commit a821dc2491861e7ab8b518720f5159b2d10433cc Author: ModelHub XC Date: Sat Aug 15 19:03:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-8b-pubmed-10k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6e3d803 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +llama3.1-8b-pubmed-10k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-pubmed-10k.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae9cccb --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: anumafzal94/llama3.1-8b-pubmed-10k +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/anumafzal94/llama3.1-8b-pubmed-10k + + +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/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-pubmed-10k-GGUF/resolve/main/llama3.1-8b-pubmed-10k.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/llama3.1-8b-pubmed-10k.IQ4_XS.gguf b/llama3.1-8b-pubmed-10k.IQ4_XS.gguf new file mode 100644 index 0000000..892fb44 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aaa4c086ad457815ab47f219dd8fa546397d9c2c1d22aef61caad21a067b8f8 +size 4484362752 diff --git a/llama3.1-8b-pubmed-10k.Q2_K.gguf b/llama3.1-8b-pubmed-10k.Q2_K.gguf new file mode 100644 index 0000000..e3785c2 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501992059f983f8ee4b24fa67ee1257b874694c3322b203dbdce417e2b26e1b5 +size 3179131392 diff --git a/llama3.1-8b-pubmed-10k.Q3_K_L.gguf b/llama3.1-8b-pubmed-10k.Q3_K_L.gguf new file mode 100644 index 0000000..6cb3359 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c598e2a9f268febd18722c13c1585d7042dc155c09b086e47e93fcc0d5d23c2f +size 4321956352 diff --git a/llama3.1-8b-pubmed-10k.Q3_K_M.gguf b/llama3.1-8b-pubmed-10k.Q3_K_M.gguf new file mode 100644 index 0000000..b1b296d --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02a11fe2593fe9e9a4587ad4ddf597cf25113f810db501e196db278f86a0f349 +size 4018917888 diff --git a/llama3.1-8b-pubmed-10k.Q3_K_S.gguf b/llama3.1-8b-pubmed-10k.Q3_K_S.gguf new file mode 100644 index 0000000..770ec2a --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9499fcd0de98e13669e8722bff6c90cb190cc6c5d95080bd9fa12a6a60d485fa +size 3664499200 diff --git a/llama3.1-8b-pubmed-10k.Q4_0_4_4.gguf b/llama3.1-8b-pubmed-10k.Q4_0_4_4.gguf new file mode 100644 index 0000000..c903011 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1301888e6c8c88ca444e54b8271db5fd2c398d31c7993b1a6dd661d220da85f +size 4661211648 diff --git a/llama3.1-8b-pubmed-10k.Q4_K_M.gguf b/llama3.1-8b-pubmed-10k.Q4_K_M.gguf new file mode 100644 index 0000000..4980cb0 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e715944cf122bc65eb6203606aa2333df1b5c35f467a294d2d75b003332695e3 +size 4920734208 diff --git a/llama3.1-8b-pubmed-10k.Q4_K_S.gguf b/llama3.1-8b-pubmed-10k.Q4_K_S.gguf new file mode 100644 index 0000000..b57e9c4 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ba61e2b175eb4a34d7b7b1374c10088603cf7824eb36c2e536ba9cab1993c9a +size 4692668928 diff --git a/llama3.1-8b-pubmed-10k.Q5_K_M.gguf b/llama3.1-8b-pubmed-10k.Q5_K_M.gguf new file mode 100644 index 0000000..0cdca74 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcdd7d08e1b71a9ac474c82d25cb94340509dff411805b19a4e99f3c7f22ab17 +size 5732987392 diff --git a/llama3.1-8b-pubmed-10k.Q5_K_S.gguf b/llama3.1-8b-pubmed-10k.Q5_K_S.gguf new file mode 100644 index 0000000..2d0ab56 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdca3452ee416f9c76f6230ce44facbd612b663c0b4b4824532cfb9d76b05814 +size 5599293952 diff --git a/llama3.1-8b-pubmed-10k.Q6_K.gguf b/llama3.1-8b-pubmed-10k.Q6_K.gguf new file mode 100644 index 0000000..e759873 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e5322f45f98326b92accc1e4dff1eea516cee201eba154e3fa89495f41c7e82 +size 6596006400 diff --git a/llama3.1-8b-pubmed-10k.Q8_0.gguf b/llama3.1-8b-pubmed-10k.Q8_0.gguf new file mode 100644 index 0000000..02fd147 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501de2c5d7a17d1e2532f39e7ba60cfe6f5f0d686b3ff4cb64f3c7ef2f8c5101 +size 8540770816 diff --git a/llama3.1-8b-pubmed-10k.f16.gguf b/llama3.1-8b-pubmed-10k.f16.gguf new file mode 100644 index 0000000..57caf24 --- /dev/null +++ b/llama3.1-8b-pubmed-10k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ab301618d7cf2e6ee61d83b24344a995fba17a36133ea8a4cb30776f8548966 +size 16068891136