84f66 --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e81b8a779624a26d8ac2e65d7c566b73db7d7a526a1845ce8785687f33ea36c9 +size 8540776512 diff --git a/Llama-3.1-8B-UA-GEC.f16.gguf b/Llama-3.1-8B-UA-GEC.f16.gguf new file mode 100644 index 0000000..776865f --- /dev/null +++ b/Llama-3.1-8B-UA-GEC.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92801b897ac231dfb3550b332843f731d5ebe53b215c18b74bb0e1da00e78e9 +size 16068896832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..54d9c18 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: thedanmaks/Llama-3.1-8B-UA-GEC +language: +- en +- uk +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- grpo +- grammar-correction +--- +## About + + + + + + +static quants of https://huggingface.co/thedanmaks/Llama-3.1-8B-UA-GEC + + +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-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UA-GEC-GGUF/resolve/main/Llama-3.1-8B-UA-GEC.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. + +