commit 6b81e7f9a5f8b4c56dcb4f5b264016242a496462 Author: ModelHub XC Date: Thu Jun 4 01:19:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..be4d3c3 --- /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 +LlamaTron-RS1-Nemesis-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaTron-RS1-Nemesis-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaTron-RS1-Nemesis-1B.IQ4_XS.gguf b/LlamaTron-RS1-Nemesis-1B.IQ4_XS.gguf new file mode 100644 index 0000000..40f5828 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f336e2dbc27cf3e69e367cee003672c376f0366df3d2869c059b1389326e3c0 +size 748385280 diff --git a/LlamaTron-RS1-Nemesis-1B.Q2_K.gguf b/LlamaTron-RS1-Nemesis-1B.Q2_K.gguf new file mode 100644 index 0000000..04a144c --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b08318912e790e0119a0279ee4b59c2e6d3e391dc125eec1e50014387bfe27 +size 580875264 diff --git a/LlamaTron-RS1-Nemesis-1B.Q3_K_L.gguf b/LlamaTron-RS1-Nemesis-1B.Q3_K_L.gguf new file mode 100644 index 0000000..90cf6ae --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e157a6ee97dc535972dcea8baf6ed4e599662974a0a6c383d72c0618ada601b +size 732525568 diff --git a/LlamaTron-RS1-Nemesis-1B.Q3_K_M.gguf b/LlamaTron-RS1-Nemesis-1B.Q3_K_M.gguf new file mode 100644 index 0000000..6ccf3d8 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaee85a841c3137945f27ef15f693216cbae129c6528d96df3078f8f2d90e215 +size 690844672 diff --git a/LlamaTron-RS1-Nemesis-1B.Q3_K_S.gguf b/LlamaTron-RS1-Nemesis-1B.Q3_K_S.gguf new file mode 100644 index 0000000..55ddc04 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087a7ae7732a153f00a4d4bff912501e92a4732b4b6571c7ef4172dfc8708143 +size 641692672 diff --git a/LlamaTron-RS1-Nemesis-1B.Q4_K_M.gguf b/LlamaTron-RS1-Nemesis-1B.Q4_K_M.gguf new file mode 100644 index 0000000..b4ef94e --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3275c803adff5e316f452bb5323646699a12381165bad13aa8f9737cdc04dd7 +size 807695360 diff --git a/LlamaTron-RS1-Nemesis-1B.Q4_K_S.gguf b/LlamaTron-RS1-Nemesis-1B.Q4_K_S.gguf new file mode 100644 index 0000000..295db08 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e812178ff9dc7f6c1b63e848b0f57c8c86458ad5b76448084ec7e4f68624ac9 +size 775648256 diff --git a/LlamaTron-RS1-Nemesis-1B.Q5_K_M.gguf b/LlamaTron-RS1-Nemesis-1B.Q5_K_M.gguf new file mode 100644 index 0000000..d755ed3 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab09631c93df5fd6ba5b464c6e551eee666e62531148a91dc56ee6cb512a9f0b +size 911504384 diff --git a/LlamaTron-RS1-Nemesis-1B.Q5_K_S.gguf b/LlamaTron-RS1-Nemesis-1B.Q5_K_S.gguf new file mode 100644 index 0000000..23a26a9 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c95207359431cbaa6830e7354cf1b8d35c2f5585f6d4b6a1cce83f7114559b8a +size 892564480 diff --git a/LlamaTron-RS1-Nemesis-1B.Q6_K.gguf b/LlamaTron-RS1-Nemesis-1B.Q6_K.gguf new file mode 100644 index 0000000..349aa49 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf033c1632ded5d518406c4cd93cece168918fd2bb4ad5deb10aac1982ac23d3 +size 1021801472 diff --git a/LlamaTron-RS1-Nemesis-1B.Q8_0.gguf b/LlamaTron-RS1-Nemesis-1B.Q8_0.gguf new file mode 100644 index 0000000..687e178 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5423bc7f2e22b33c615e275c6799fe8d4f17baa93b79561d828ef1156408ce9f +size 1321083904 diff --git a/LlamaTron-RS1-Nemesis-1B.f16.gguf b/LlamaTron-RS1-Nemesis-1B.f16.gguf new file mode 100644 index 0000000..ad8c752 --- /dev/null +++ b/LlamaTron-RS1-Nemesis-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4afd74021d7e2f6a829d6477c6e5e9c38c777e26e568943175122391a8ce7b +size 2479596544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4ccd905 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Rumiii/LlamaTron-RS1-Nemesis-1B +datasets: +- OpenMed/Medical-Reasoning-SFT-MiniMax-M2.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- medical +- clinical +- reasoning +- qlora +- llama +- healthcare +- chain-of-thought +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Rumiii/LlamaTron-RS1-Nemesis-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LlamaTron-RS1-Nemesis-1B-GGUF).*** + +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/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaTron-RS1-Nemesis-1B-GGUF/resolve/main/LlamaTron-RS1-Nemesis-1B.f16.gguf) | f16 | 2.6 | 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. + +