commit aa144350720c7acf110904b5e19c0f64e73278f6 Author: ModelHub XC Date: Thu Aug 20 03:15:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..34803b6 --- /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 +JSL-Med-Sft-Llama-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +JSL-Med-Sft-Llama-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/JSL-Med-Sft-Llama-3-8B.IQ4_XS.gguf b/JSL-Med-Sft-Llama-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..c65ec0d --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622cea695f35572d60d6b7b85ffce4ec50026686672c58a8f4b07bf0b2ece74b +size 4484363104 diff --git a/JSL-Med-Sft-Llama-3-8B.Q2_K.gguf b/JSL-Med-Sft-Llama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..56471dc --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9619e8249bba0872b4f1e679b9e6f00985af61f1ad539e3b1c7d65544362c33 +size 3179131744 diff --git a/JSL-Med-Sft-Llama-3-8B.Q3_K_L.gguf b/JSL-Med-Sft-Llama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..aec1623 --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801296438c8ede0ef8a4e6d119bbff6060280bf5e8eb182b83fc169a2a7f181c +size 4321956704 diff --git a/JSL-Med-Sft-Llama-3-8B.Q3_K_M.gguf b/JSL-Med-Sft-Llama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..b16057d --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867e7136ef0d79c8c6448feebcd679347accf4a48c061c897f5d7d3b9ed81ee8 +size 4018918240 diff --git a/JSL-Med-Sft-Llama-3-8B.Q3_K_S.gguf b/JSL-Med-Sft-Llama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..58323cc --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e6edfb5140e59c04cb48c87102dab98216ae4b003ef01c84a52ba6a4139e4e +size 3664499552 diff --git a/JSL-Med-Sft-Llama-3-8B.Q4_K_M.gguf b/JSL-Med-Sft-Llama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..cc78abd --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cde47bf2a9b68d68762e52bdfe5be0590fe0bab40697612208088958cea3a40 +size 4920734560 diff --git a/JSL-Med-Sft-Llama-3-8B.Q4_K_S.gguf b/JSL-Med-Sft-Llama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..7040932 --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10d34b3a0c70536f32b990a5fa660a906eee324cebf2e0be733e4c9cca175875 +size 4692669280 diff --git a/JSL-Med-Sft-Llama-3-8B.Q5_K_M.gguf b/JSL-Med-Sft-Llama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..c802fa5 --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5954796a80d4dc98030e5451fa8f743c010ac5f8720e5b321a07ab16d2fd95d +size 5732987744 diff --git a/JSL-Med-Sft-Llama-3-8B.Q5_K_S.gguf b/JSL-Med-Sft-Llama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..f6d496e --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1360e871569b0a221d6ef76b3b7e7d4efc3913942a4bd3d64dd96811229fcaa +size 5599294304 diff --git a/JSL-Med-Sft-Llama-3-8B.Q6_K.gguf b/JSL-Med-Sft-Llama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..98c19bd --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4629c0667df134a1cdbe77fb9f8a790c9a88fd666b79226552d08c96465f3ccd +size 6596006752 diff --git a/JSL-Med-Sft-Llama-3-8B.Q8_0.gguf b/JSL-Med-Sft-Llama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..c37ea68 --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67337d48de370022fd5522d5f7584d0268e3bb50b92fbca7cd503a736698bbd2 +size 8540771168 diff --git a/JSL-Med-Sft-Llama-3-8B.f16.gguf b/JSL-Med-Sft-Llama-3-8B.f16.gguf new file mode 100644 index 0000000..6df6bc1 --- /dev/null +++ b/JSL-Med-Sft-Llama-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5632cf5d7c5ac083de09ec0fc3ae6da0efb1ac40f24d62a80612e1b253c3e7f2 +size 16068891488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e5050e8 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: johnsnowlabs/JSL-Med-Sft-Llama-3-8B +language: +- en +library_name: transformers +license: cc-by-nc-nd-4.0 +quantized_by: mradermacher +tags: +- llama-3-8b +- sft +- medical +--- +## About + + + + + + +static quants of https://huggingface.co/johnsnowlabs/JSL-Med-Sft-Llama-3-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-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/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/JSL-Med-Sft-Llama-3-8B-GGUF/resolve/main/JSL-Med-Sft-Llama-3-8B.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. + +