commit 74b7c7e55c566854c01565815035d8d685a0c8bc Author: ModelHub XC Date: Fri Jun 12 17:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/bagel-8b-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f6cb61c --- /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 +bagel-8b-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +bagel-8b-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..36119e0 --- /dev/null +++ b/README.md @@ -0,0 +1,113 @@ +--- +base_model: jondurbin/bagel-8b-v1.0 +datasets: +- ai2_arc +- allenai/ultrafeedback_binarized_cleaned +- argilla/distilabel-intel-orca-dpo-pairs +- jondurbin/airoboros-3.2 +- codeparrot/apps +- facebook/belebele +- bluemoon-fandom-1-1-rp-cleaned +- boolq +- camel-ai/biology +- camel-ai/chemistry +- camel-ai/math +- camel-ai/physics +- jondurbin/contextual-dpo-v0.1 +- jondurbin/gutenberg-dpo-v0.1 +- jondurbin/py-dpo-v0.1 +- jondurbin/truthy-dpo-v0.1 +- LDJnr/Capybara +- jondurbin/cinematika-v0.1 +- WizardLM/WizardLM_evol_instruct_70k +- glaiveai/glaive-function-calling-v2 +- jondurbin/gutenberg-dpo-v0.1 +- grimulkan/LimaRP-augmented +- lmsys/lmsys-chat-1m +- ParisNeo/lollms_aware_dataset +- TIGER-Lab/MathInstruct +- Muennighoff/natural-instructions +- openbookqa +- kingbri/PIPPA-shareGPT +- piqa +- Vezora/Tested-22k-Python-Alpaca +- ropes +- cakiki/rosetta-code +- Open-Orca/SlimOrca +- b-mc2/sql-create-context +- squad_v2 +- mattpscott/airoboros-summarization +- migtissera/Synthia-v1.3 +- unalignment/toxic-dpo-v0.2 +- WhiteRabbitNeo/WRN-Chapter-1 +- WhiteRabbitNeo/WRN-Chapter-2 +- winogrande +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE +license_name: llama3 +quantized_by: mradermacher +tags: +- llama-3 +- bagel +--- +## About + + + + + +static quants of https://huggingface.co/jondurbin/bagel-8b-v1.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF +## 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/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-GGUF/resolve/main/bagel-8b-v1.0.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. + + diff --git a/bagel-8b-v1.0.IQ3_M.gguf b/bagel-8b-v1.0.IQ3_M.gguf new file mode 100644 index 0000000..e3a6e1f --- /dev/null +++ b/bagel-8b-v1.0.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4a03cc945cad45dea84551b0b9b6efdb90f52f3b0063424d531d252c90f379 +size 3785336128 diff --git a/bagel-8b-v1.0.IQ3_S.gguf b/bagel-8b-v1.0.IQ3_S.gguf new file mode 100644 index 0000000..589b21d --- /dev/null +++ b/bagel-8b-v1.0.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d3cf34b540973289c109685842eacc750487622c815c638e4b9a8930a39993 +size 3682837824 diff --git a/bagel-8b-v1.0.IQ3_XS.gguf b/bagel-8b-v1.0.IQ3_XS.gguf new file mode 100644 index 0000000..2620362 --- /dev/null +++ b/bagel-8b-v1.0.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3499d00d28441bbb68bc8ca7f4e2c355aa8f1786d7951663c3e3b63358f08bd1 +size 3519259968 diff --git a/bagel-8b-v1.0.IQ4_XS.gguf b/bagel-8b-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..dd54c40 --- /dev/null +++ b/bagel-8b-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56412974ef379af8befaf54c233f55db0c8ea9f7a80bfa3ad68cba6b579a060 +size 4484875584 diff --git a/bagel-8b-v1.0.Q2_K.gguf b/bagel-8b-v1.0.Q2_K.gguf new file mode 100644 index 0000000..03fc347 --- /dev/null +++ b/bagel-8b-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:769a6572c83e5699468ee3a115526ee77d5652c9959df88c4f0d1e27e37251e1 +size 3179644224 diff --git a/bagel-8b-v1.0.Q3_K_L.gguf b/bagel-8b-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..94cf4ed --- /dev/null +++ b/bagel-8b-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ce2d8691468960e82ccb8fe019392751baa8c4ab9ff7b72556c704a609b237 +size 4322469184 diff --git a/bagel-8b-v1.0.Q3_K_M.gguf b/bagel-8b-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..1b391a6 --- /dev/null +++ b/bagel-8b-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39be1f51848d4c367029750f98ccff6beffd7eff01e6e8f1f73a0a02c9b3a805 +size 4019430720 diff --git a/bagel-8b-v1.0.Q3_K_S.gguf b/bagel-8b-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..e311344 --- /dev/null +++ b/bagel-8b-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b9a6b669632eb85264d6ead76117c41f56d4ebc8bed3b9e64982417976cff28 +size 3665012032 diff --git a/bagel-8b-v1.0.Q4_K_M.gguf b/bagel-8b-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..b145f2d --- /dev/null +++ b/bagel-8b-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a24700621f448e078cd741e2a6075cc356c2e23ac46feeaf6f9276d086214e2c +size 4921247040 diff --git a/bagel-8b-v1.0.Q4_K_S.gguf b/bagel-8b-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..4d4bbc5 --- /dev/null +++ b/bagel-8b-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4a612b5f5e324a8a8c960b231ee062fa140145f2b499351a7a9149c8b854aa +size 4693181760 diff --git a/bagel-8b-v1.0.Q5_K_M.gguf b/bagel-8b-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..3d9b9d6 --- /dev/null +++ b/bagel-8b-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ec2064085bbf9e5671d914cf0edacd30e0bdd1c8868e2d9924db56889e2e119 +size 5733500224 diff --git a/bagel-8b-v1.0.Q5_K_S.gguf b/bagel-8b-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..fcee014 --- /dev/null +++ b/bagel-8b-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2965c3afcf198378b1f0c48897e1ef1a3e7c2736c107a12e40ee993a62335b4 +size 5599806784 diff --git a/bagel-8b-v1.0.Q6_K.gguf b/bagel-8b-v1.0.Q6_K.gguf new file mode 100644 index 0000000..993ad15 --- /dev/null +++ b/bagel-8b-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f66af5af7ddf25e783a2ebeb8d232a6cfacfa47479f5fd67af4bbdd6fb828e07 +size 6596519232 diff --git a/bagel-8b-v1.0.Q8_0.gguf b/bagel-8b-v1.0.Q8_0.gguf new file mode 100644 index 0000000..5dbbc72 --- /dev/null +++ b/bagel-8b-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22974531af974308a0eecc04edae47b6d197834913c12406e5bff824d54c3b9 +size 8541283648 diff --git a/bagel-8b-v1.0.f16.gguf b/bagel-8b-v1.0.f16.gguf new file mode 100644 index 0000000..c162ce0 --- /dev/null +++ b/bagel-8b-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa424091bbeccba62544d5d35e476a0d9e89f7c55c835c0a1835d3d58d97450a +size 16069403968