commit d79655b843ae54c3ce646ce2c72ac1336f0f1b74 Author: ModelHub XC Date: Thu Jun 11 08:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Wolof-Llama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dd3b2fc --- /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 +Wolof-Llama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-Llama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wolof-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..b2448f2 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: vonewman/Wolof-Llama-3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/vonewman/Wolof-Llama-3.1-8B + + +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/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-Llama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Wolof-Llama-3.1-8B-GGUF/resolve/main/Wolof-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/Wolof-Llama-3.1-8B.IQ4_XS.gguf b/Wolof-Llama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..f9ffaed --- /dev/null +++ b/Wolof-Llama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42239078de6820ae7309cd6f9064de5e7d19d891564060b99e7600650d344a15 +size 4484364544 diff --git a/Wolof-Llama-3.1-8B.Q2_K.gguf b/Wolof-Llama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..d889ec0 --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9defb538d73023bdf8cf7c5b9aae0976bc507c62bc371b956f192220302d5ff9 +size 3179133184 diff --git a/Wolof-Llama-3.1-8B.Q3_K_L.gguf b/Wolof-Llama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..88f7924 --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7434296ed16571045a87e1c0c9b23a5682e6cb452c597c9fb873b5a354f7906f +size 4321958144 diff --git a/Wolof-Llama-3.1-8B.Q3_K_M.gguf b/Wolof-Llama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..4b7f357 --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b6f6f0abafc6c0d2b5bab4dfaff80c7478d4a0b14553e52e437b3da1822b41 +size 4018919680 diff --git a/Wolof-Llama-3.1-8B.Q3_K_S.gguf b/Wolof-Llama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..1725ecc --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83588652824db7980b1f852209ca0be2bcac41fa94ea6ed4bbed25c592f5be35 +size 3664500992 diff --git a/Wolof-Llama-3.1-8B.Q4_K_M.gguf b/Wolof-Llama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..2b45adf --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f3cb61920bea1a8bbbefeea17eb654360cd859000b4271e4cfeae07fecd605d +size 4920736000 diff --git a/Wolof-Llama-3.1-8B.Q4_K_S.gguf b/Wolof-Llama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..1e38449 --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11bc9ca4ede944e756e77236a82013be73ae12f18fcd0a21d1b7319a11c871b1 +size 4692670720 diff --git a/Wolof-Llama-3.1-8B.Q5_K_M.gguf b/Wolof-Llama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..187965c --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4998b7dd8b939e5e8d13afe06b1c48b29fd73f8f6c5fea29355190d4eebc38c +size 5732989184 diff --git a/Wolof-Llama-3.1-8B.Q5_K_S.gguf b/Wolof-Llama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..ec9440a --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8346eab93fe940b73ab1d19a8028f4827d763b12cdb68e64129fe0d6f4df81f +size 5599295744 diff --git a/Wolof-Llama-3.1-8B.Q6_K.gguf b/Wolof-Llama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..f954130 --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c95c62d445317f589104033425b96cd45f86c7dc343a6e952e559309e42d71 +size 6596008192 diff --git a/Wolof-Llama-3.1-8B.Q8_0.gguf b/Wolof-Llama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..2a76b67 --- /dev/null +++ b/Wolof-Llama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2787bfc42befa7ecd4b174d3383997740fe3cac64d2ab76e8494ba67d2dbb42f +size 8540772608 diff --git a/Wolof-Llama-3.1-8B.f16.gguf b/Wolof-Llama-3.1-8B.f16.gguf new file mode 100644 index 0000000..2ef2f8e --- /dev/null +++ b/Wolof-Llama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5729a630570f0cf875cf42d2d09dfcbfa5384e3cacd1b2fdbb8e9616160d651 +size 16068892928