commit c1c68e71e6794bb6a81ecff3931e53a3ca1a2254 Author: ModelHub XC Date: Tue Jun 23 08:22:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-medx_v3.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cca61f2 --- /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-medx_v3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-medx_v3.1.IQ3_M.gguf b/Llama-medx_v3.1.IQ3_M.gguf new file mode 100644 index 0000000..2305ef5 --- /dev/null +++ b/Llama-medx_v3.1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d03d16b6b68a534190dde211918c669720374157c97aeaa03df584c154fbf8 +size 3784833632 diff --git a/Llama-medx_v3.1.IQ3_S.gguf b/Llama-medx_v3.1.IQ3_S.gguf new file mode 100644 index 0000000..bdbe781 --- /dev/null +++ b/Llama-medx_v3.1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b2929ca41a504425ccc582faee41c64fc73bfa51a811845af588953f81b65c +size 3682335328 diff --git a/Llama-medx_v3.1.IQ3_XS.gguf b/Llama-medx_v3.1.IQ3_XS.gguf new file mode 100644 index 0000000..2c14dc4 --- /dev/null +++ b/Llama-medx_v3.1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d339dd9f868707feb17c6a4e25bd76163ee2d402cd3f1d6c590921e0fea1e3 +size 3518757472 diff --git a/Llama-medx_v3.1.IQ4_XS.gguf b/Llama-medx_v3.1.IQ4_XS.gguf new file mode 100644 index 0000000..626a147 --- /dev/null +++ b/Llama-medx_v3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5ea5a91b7091fcb02412d708a770dbef7654918a941f4b6fdb1c77629fff8f8 +size 4484373920 diff --git a/Llama-medx_v3.1.Q2_K.gguf b/Llama-medx_v3.1.Q2_K.gguf new file mode 100644 index 0000000..3869e82 --- /dev/null +++ b/Llama-medx_v3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef96d4d2020650b79f2f9ab00e2b271b62d8a67aa1877a2d11e323203e8a53a +size 3179140896 diff --git a/Llama-medx_v3.1.Q3_K_L.gguf b/Llama-medx_v3.1.Q3_K_L.gguf new file mode 100644 index 0000000..e5b0821 --- /dev/null +++ b/Llama-medx_v3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b292786faaa80227d2ee3904d7507324f899c2c3946ef889d9bbb77ba5c726f +size 4321966688 diff --git a/Llama-medx_v3.1.Q3_K_M.gguf b/Llama-medx_v3.1.Q3_K_M.gguf new file mode 100644 index 0000000..2997e87 --- /dev/null +++ b/Llama-medx_v3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b882b7557611dca021827f37154eb6e39a9e0ab7fa8369c4935bf0b98abf5d0 +size 4018928224 diff --git a/Llama-medx_v3.1.Q3_K_S.gguf b/Llama-medx_v3.1.Q3_K_S.gguf new file mode 100644 index 0000000..4526a5f --- /dev/null +++ b/Llama-medx_v3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6dbb5ac9cdb1a1e2fb9ad4ffb7fa310edd8a3615d767dbfe466bc8b94273097 +size 3664509536 diff --git a/Llama-medx_v3.1.Q4_K_M.gguf b/Llama-medx_v3.1.Q4_K_M.gguf new file mode 100644 index 0000000..1c4a670 --- /dev/null +++ b/Llama-medx_v3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0899e310243db003ac26fd8fdc496f528704645aae25e47773fec092ce8698b +size 4920745632 diff --git a/Llama-medx_v3.1.Q4_K_S.gguf b/Llama-medx_v3.1.Q4_K_S.gguf new file mode 100644 index 0000000..c094034 --- /dev/null +++ b/Llama-medx_v3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924aeeacaa8406da1eec5e6b9d17baa317928611fb89a95fae86f78806ae7aea +size 4692680352 diff --git a/Llama-medx_v3.1.Q5_K_M.gguf b/Llama-medx_v3.1.Q5_K_M.gguf new file mode 100644 index 0000000..3484b90 --- /dev/null +++ b/Llama-medx_v3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183e52926cf8a360b21e1e7bdd6cee79bf232c5d567d5b08bce65d2f0115c44f +size 5732999840 diff --git a/Llama-medx_v3.1.Q5_K_S.gguf b/Llama-medx_v3.1.Q5_K_S.gguf new file mode 100644 index 0000000..2b7d53f --- /dev/null +++ b/Llama-medx_v3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:402d1f947c32ca29ff3eec4c3b3819202f5f058fcd7ce3b25cc6cb2dc6e35ab6 +size 5599306400 diff --git a/Llama-medx_v3.1.Q6_K.gguf b/Llama-medx_v3.1.Q6_K.gguf new file mode 100644 index 0000000..3493fde --- /dev/null +++ b/Llama-medx_v3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc2ca4d1c42d44491f170485e7ab7ba1b0530349f5582c5b45f165ca41e1195 +size 6596019936 diff --git a/Llama-medx_v3.1.Q8_0.gguf b/Llama-medx_v3.1.Q8_0.gguf new file mode 100644 index 0000000..4b3ce2c --- /dev/null +++ b/Llama-medx_v3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed45bd949e041bb8a48300296a4c3235899752f34a81d0f6e2f864387ad7f89 +size 8540788320 diff --git a/Llama-medx_v3.1.f16.gguf b/Llama-medx_v3.1.f16.gguf new file mode 100644 index 0000000..40ecdf0 --- /dev/null +++ b/Llama-medx_v3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d4b513f1ccf35bdd29087b82b8bc61b57bc5e2c4a6295e6d51397f256d8a38 +size 16068924000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd38273 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: skumar9/Llama-medx_v3.1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/skumar9/Llama-medx_v3.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-medx_v3.1-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_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3.1-GGUF/resolve/main/Llama-medx_v3.1.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. + +