commit bd8260c0707da032c021fbd0df23db639f788638 Author: ModelHub XC Date: Fri Oct 16 19:16:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Medichat-V2-Llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e54b5ef --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Medichat-V2-Llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-V2-Llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Medichat-V2-Llama3-8B.IQ3_M.gguf b/Medichat-V2-Llama3-8B.IQ3_M.gguf new file mode 100644 index 0000000..694cb56 --- /dev/null +++ b/Medichat-V2-Llama3-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff0417c0abc2bb74684e33936d0ceb7b170fdb639d372114ac8b19d69d03b291 +size 3784823648 diff --git a/Medichat-V2-Llama3-8B.IQ3_S.gguf b/Medichat-V2-Llama3-8B.IQ3_S.gguf new file mode 100644 index 0000000..f062494 --- /dev/null +++ b/Medichat-V2-Llama3-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:515af2d8c9d8cb7e3eebb22c37b664cc43c89ef6ab1ed8d1bcd3f735270e6514 +size 3682325344 diff --git a/Medichat-V2-Llama3-8B.IQ3_XS.gguf b/Medichat-V2-Llama3-8B.IQ3_XS.gguf new file mode 100644 index 0000000..89fcd8f --- /dev/null +++ b/Medichat-V2-Llama3-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e9095bb5ff54b7499f27ee2d7650251590c5e9425166b2e873df6deb589bc6 +size 3518747488 diff --git a/Medichat-V2-Llama3-8B.IQ4_XS.gguf b/Medichat-V2-Llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..5f30e15 --- /dev/null +++ b/Medichat-V2-Llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:972f6be91962b81f6b49c7020bcd3b6c09db71af047e11338385899b8cd2a475 +size 4484363104 diff --git a/Medichat-V2-Llama3-8B.Q2_K.gguf b/Medichat-V2-Llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..51a626a --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cb1ba6e6198832d53744e93a409b6867b1fcad6798b3528fd2cb16acc71e15 +size 3179131744 diff --git a/Medichat-V2-Llama3-8B.Q3_K_L.gguf b/Medichat-V2-Llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..fc44168 --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f2a6b986dfae742baf9c70374b1e100ba4743475b0b4fc8917ab8c189278622 +size 4321956704 diff --git a/Medichat-V2-Llama3-8B.Q3_K_M.gguf b/Medichat-V2-Llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..4ad1345 --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9853238bedcc9aeedd48c6f7815dd810d5e9e518e66d9e7737fc0ddbd1a864ec +size 4018918240 diff --git a/Medichat-V2-Llama3-8B.Q3_K_S.gguf b/Medichat-V2-Llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..4657cb0 --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ad28eba9163764980ee44ad69869182134a352a663ea5f72261b9d6b58ed02 +size 3664499552 diff --git a/Medichat-V2-Llama3-8B.Q4_K_M.gguf b/Medichat-V2-Llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..dfdcf1b --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dea681c9d097c14224010480de63f829d5ae6e81ca22b4714aaa7d48e2b9b0b1 +size 4920734560 diff --git a/Medichat-V2-Llama3-8B.Q4_K_S.gguf b/Medichat-V2-Llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..baeb4ef --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556507c2fc2238791bc046176e1ec3b774a1b032746abe891376584cf180e5ce +size 4692669280 diff --git a/Medichat-V2-Llama3-8B.Q5_K_M.gguf b/Medichat-V2-Llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..7f1f5d5 --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3481474f7525da318a3b476905bdb77cbf0bd5c4338364d08cd11c73817fb2a7 +size 5732987744 diff --git a/Medichat-V2-Llama3-8B.Q5_K_S.gguf b/Medichat-V2-Llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..8904e39 --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2618ceb979c8415313e4d8293dde8ccb4ebbba3e31e2b61accd454c1550c60f4 +size 5599294304 diff --git a/Medichat-V2-Llama3-8B.Q6_K.gguf b/Medichat-V2-Llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..1c314f8 --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59772c4b473c63258a319f5c123731f8169a3cc5f417d75e1049ca96932d8a49 +size 6596006752 diff --git a/Medichat-V2-Llama3-8B.Q8_0.gguf b/Medichat-V2-Llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..38af6ae --- /dev/null +++ b/Medichat-V2-Llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141f2a206b3b2a71d71c0af38d65b8582fd2767e05281b343af1481089c43438 +size 8540771168 diff --git a/Medichat-V2-Llama3-8B.f16.gguf b/Medichat-V2-Llama3-8B.f16.gguf new file mode 100644 index 0000000..fca33f5 --- /dev/null +++ b/Medichat-V2-Llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3146c5e2214563a3c9510961edcda63def4891bdb31eec8ebbdf05021ac7514 +size 16068891488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8748be0 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: sethuiyer/Medichat-V2-Llama3-8B +datasets: +- ruslanmv/ai-medical-chatbot +- Locutusque/hercules-v5.0 +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- mergekit +- merge +- medical +--- +## About + + + + + + +static quants of https://huggingface.co/sethuiyer/Medichat-V2-Llama3-8B + + +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/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Medichat-V2-Llama3-8B-GGUF/resolve/main/Medichat-V2-Llama3-8B.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. + +