commit 543003a5549fe406ad57bd8c9eacb27af00320a2 Author: ModelHub XC Date: Tue Sep 29 19:39:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/bgGPT-llama-3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..17e2a11 --- /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 +bgGPT-llama-3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +bgGPT-llama-3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..032b999 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: burgasdotpro/bgGPT-llama-3.2-3B +datasets: +- burgasdotpro/synthetic_dataset +language: +- bg +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- sebaxakerhtc +- bggpt +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/burgasdotpro/bgGPT-llama-3.2-3B + + +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/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/bgGPT-llama-3.2-3B-GGUF/resolve/main/bgGPT-llama-3.2-3B.f16.gguf) | f16 | 6.5 | 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/bgGPT-llama-3.2-3B.IQ4_XS.gguf b/bgGPT-llama-3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..bbef2e7 --- /dev/null +++ b/bgGPT-llama-3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93ffddc17538cc97d9e237aed2d925957aeaa90d89974f3af2e437a5e1a532bc +size 1840904672 diff --git a/bgGPT-llama-3.2-3B.Q2_K.gguf b/bgGPT-llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..4b3e8d8 --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a93c2561fb9195b6e4905a742b7b9b6c6b97d86ccff79cef790ffa2bb3c348 +size 1363933664 diff --git a/bgGPT-llama-3.2-3B.Q3_K_L.gguf b/bgGPT-llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..d934fe1 --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c84523621c4a86a5ce64e2a68de1b8eeda3aadf0f674a2db36b57d41bf5b3b75 +size 1815345632 diff --git a/bgGPT-llama-3.2-3B.Q3_K_M.gguf b/bgGPT-llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..5fb1a9a --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0dc4421317786ad32a944a49649543c52ac2ff8e915c5328f2659169f1a2711 +size 1687157216 diff --git a/bgGPT-llama-3.2-3B.Q3_K_S.gguf b/bgGPT-llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..eaa816d --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c975431bc8448fd2098b3662e3cba5b6398333489932d23c0a2b64739e0a6374 +size 1542846944 diff --git a/bgGPT-llama-3.2-3B.Q4_K_M.gguf b/bgGPT-llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..354dec1 --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3bdc7a294f0a2acbd1398f72edf10a053fac16a4ba63e300ed20f924e0ba50f +size 2019375584 diff --git a/bgGPT-llama-3.2-3B.Q4_K_S.gguf b/bgGPT-llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..b212cc9 --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a3067ceb0e923dfc4e4c2396f8ef2939857e5ff6f521a726b70b411a210df9 +size 1928198624 diff --git a/bgGPT-llama-3.2-3B.Q5_K_M.gguf b/bgGPT-llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..79d1303 --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23383483f184021e45b77b08eea936ac2030e1fe46061378c9c2c6ce5a4e383 +size 2322151904 diff --git a/bgGPT-llama-3.2-3B.Q5_K_S.gguf b/bgGPT-llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..73de649 --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6028997462e9a7e8d0291de30d6eef515b402791fceb05c93e17a425bb49a57c +size 2269510112 diff --git a/bgGPT-llama-3.2-3B.Q6_K.gguf b/bgGPT-llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..80fb2a0 --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b64dddfe570f6ce2bedfdbbaf050277b23a33847e94b8ec0f62a03f10d26ad9 +size 2643851744 diff --git a/bgGPT-llama-3.2-3B.Q8_0.gguf b/bgGPT-llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..3b306e8 --- /dev/null +++ b/bgGPT-llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f8386a57f3d739cc74b882b56274c973796f111f8e6dbfc0c5f73f7c47f1ba +size 3421897184 diff --git a/bgGPT-llama-3.2-3B.f16.gguf b/bgGPT-llama-3.2-3B.f16.gguf new file mode 100644 index 0000000..d3aa342 --- /dev/null +++ b/bgGPT-llama-3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:041b7b2ac1a1ecbc77f7ddba23a2713ed80789f5f6a2bf923672705e6f61b58d +size 6433685984