commit 386a61f81c1d9a4ef2614455dd95cff62b859860 Author: ModelHub XC Date: Sun Aug 9 06:03:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8b-Tamil-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f9cb844 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-Tamil.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Tamil.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8b-Tamil.IQ3_M.gguf b/Llama-3.1-8b-Tamil.IQ3_M.gguf new file mode 100644 index 0000000..d60dc48 --- /dev/null +++ b/Llama-3.1-8b-Tamil.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e7ddc12605836fe0102b73e16516edc66606d54c87bf0fc8392d579c7505d61 +size 3784824128 diff --git a/Llama-3.1-8b-Tamil.IQ3_S.gguf b/Llama-3.1-8b-Tamil.IQ3_S.gguf new file mode 100644 index 0000000..1cad7d4 --- /dev/null +++ b/Llama-3.1-8b-Tamil.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b95b9f1799de1b031e44e41270ca7cdef0f877efe2a79bf541235da3f4626bed +size 3682325824 diff --git a/Llama-3.1-8b-Tamil.IQ3_XS.gguf b/Llama-3.1-8b-Tamil.IQ3_XS.gguf new file mode 100644 index 0000000..70778f5 --- /dev/null +++ b/Llama-3.1-8b-Tamil.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d987ec5b9e48e440372ee35014a2a2b66e83a2b923f68ae02228c0e712723d7 +size 3518747968 diff --git a/Llama-3.1-8b-Tamil.IQ4_XS.gguf b/Llama-3.1-8b-Tamil.IQ4_XS.gguf new file mode 100644 index 0000000..6da01a5 --- /dev/null +++ b/Llama-3.1-8b-Tamil.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:338364e26da67d082cda9d9645567c512b89fcfe0509554b4d99735ea5006b4a +size 4484363584 diff --git a/Llama-3.1-8b-Tamil.Q2_K.gguf b/Llama-3.1-8b-Tamil.Q2_K.gguf new file mode 100644 index 0000000..78436f3 --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fea2d6aca343f47f439c3447cba06e371800f510a9a1b9e0f74179e41a953638 +size 3179132224 diff --git a/Llama-3.1-8b-Tamil.Q3_K_L.gguf b/Llama-3.1-8b-Tamil.Q3_K_L.gguf new file mode 100644 index 0000000..9d3211f --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3ec8d1fd151e0c9f917dd896783e62a30a349f88b9f824e37172776cc52163 +size 4321957184 diff --git a/Llama-3.1-8b-Tamil.Q3_K_M.gguf b/Llama-3.1-8b-Tamil.Q3_K_M.gguf new file mode 100644 index 0000000..2dc2e40 --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:754f46065c1666053ad3e93c20973d4d1d6f4a299b0d8ff32e68123a6bca921b +size 4018918720 diff --git a/Llama-3.1-8b-Tamil.Q3_K_S.gguf b/Llama-3.1-8b-Tamil.Q3_K_S.gguf new file mode 100644 index 0000000..dd6649a --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f54e1cf08482a02d697eecd0736207440a688d9e291e0ee0b30e63c8406bc241 +size 3664500032 diff --git a/Llama-3.1-8b-Tamil.Q4_K_M.gguf b/Llama-3.1-8b-Tamil.Q4_K_M.gguf new file mode 100644 index 0000000..941c8a9 --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3972604029828f921df6da789e64776e8ea6c122b48335c05b47c3eee1d061b +size 4920735040 diff --git a/Llama-3.1-8b-Tamil.Q4_K_S.gguf b/Llama-3.1-8b-Tamil.Q4_K_S.gguf new file mode 100644 index 0000000..6d05b1f --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe27135730f5577fe9b0bbf3605de6e69504016f6c72b77ae150cb8be732646 +size 4692669760 diff --git a/Llama-3.1-8b-Tamil.Q5_K_M.gguf b/Llama-3.1-8b-Tamil.Q5_K_M.gguf new file mode 100644 index 0000000..d6fe896 --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ccd61bd0e3b748b8eeb5431608fcb74fb0b3d60c0a0e6ebe48f51363cddf16 +size 5732988224 diff --git a/Llama-3.1-8b-Tamil.Q5_K_S.gguf b/Llama-3.1-8b-Tamil.Q5_K_S.gguf new file mode 100644 index 0000000..581329d --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af8a95fa67679c7f2f5fffc6f1d90d1a83e9752800df5da0019e2cde11dd104 +size 5599294784 diff --git a/Llama-3.1-8b-Tamil.Q6_K.gguf b/Llama-3.1-8b-Tamil.Q6_K.gguf new file mode 100644 index 0000000..4715aa1 --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c712608f2b9ae76996e219d292eb61c9874c145d275a5b379de38fba03463f +size 6596007232 diff --git a/Llama-3.1-8b-Tamil.Q8_0.gguf b/Llama-3.1-8b-Tamil.Q8_0.gguf new file mode 100644 index 0000000..4025dbe --- /dev/null +++ b/Llama-3.1-8b-Tamil.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cff5984b58226c9098a177379a6bf81c5128095e8d8d246b163255debdcd0e +size 8540771648 diff --git a/Llama-3.1-8b-Tamil.f16.gguf b/Llama-3.1-8b-Tamil.f16.gguf new file mode 100644 index 0000000..241baf1 --- /dev/null +++ b/Llama-3.1-8b-Tamil.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89bac1b97a9adcdbc8cc3885da3dfb34d529151a69945a3dd7def3bf965e2822 +size 16068891968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..573b6d0 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: berger123/Llama-3.1-8b-Tamil +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/berger123/Llama-3.1-8b-Tamil + + +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-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Tamil-GGUF/resolve/main/Llama-3.1-8b-Tamil.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. + +