commit 71b2bcbd2ea103ab71d3accf86971ed1405a979a Author: ModelHub XC Date: Sat May 23 06:43:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-medx_v3.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..15de3a4 --- /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 +Llama-medx_v3.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-medx_v3.2.IQ4_XS.gguf b/Llama-medx_v3.2.IQ4_XS.gguf new file mode 100644 index 0000000..985eacc --- /dev/null +++ b/Llama-medx_v3.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4094581c48ae97fc82f45235a4c8c0628d194988be415a3a46b656c2c16dc9e5 +size 4484374208 diff --git a/Llama-medx_v3.2.Q2_K.gguf b/Llama-medx_v3.2.Q2_K.gguf new file mode 100644 index 0000000..7764264 --- /dev/null +++ b/Llama-medx_v3.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8acd5160c769fb1826bffd3e345bfa929fc6b3f80b74993e3bc55ae8b20dd233 +size 3179141184 diff --git a/Llama-medx_v3.2.Q3_K_L.gguf b/Llama-medx_v3.2.Q3_K_L.gguf new file mode 100644 index 0000000..4067e3e --- /dev/null +++ b/Llama-medx_v3.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:606c257c506ed4b6f460bd0b54090040c27503526e74cf1405e8aa7f2375c1d0 +size 4321966976 diff --git a/Llama-medx_v3.2.Q3_K_M.gguf b/Llama-medx_v3.2.Q3_K_M.gguf new file mode 100644 index 0000000..7b53776 --- /dev/null +++ b/Llama-medx_v3.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f527bbc527bc91d2e75f52eacda73a590bfca14eb9b805e75e31210a7bf26b +size 4018928512 diff --git a/Llama-medx_v3.2.Q3_K_S.gguf b/Llama-medx_v3.2.Q3_K_S.gguf new file mode 100644 index 0000000..d7c29f6 --- /dev/null +++ b/Llama-medx_v3.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6474cccf1e7f3ffd8705f94d450c14e061da497eb44f95bddb4adca84d67d539 +size 3664509824 diff --git a/Llama-medx_v3.2.Q4_K_M.gguf b/Llama-medx_v3.2.Q4_K_M.gguf new file mode 100644 index 0000000..74dafc0 --- /dev/null +++ b/Llama-medx_v3.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41d1f1302915185138eb7d1957ae78fd4c2a2f4db982fe3b198a8fca43f268e +size 4920745920 diff --git a/Llama-medx_v3.2.Q4_K_S.gguf b/Llama-medx_v3.2.Q4_K_S.gguf new file mode 100644 index 0000000..19cd213 --- /dev/null +++ b/Llama-medx_v3.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb7b665c8c71b7210b761f22bd30d526a448c03f1fe814cae78cd9b48ae127d +size 4692680640 diff --git a/Llama-medx_v3.2.Q5_K_M.gguf b/Llama-medx_v3.2.Q5_K_M.gguf new file mode 100644 index 0000000..9213870 --- /dev/null +++ b/Llama-medx_v3.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b351aea760d078740f5762c91fb7ec6ad45c204c410244c2a66c66642823723 +size 5733000128 diff --git a/Llama-medx_v3.2.Q5_K_S.gguf b/Llama-medx_v3.2.Q5_K_S.gguf new file mode 100644 index 0000000..8de5a2b --- /dev/null +++ b/Llama-medx_v3.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec61d7a72ab3e6d4d928742a55fa8c169eecdd7663af3a5132cd27a01b40330 +size 5599306688 diff --git a/Llama-medx_v3.2.Q6_K.gguf b/Llama-medx_v3.2.Q6_K.gguf new file mode 100644 index 0000000..f94a4d4 --- /dev/null +++ b/Llama-medx_v3.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32f1c85681a1a07632f3aa9dfdad9118c6f759454bff321a33be112dceaf34d1 +size 6596020224 diff --git a/Llama-medx_v3.2.Q8_0.gguf b/Llama-medx_v3.2.Q8_0.gguf new file mode 100644 index 0000000..ae58c82 --- /dev/null +++ b/Llama-medx_v3.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffcb22b4312f5ba0da5d8650c1929d3c13636607ae5a3e62983ef1e556030690 +size 8540788608 diff --git a/Llama-medx_v3.2.f16.gguf b/Llama-medx_v3.2.f16.gguf new file mode 100644 index 0000000..3981280 --- /dev/null +++ b/Llama-medx_v3.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1243f58ca6fa6db69720cd22939ecb8ace115752a2c3c47853822474a9235c86 +size 16068924288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5d79632 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: skumar9/Llama-medx_v3.2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/skumar9/Llama-medx_v3.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-medx_v3.2-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/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.2-GGUF/resolve/main/Llama-medx_v3.2.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. + +