commit 25fd718b8f5e795fb83b4b91eddf4dccc64becdf Author: ModelHub XC Date: Tue Jun 16 19:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ae3e962 --- /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 +GanitLLM-1.7B_SFT_GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B_SFT_GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GanitLLM-1.7B_SFT_GRPO.IQ4_XS.gguf b/GanitLLM-1.7B_SFT_GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..56513c0 --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78ff97a40397a54d258eeaffc201e016bb7e76e6690fed59922ef65b33d643b +size 1181588320 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q2_K.gguf b/GanitLLM-1.7B_SFT_GRPO.Q2_K.gguf new file mode 100644 index 0000000..3e1f325 --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65019c1a23b31c7630b3d4a74b271583e7285a33b981600e8e47a816ffbb6f86 +size 879897440 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q3_K_L.gguf b/GanitLLM-1.7B_SFT_GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..a40ea85 --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f519d8fedd94cc37fae9a69e7bff19f37634b3b318c67f9b09476166f08b2a65 +size 1137206112 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q3_K_M.gguf b/GanitLLM-1.7B_SFT_GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..018f8ed --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c491a19b1ffe3d9b2b853816de31d044a5301a8399dfd0fc8b10a60b0f62836 +size 1073242976 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q3_K_S.gguf b/GanitLLM-1.7B_SFT_GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..4a78d5b --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0260fcd6f78adbad5631b399a4a7373dbbc3471e0a770739e64f884a29a36e27 +size 1000956768 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q4_K_M.gguf b/GanitLLM-1.7B_SFT_GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..3f47b5f --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a58029835209509e8a779c4b2b25e69de96953fd157ef03162a57c33236be25b +size 1282440032 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q4_K_S.gguf b/GanitLLM-1.7B_SFT_GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..716374e --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d96ac0a3666986a7bd835665f0a595add3cf3e765d40862c3791b4d8e83a4821 +size 1235221344 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q5_K_M.gguf b/GanitLLM-1.7B_SFT_GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..1b94f05 --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea91fff2919a29034b8d5e384a6a65f3243ec9ff937e9a40cdb3506cf49c74b +size 1471806304 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q5_K_S.gguf b/GanitLLM-1.7B_SFT_GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..ba8105d --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245e1bdbb6bdf055bd6a5e7d387d2c8df85f3ea644e705468e57753d956f2875 +size 1444510560 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q6_K.gguf b/GanitLLM-1.7B_SFT_GRPO.Q6_K.gguf new file mode 100644 index 0000000..0b6f33d --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9e1138f3d35aee7a5e78931490e43685a753759d99212959efc09031f8cdef +size 1673007968 diff --git a/GanitLLM-1.7B_SFT_GRPO.Q8_0.gguf b/GanitLLM-1.7B_SFT_GRPO.Q8_0.gguf new file mode 100644 index 0000000..7e50128 --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e71891467abd6b24fc1bfddad990bad534dfdc41256c6f6ad802b2fd714f07d8 +size 2165039968 diff --git a/GanitLLM-1.7B_SFT_GRPO.f16.gguf b/GanitLLM-1.7B_SFT_GRPO.f16.gguf new file mode 100644 index 0000000..cc791d1 --- /dev/null +++ b/GanitLLM-1.7B_SFT_GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:726eb330679c130ec18e003a9cd3c33771ec6da7aa8e2a2a6242234b9961d1fa +size 4069679968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..16f5d58 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: dipta007/GanitLLM-1.7B_SFT_GRPO +datasets: +- dipta007/Ganit +language: +- bn +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- math +- bengali +- reasoning +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/dipta007/GanitLLM-1.7B_SFT_GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GanitLLM-1.7B_SFT_GRPO-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/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q3_K_M.gguf) | Q3_K_M | 1.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.IQ4_XS.gguf) | IQ4_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q4_K_M.gguf) | Q4_K_M | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q5_K_S.gguf) | Q5_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q5_K_M.gguf) | Q5_K_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q6_K.gguf) | Q6_K | 1.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.Q8_0.gguf) | Q8_0 | 2.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B_SFT_GRPO-GGUF/resolve/main/GanitLLM-1.7B_SFT_GRPO.f16.gguf) | f16 | 4.2 | 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. + +