commit e8f1fd02bc2e77fb01247f99d5bab21c7f3aaf92 Author: ModelHub XC Date: Sat Aug 8 13:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-1B-bg-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ae20888 --- /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 +Llama3.2-1B-bg.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-bg.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-1B-bg.IQ4_XS.gguf b/Llama3.2-1B-bg.IQ4_XS.gguf new file mode 100644 index 0000000..ab8dd40 --- /dev/null +++ b/Llama3.2-1B-bg.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:625607e93901ea15e9afbd9f0bb8e43c4206d7c2ee4c8ee722a80a2bc775cabc +size 748382464 diff --git a/Llama3.2-1B-bg.Q2_K.gguf b/Llama3.2-1B-bg.Q2_K.gguf new file mode 100644 index 0000000..53a2bc9 --- /dev/null +++ b/Llama3.2-1B-bg.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffd7336e4d0f1f50c146832a9e7c1ce91cd6c71a71fadb0c51a98dd40f15b15 +size 580872448 diff --git a/Llama3.2-1B-bg.Q3_K_L.gguf b/Llama3.2-1B-bg.Q3_K_L.gguf new file mode 100644 index 0000000..57e48c2 --- /dev/null +++ b/Llama3.2-1B-bg.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b2e78fc8b45ba43d65c6ff277abadefa9d12d12e365a202fb9a580966227d3 +size 732522752 diff --git a/Llama3.2-1B-bg.Q3_K_M.gguf b/Llama3.2-1B-bg.Q3_K_M.gguf new file mode 100644 index 0000000..5d67794 --- /dev/null +++ b/Llama3.2-1B-bg.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7ba0140919873508fb8dfa951de724234c328071be1cf4db96203f6b5b1fd6f +size 690841856 diff --git a/Llama3.2-1B-bg.Q3_K_S.gguf b/Llama3.2-1B-bg.Q3_K_S.gguf new file mode 100644 index 0000000..5997ed9 --- /dev/null +++ b/Llama3.2-1B-bg.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c780c4c0e473870d2426d9c6cfb25172a3388efdfb01a3e5bdb720d92a8b90d1 +size 641689856 diff --git a/Llama3.2-1B-bg.Q4_K_M.gguf b/Llama3.2-1B-bg.Q4_K_M.gguf new file mode 100644 index 0000000..f5a3b96 --- /dev/null +++ b/Llama3.2-1B-bg.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576ee29d0f6643be82c6c146e786df435ac61ca0ef647e92df53c9909553f2a1 +size 807692544 diff --git a/Llama3.2-1B-bg.Q4_K_S.gguf b/Llama3.2-1B-bg.Q4_K_S.gguf new file mode 100644 index 0000000..e29193a --- /dev/null +++ b/Llama3.2-1B-bg.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a279c5aee0331f83bd819b878106c6889795a05ae3da242a311220786d8a62c7 +size 775645440 diff --git a/Llama3.2-1B-bg.Q5_K_M.gguf b/Llama3.2-1B-bg.Q5_K_M.gguf new file mode 100644 index 0000000..bb1d856 --- /dev/null +++ b/Llama3.2-1B-bg.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b428942f7265cda4f2f91cba1668b60b6273068aaff0f9f876cb534dccb0e35 +size 911501568 diff --git a/Llama3.2-1B-bg.Q5_K_S.gguf b/Llama3.2-1B-bg.Q5_K_S.gguf new file mode 100644 index 0000000..2f7e50c --- /dev/null +++ b/Llama3.2-1B-bg.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e3032cad7a4981e03737c895fff0ecb54f2d1037eadbcbbeea4070d3f743ee +size 892561664 diff --git a/Llama3.2-1B-bg.Q6_K.gguf b/Llama3.2-1B-bg.Q6_K.gguf new file mode 100644 index 0000000..49e2d26 --- /dev/null +++ b/Llama3.2-1B-bg.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380371315a9314bfe49c2dd58cf7c8da8032e52518b99174e461fc6ccba29e33 +size 1021798656 diff --git a/Llama3.2-1B-bg.Q8_0.gguf b/Llama3.2-1B-bg.Q8_0.gguf new file mode 100644 index 0000000..49c70a7 --- /dev/null +++ b/Llama3.2-1B-bg.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41ef1f3dc258cc468499c64e7db6faf9baba090dc1d38c7c4dba740b648552d +size 1321081088 diff --git a/Llama3.2-1B-bg.f16.gguf b/Llama3.2-1B-bg.f16.gguf new file mode 100644 index 0000000..158f807 --- /dev/null +++ b/Llama3.2-1B-bg.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f80f7b341d8196773b24ee6f9563d2e54ba4767c8fc7652312e1b0fffd36e7c +size 2479593728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d0a485d --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: petkopetkov/Llama3.2-1B-bg +datasets: +- petkopetkov/math_qa-bg +- petkopetkov/gsm8k-bg +- petkopetkov/winogrande_xl-bg +- petkopetkov/hellaswag-bg +- petkopetkov/mmlu-bg +- petkopetkov/arc-easy-bg +- petkopetkov/arc-challenge-bg +language: +- en +- bg +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/petkopetkov/Llama3.2-1B-bg + + +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/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-bg-GGUF/resolve/main/Llama3.2-1B-bg.f16.gguf) | f16 | 2.6 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +