commit 0b296fb4f0076c0adb8dbca9a7c7a3ddb705a442 Author: ModelHub XC Date: Thu Jul 2 06:48:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..70e3dd2 --- /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 +Megatron-Bots-1.7B-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Bots-1.7B-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Megatron-Bots-1.7B-Reasoning.IQ4_XS.gguf b/Megatron-Bots-1.7B-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..2be0df2 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25eb307759ebf6683d001bf0bc9f636cdf844a797b7fdbfc1c4bca3dfd6e1b31 +size 1016277792 diff --git a/Megatron-Bots-1.7B-Reasoning.Q2_K.gguf b/Megatron-Bots-1.7B-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..2a4f66f --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69513118624c9de7171a2b8d0059aa56e6fe37c0f3db44ab8a26ef31c5b341c0 +size 777792288 diff --git a/Megatron-Bots-1.7B-Reasoning.Q3_K_L.gguf b/Megatron-Bots-1.7B-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..3a5b593 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99443397e1ac190cc5d12e97d69cd962a2b8d8393ac5dbdeb41e619f75d1becf +size 1003498272 diff --git a/Megatron-Bots-1.7B-Reasoning.Q3_K_M.gguf b/Megatron-Bots-1.7B-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..f23e5e7 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0280460f0bda09206964ce2926cdc12efb25da8cdaea7fb510d598428c14b5 +size 939535136 diff --git a/Megatron-Bots-1.7B-Reasoning.Q3_K_S.gguf b/Megatron-Bots-1.7B-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..2bca274 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd95e51060baf35a67dfe9bb0d245f52cba3326e7f6eb789f2ca7e8ca383def +size 867248928 diff --git a/Megatron-Bots-1.7B-Reasoning.Q4_K_M.gguf b/Megatron-Bots-1.7B-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..076e73f --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b892098434cda0263bf5c3e794cd71d4802ae44da59e1307a011dece91889e7e +size 1107405600 diff --git a/Megatron-Bots-1.7B-Reasoning.Q4_K_S.gguf b/Megatron-Bots-1.7B-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..e2565b7 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d74830c360b768b1ce5c08ff0c77429d64090cc692b8666ce71c00c4ffe121 +size 1060186912 diff --git a/Megatron-Bots-1.7B-Reasoning.Q5_K_M.gguf b/Megatron-Bots-1.7B-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..620f7c5 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8106f0abf37747f6d56b7ed5cb87bdd076e363932ab4a23d907bbe1cbafbb72 +size 1257876256 diff --git a/Megatron-Bots-1.7B-Reasoning.Q5_K_S.gguf b/Megatron-Bots-1.7B-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..58a9b00 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47024492f474173820c1da8c283cb622191ee57a688f5ce9abc08d386135ed3 +size 1230580512 diff --git a/Megatron-Bots-1.7B-Reasoning.Q6_K.gguf b/Megatron-Bots-1.7B-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..e9942e0 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1de1fa3b1a1ba0507de8c3cff6c171ebc723f6717882dac9e3dbd95d1818d3 +size 1417751328 diff --git a/Megatron-Bots-1.7B-Reasoning.Q8_0.gguf b/Megatron-Bots-1.7B-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..e1fcc09 --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52d3ac71d23739576e77df503eb85ecc40601edb7acd18b2924d7a1213a92e23 +size 1834423072 diff --git a/Megatron-Bots-1.7B-Reasoning.f16.gguf b/Megatron-Bots-1.7B-Reasoning.f16.gguf new file mode 100644 index 0000000..8b4582d --- /dev/null +++ b/Megatron-Bots-1.7B-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c44447e691fcdf700729552eebf716afb824202c73d32a722cd0e60c2e42d5 +size 3447345952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..289c8dc --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: prithivMLmods/Megatron-Bots-1.7B-Reasoning +datasets: +- MiniMaxAI/SynLogic +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- code +- synlogic +- moe +- math +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Megatron-Bots-1.7B-Reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Megatron-Bots-1.7B-Reasoning-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/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Bots-1.7B-Reasoning-GGUF/resolve/main/Megatron-Bots-1.7B-Reasoning.f16.gguf) | f16 | 3.5 | 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. + +