commit 2db026bb688957b45285e449f71b632cb52dcce5 Author: ModelHub XC Date: Tue Jun 2 10:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BMW-Llama-3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4e5d90d --- /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 +BMW-Llama-3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BMW-Llama-3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BMW-Llama-3.2-1B.IQ4_XS.gguf b/BMW-Llama-3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..1821745 --- /dev/null +++ b/BMW-Llama-3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3cddde766a94c045a53f20a7d5b54f91ac06622f4b007d930f23a958b5679d3 +size 748385088 diff --git a/BMW-Llama-3.2-1B.Q2_K.gguf b/BMW-Llama-3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..4a82824 --- /dev/null +++ b/BMW-Llama-3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c55857637b302e4006dca681167968dca7e4ed85ca0bb5827360e47722ad2ba +size 580875072 diff --git a/BMW-Llama-3.2-1B.Q3_K_L.gguf b/BMW-Llama-3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..decb4e6 --- /dev/null +++ b/BMW-Llama-3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa5e0a2979632facd404b58136bdf9f1249b00d7e6daf5a6a12ac0669e0a648 +size 732525376 diff --git a/BMW-Llama-3.2-1B.Q3_K_M.gguf b/BMW-Llama-3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..d8036f3 --- /dev/null +++ b/BMW-Llama-3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601289738a51fc84d0479a7e7aef970c9138da2ffc1f4170a36101438bedcb51 +size 690844480 diff --git a/BMW-Llama-3.2-1B.Q3_K_S.gguf b/BMW-Llama-3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..92702bb --- /dev/null +++ b/BMW-Llama-3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:746dec8dff62fa59f620069f71a74b2790101bc36d13fccf64613bb97093c1cc +size 641692480 diff --git a/BMW-Llama-3.2-1B.Q4_K_M.gguf b/BMW-Llama-3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..c43d21e --- /dev/null +++ b/BMW-Llama-3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54cd254322ab48984269d001c56bdb6daefb2b28903f365b0a30b90549254537 +size 807695168 diff --git a/BMW-Llama-3.2-1B.Q4_K_S.gguf b/BMW-Llama-3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..fc9a61b --- /dev/null +++ b/BMW-Llama-3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7e34bad4bea246d935cfa3eeda3f2c2b072208adee746a96e92c2057b2bb0d5 +size 775648064 diff --git a/BMW-Llama-3.2-1B.Q5_K_M.gguf b/BMW-Llama-3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..15c0ca5 --- /dev/null +++ b/BMW-Llama-3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f186ca9b5865fd1a34492b535a80c749346f574bf70022d84f019430afe09993 +size 911504192 diff --git a/BMW-Llama-3.2-1B.Q5_K_S.gguf b/BMW-Llama-3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..5d2655a --- /dev/null +++ b/BMW-Llama-3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b41c3f693947ca613ed3cc54c03d21a5a26323021ec3bb0f15806c39a3192a6d +size 892564288 diff --git a/BMW-Llama-3.2-1B.Q6_K.gguf b/BMW-Llama-3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..a31710b --- /dev/null +++ b/BMW-Llama-3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f3ebed7f694ab9e79cd334e8a04cb9b41a5b5c5dc77a793235e0a87e6e702e +size 1021801280 diff --git a/BMW-Llama-3.2-1B.Q8_0.gguf b/BMW-Llama-3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..d617742 --- /dev/null +++ b/BMW-Llama-3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c643aff6931e7866c3cfd450f8ee824d7b903100573894a339e537fcfc5f3960 +size 1321083712 diff --git a/BMW-Llama-3.2-1B.f16.gguf b/BMW-Llama-3.2-1B.f16.gguf new file mode 100644 index 0000000..42988b5 --- /dev/null +++ b/BMW-Llama-3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5202e0359ca75c3aa6937e013942e082c0babf4a804f40752e92b2a3d11f75a +size 2479596352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..86dd496 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Alwin-Yang/BMW-Llama-3.2-1B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Alwin-Yang/BMW-Llama-3.2-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BMW-Llama-3.2-1B-GGUF).*** + +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/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BMW-Llama-3.2-1B-GGUF/resolve/main/BMW-Llama-3.2-1B.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. + +