commit 1f63adf7585abcf0931f44dab160961613caf4f4 Author: ModelHub XC Date: Thu Apr 23 00:33:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/bloom_ncbi_finetuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a4e5306 --- /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 +bloom_ncbi_finetuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +bloom_ncbi_finetuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..60c86c0 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: leslyarun/bloom_ncbi_finetuned +datasets: +- ncbi_disease +language: en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +--- +## About + + + + + + +static quants of https://huggingface.co/leslyarun/bloom_ncbi_finetuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#bloom_ncbi_finetuned-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/bloom_ncbi_finetuned-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/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.Q8_0.gguf) | Q8_0 | 1.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/bloom_ncbi_finetuned-GGUF/resolve/main/bloom_ncbi_finetuned.f16.gguf) | f16 | 2.2 | 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/bloom_ncbi_finetuned.IQ4_XS.gguf b/bloom_ncbi_finetuned.IQ4_XS.gguf new file mode 100644 index 0000000..42f3391 --- /dev/null +++ b/bloom_ncbi_finetuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bbfc34fcf0d2afb0fccff6f924943b275491ed3630efa1d820f683d982e83f4 +size 696068992 diff --git a/bloom_ncbi_finetuned.Q2_K.gguf b/bloom_ncbi_finetuned.Q2_K.gguf new file mode 100644 index 0000000..664803c --- /dev/null +++ b/bloom_ncbi_finetuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f6ad04dbcdd9a813d7e5aac00eaa0761f8b1e64239c655554b71cc2f2d41fe +size 582380416 diff --git a/bloom_ncbi_finetuned.Q3_K_L.gguf b/bloom_ncbi_finetuned.Q3_K_L.gguf new file mode 100644 index 0000000..92df630 --- /dev/null +++ b/bloom_ncbi_finetuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef029873859d9f086dd768310dd7c94f544b0175625624e2f0fb87a3ab06207 +size 718187392 diff --git a/bloom_ncbi_finetuned.Q3_K_M.gguf b/bloom_ncbi_finetuned.Q3_K_M.gguf new file mode 100644 index 0000000..afcafd2 --- /dev/null +++ b/bloom_ncbi_finetuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f20ec4a3bb26cbb2c804ee004ca840bae33b7b0038c70480d1927c77fa2e878c +size 683977600 diff --git a/bloom_ncbi_finetuned.Q3_K_S.gguf b/bloom_ncbi_finetuned.Q3_K_S.gguf new file mode 100644 index 0000000..32509e6 --- /dev/null +++ b/bloom_ncbi_finetuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6dd0441cce9dbc1dcf1cbadf2cab12d64aed46bcb9f4f618e8ddb805a85e26b +size 622635904 diff --git a/bloom_ncbi_finetuned.Q4_K_M.gguf b/bloom_ncbi_finetuned.Q4_K_M.gguf new file mode 100644 index 0000000..9db8434 --- /dev/null +++ b/bloom_ncbi_finetuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce5a5ac49c079a5b0e8acb75d51a428925661310aebc7b1eee55b7910e4b51ff +size 763308928 diff --git a/bloom_ncbi_finetuned.Q4_K_S.gguf b/bloom_ncbi_finetuned.Q4_K_S.gguf new file mode 100644 index 0000000..4b8b67b --- /dev/null +++ b/bloom_ncbi_finetuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94192e65b7fd18ae2b3e174a99ef07e033102e0dd6918c9f52ac519901f3a563 +size 716417920 diff --git a/bloom_ncbi_finetuned.Q5_K_M.gguf b/bloom_ncbi_finetuned.Q5_K_M.gguf new file mode 100644 index 0000000..5d282ad --- /dev/null +++ b/bloom_ncbi_finetuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74b69ede2b8f502e63afeb91b470ae7d3c9e0bd3d3aef82d2aba19b6cb1519c7 +size 835414912 diff --git a/bloom_ncbi_finetuned.Q5_K_S.gguf b/bloom_ncbi_finetuned.Q5_K_S.gguf new file mode 100644 index 0000000..bb46cd0 --- /dev/null +++ b/bloom_ncbi_finetuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6038b172bb736a3a3b4facfcdc06155f4647bbe6eeb13b6ef170ee8731fafaa0 +size 797813632 diff --git a/bloom_ncbi_finetuned.Q6_K.gguf b/bloom_ncbi_finetuned.Q6_K.gguf new file mode 100644 index 0000000..6079bab --- /dev/null +++ b/bloom_ncbi_finetuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a59479e8dbc1f8d9ba89e8b2dcd05f709041da2ab60b44db31c63f98a26c36 +size 888056704 diff --git a/bloom_ncbi_finetuned.Q8_0.gguf b/bloom_ncbi_finetuned.Q8_0.gguf new file mode 100644 index 0000000..54a8700 --- /dev/null +++ b/bloom_ncbi_finetuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d54e17aa8870a8fec819f7c877216d8d974be85b04cdfd0a76c8b50b019acf1 +size 1145944960 diff --git a/bloom_ncbi_finetuned.f16.gguf b/bloom_ncbi_finetuned.f16.gguf new file mode 100644 index 0000000..fdf280a --- /dev/null +++ b/bloom_ncbi_finetuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b708e7ce309635d3ba79a72e9b5b4c7d1907e1783f6878853e3c97c32b74ad +size 2144222080