commit e494f25d4491216a0bb165f122bbfa472761da5d Author: ModelHub XC Date: Wed Sep 23 03:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-3-8B-hinglish-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..465d0da --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Meta-Llama-3-8B-hinglish.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.f16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-hinglish.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3-8B-hinglish.IQ3_M.gguf b/Meta-Llama-3-8B-hinglish.IQ3_M.gguf new file mode 100644 index 0000000..48b1702 --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511a02ddef39bc4fd64c670ed62c75a72894c776c78bfd885ebc09a84cb757fe +size 3784823136 diff --git a/Meta-Llama-3-8B-hinglish.IQ3_S.gguf b/Meta-Llama-3-8B-hinglish.IQ3_S.gguf new file mode 100644 index 0000000..888bdad --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d39ecfc9ccedaffaceb13db2a2394d765768418b33be129092f6a8a3936b6f +size 3682324832 diff --git a/Meta-Llama-3-8B-hinglish.IQ3_XS.gguf b/Meta-Llama-3-8B-hinglish.IQ3_XS.gguf new file mode 100644 index 0000000..afaa7c7 --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cb6bede87b1a2767550402650ba861734f12f3388048552e6fc42c292d88d13 +size 3518746976 diff --git a/Meta-Llama-3-8B-hinglish.IQ4_XS.gguf b/Meta-Llama-3-8B-hinglish.IQ4_XS.gguf new file mode 100644 index 0000000..89c1601 --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019a5733aff70e35fde34c324a058fef173d0106c8804efc7d7fdaed7a44f711 +size 4484362592 diff --git a/Meta-Llama-3-8B-hinglish.Q2_K.gguf b/Meta-Llama-3-8B-hinglish.Q2_K.gguf new file mode 100644 index 0000000..b5c3d5f --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9b99b26e9bf98b21b2f740949e2fdc5cc4dba2ec7749708de47b8eb3c5a6dea +size 3179131232 diff --git a/Meta-Llama-3-8B-hinglish.Q3_K_L.gguf b/Meta-Llama-3-8B-hinglish.Q3_K_L.gguf new file mode 100644 index 0000000..edf4d00 --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d10bf41b7cf74365b1c2d6f6ba6909a4b88e532dd425c552d0f0112bd8bea0 +size 4321956192 diff --git a/Meta-Llama-3-8B-hinglish.Q3_K_M.gguf b/Meta-Llama-3-8B-hinglish.Q3_K_M.gguf new file mode 100644 index 0000000..a54a1fb --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9051f6a193f53b483aaf59a7a9208811244edf87aa3b5fe1cdcd5e743a99fed +size 4018917728 diff --git a/Meta-Llama-3-8B-hinglish.Q3_K_S.gguf b/Meta-Llama-3-8B-hinglish.Q3_K_S.gguf new file mode 100644 index 0000000..504d6fa --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a18eb970efd0c8cc5a8db7b21274e294fc6f1fb7efc03d936b2c481dd7c055 +size 3664499040 diff --git a/Meta-Llama-3-8B-hinglish.Q4_K_M.gguf b/Meta-Llama-3-8B-hinglish.Q4_K_M.gguf new file mode 100644 index 0000000..0b6f5cd --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2ddee764eba6f8005a3ffe40890b8bb896974f2bcf6539a79a14eade66b891 +size 4920734048 diff --git a/Meta-Llama-3-8B-hinglish.Q4_K_S.gguf b/Meta-Llama-3-8B-hinglish.Q4_K_S.gguf new file mode 100644 index 0000000..53b4792 --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98f4a07b6d6159c4a92c87c081831a033f67ed4d9223ab4f337a5b5031c7392c +size 4692668768 diff --git a/Meta-Llama-3-8B-hinglish.Q5_K_M.gguf b/Meta-Llama-3-8B-hinglish.Q5_K_M.gguf new file mode 100644 index 0000000..64959ff --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d87b97f58bce910dcebeda6d97a1395453efe26fd57545a7949feaa428cd39 +size 5732987232 diff --git a/Meta-Llama-3-8B-hinglish.Q5_K_S.gguf b/Meta-Llama-3-8B-hinglish.Q5_K_S.gguf new file mode 100644 index 0000000..69161fd --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513def078f16a5d42ce9de229ad256fc151fbdbd2c804344f70b261067f5dda6 +size 5599293792 diff --git a/Meta-Llama-3-8B-hinglish.Q6_K.gguf b/Meta-Llama-3-8B-hinglish.Q6_K.gguf new file mode 100644 index 0000000..0b8dec2 --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3ec865bc400fb210f4e9f0deb77a86f9bfb0dc580ce9d3ec4d399852795d4d9 +size 6596006240 diff --git a/Meta-Llama-3-8B-hinglish.Q8_0.gguf b/Meta-Llama-3-8B-hinglish.Q8_0.gguf new file mode 100644 index 0000000..344d3c8 --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae93f007b360031d3645a022a19df7186cd931278edb0ce3b395745c1a420e34 +size 8540770656 diff --git a/Meta-Llama-3-8B-hinglish.f16.gguf b/Meta-Llama-3-8B-hinglish.f16.gguf new file mode 100644 index 0000000..cafb911 --- /dev/null +++ b/Meta-Llama-3-8B-hinglish.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe2edcaea7071f7f39ac046039ee38d664f2563026ef0084658b7a009390feef +size 16068890976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eee02a5 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: impuneetg/Meta-Llama-3-8B-hinglish +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/impuneetg/Meta-Llama-3-8B-hinglish + + +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/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.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. + +