commit b54ca68e3a7a6b8d10abc67f2310737bf169286f Author: ModelHub XC Date: Sat May 23 03:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-medx_v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a19e66 --- /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.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-medx_v3.IQ4_XS.gguf b/Llama-medx_v3.IQ4_XS.gguf new file mode 100644 index 0000000..5e32849 --- /dev/null +++ b/Llama-medx_v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e261d2a547b3e2baab2b569abdcaf8852da7a8de6aab84dc29db63d47266fb22 +size 4484374112 diff --git a/Llama-medx_v3.Q2_K.gguf b/Llama-medx_v3.Q2_K.gguf new file mode 100644 index 0000000..2531bae --- /dev/null +++ b/Llama-medx_v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d29be3655eca50c47b622a92ab2ebefa5c81d80e3880c13b8915f87f146351d1 +size 3179141088 diff --git a/Llama-medx_v3.Q3_K_L.gguf b/Llama-medx_v3.Q3_K_L.gguf new file mode 100644 index 0000000..e7155e6 --- /dev/null +++ b/Llama-medx_v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4afa1ecac3922fc23a62935a2c2c1fe36291a5acb58104634ab7791580dc27c +size 4321966880 diff --git a/Llama-medx_v3.Q3_K_M.gguf b/Llama-medx_v3.Q3_K_M.gguf new file mode 100644 index 0000000..86745da --- /dev/null +++ b/Llama-medx_v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e213a15b700bcde373509919417e8c08b572e132b514a38321cac7022965e7 +size 4018928416 diff --git a/Llama-medx_v3.Q3_K_S.gguf b/Llama-medx_v3.Q3_K_S.gguf new file mode 100644 index 0000000..43438cb --- /dev/null +++ b/Llama-medx_v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0430f8f3b7cb01d29ebe10d3b0228311191288ac35340d29945609cd4aead39 +size 3664509728 diff --git a/Llama-medx_v3.Q4_K_M.gguf b/Llama-medx_v3.Q4_K_M.gguf new file mode 100644 index 0000000..3f89745 --- /dev/null +++ b/Llama-medx_v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f63bb20ede386d38acdf741e7696ba6eed98dbdf22a85633b42b421a7edf4599 +size 4920745824 diff --git a/Llama-medx_v3.Q4_K_S.gguf b/Llama-medx_v3.Q4_K_S.gguf new file mode 100644 index 0000000..69b9e68 --- /dev/null +++ b/Llama-medx_v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eac9dd72f0094b25ff12c1d14f68efff380b2c595379101bc70fe0f85d20db60 +size 4692680544 diff --git a/Llama-medx_v3.Q5_K_M.gguf b/Llama-medx_v3.Q5_K_M.gguf new file mode 100644 index 0000000..ef6ddf2 --- /dev/null +++ b/Llama-medx_v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf36dab6fce859d485949759d82c2aa7e9d2629398e769fd5cc65778e403f1fd +size 5733000032 diff --git a/Llama-medx_v3.Q5_K_S.gguf b/Llama-medx_v3.Q5_K_S.gguf new file mode 100644 index 0000000..73606f0 --- /dev/null +++ b/Llama-medx_v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a03d5cfadeb368b3e60a42370c2ec29e59dfbbf2eb4ca26c0f3d01475b0308 +size 5599306592 diff --git a/Llama-medx_v3.Q6_K.gguf b/Llama-medx_v3.Q6_K.gguf new file mode 100644 index 0000000..8d06437 --- /dev/null +++ b/Llama-medx_v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ccfd39dc8a8798541bb51282b8e957dcf4c232dd6d26b37fc67272324d9b47 +size 6596020128 diff --git a/Llama-medx_v3.Q8_0.gguf b/Llama-medx_v3.Q8_0.gguf new file mode 100644 index 0000000..4013592 --- /dev/null +++ b/Llama-medx_v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b874f5f8b91c37f1e9b888a6ecb246e4a139e8e0ee53ff9e9690171d9271b51 +size 8540788512 diff --git a/Llama-medx_v3.f16.gguf b/Llama-medx_v3.f16.gguf new file mode 100644 index 0000000..e8c337a --- /dev/null +++ b/Llama-medx_v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6067051143d148be5b56ceb24abf95e8018bc7e9c65220852475b421f5d5cf72 +size 16068924192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..12a0bec --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: skumar9/Llama-medx_v3 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/skumar9/Llama-medx_v3 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-medx_v3-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-GGUF/resolve/main/Llama-medx_v3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-GGUF/resolve/main/Llama-medx_v3.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. + +