commit 9540436a14430d908bb358abc0913584dcedb674 Author: ModelHub XC Date: Mon Sep 28 02:43:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d2fef22 --- /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 +llama-3-8b-chat-doctor-databrick-full.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-doctor-databrick-full.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..30a7219 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: tannguyen2311/llama-3-8b-chat-doctor-databrick-full +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/tannguyen2311/llama-3-8b-chat-doctor-databrick-full + + +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/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-doctor-databrick-full-GGUF/resolve/main/llama-3-8b-chat-doctor-databrick-full.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/llama-3-8b-chat-doctor-databrick-full.IQ3_M.gguf b/llama-3-8b-chat-doctor-databrick-full.IQ3_M.gguf new file mode 100644 index 0000000..4667be7 --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9a3dae808a7137d0c10fabd861cc8d5eb13ab6e4fa29dccb8096a1f5f6768a +size 3784834208 diff --git a/llama-3-8b-chat-doctor-databrick-full.IQ3_S.gguf b/llama-3-8b-chat-doctor-databrick-full.IQ3_S.gguf new file mode 100644 index 0000000..44bb2fd --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6221e6eba76a569c2dcfa55bfebda601508b27f8ebb565a7031a56a14936400 +size 3682335904 diff --git a/llama-3-8b-chat-doctor-databrick-full.IQ3_XS.gguf b/llama-3-8b-chat-doctor-databrick-full.IQ3_XS.gguf new file mode 100644 index 0000000..26f87b2 --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4331cb6c7e907d59890c1bbf747306aaba610fe6153a29e49ec6f24bbe5e638 +size 3518758048 diff --git a/llama-3-8b-chat-doctor-databrick-full.IQ4_XS.gguf b/llama-3-8b-chat-doctor-databrick-full.IQ4_XS.gguf new file mode 100644 index 0000000..23d2e21 --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8458993a7a1d429a873b858563dfb5c721a81f64d7d9a749c12e29aba2def60f +size 4484374496 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q2_K.gguf b/llama-3-8b-chat-doctor-databrick-full.Q2_K.gguf new file mode 100644 index 0000000..66e6b14 --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05c9b26ae5743721194784708f7108696e4867f2c709ec60249ed90dcf22822e +size 3179141472 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q3_K_L.gguf b/llama-3-8b-chat-doctor-databrick-full.Q3_K_L.gguf new file mode 100644 index 0000000..cb01f3c --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1f556fbe413ae19aaaacbffe6b1377b439905bebb2a8c3a5cc0791f579dcd96 +size 4321967264 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q3_K_M.gguf b/llama-3-8b-chat-doctor-databrick-full.Q3_K_M.gguf new file mode 100644 index 0000000..c5498fc --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3f368f1da3d2cb45cf1ea8674d2d78412810793577c56bc9288517185f7ae8 +size 4018928800 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q3_K_S.gguf b/llama-3-8b-chat-doctor-databrick-full.Q3_K_S.gguf new file mode 100644 index 0000000..8504515 --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea68971d3c1771ccff61e29e947dfc9b8865a95b9c0e2139883ee80613c3b312 +size 3664510112 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q4_K_M.gguf b/llama-3-8b-chat-doctor-databrick-full.Q4_K_M.gguf new file mode 100644 index 0000000..e4c7dfb --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cb95d96fc13c36b9dd9b82af305b6aadb263b6d4b2662ea4b7abfbc5dc9674b +size 4920746208 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q4_K_S.gguf b/llama-3-8b-chat-doctor-databrick-full.Q4_K_S.gguf new file mode 100644 index 0000000..859df12 --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3a0241939c90b6abe9d8a7abd07a5fd6ba10786ea44c87b3826d00901b2924 +size 4692680928 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q5_K_M.gguf b/llama-3-8b-chat-doctor-databrick-full.Q5_K_M.gguf new file mode 100644 index 0000000..be690b5 --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04164ef9892597ba2a95b798e31024d270b279356682754bcda3f3fb552a7543 +size 5733000416 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q5_K_S.gguf b/llama-3-8b-chat-doctor-databrick-full.Q5_K_S.gguf new file mode 100644 index 0000000..42cfddb --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:398c615cd4a8e4960cffe309074ac21ac4794063ece6f2c39698ef713965eceb +size 5599306976 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q6_K.gguf b/llama-3-8b-chat-doctor-databrick-full.Q6_K.gguf new file mode 100644 index 0000000..3d6f68f --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae505c942de960898821bf3b9928020db064b01f7e5590fed65dc7dbab798b1f +size 6596020512 diff --git a/llama-3-8b-chat-doctor-databrick-full.Q8_0.gguf b/llama-3-8b-chat-doctor-databrick-full.Q8_0.gguf new file mode 100644 index 0000000..0dd4e8b --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e4dfff085274a9e5ea69040f8123d106997ed655cde64b670d30b7162ccbd1 +size 8540788896 diff --git a/llama-3-8b-chat-doctor-databrick-full.f16.gguf b/llama-3-8b-chat-doctor-databrick-full.f16.gguf new file mode 100644 index 0000000..a7e2ebf --- /dev/null +++ b/llama-3-8b-chat-doctor-databrick-full.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a343aebb65f958350ac9aa665ac70cef5c1a6b3c22537957467a62065dbf2a3e +size 16068924576