commit 1412608cd9a87e5c91c886f29af311499904efbc Author: ModelHub XC Date: Fri Jun 26 08:57:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GanitLLM-1.7B-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fd311de --- /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.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GanitLLM-1.7B-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GanitLLM-1.7B-SFT.IQ4_XS.gguf b/GanitLLM-1.7B-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..e8484e0 --- /dev/null +++ b/GanitLLM-1.7B-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867a52f48ef1e6c073239753c7f84b25a9077b818ce8ffd3df2cda9cc787bd63 +size 1181588416 diff --git a/GanitLLM-1.7B-SFT.Q2_K.gguf b/GanitLLM-1.7B-SFT.Q2_K.gguf new file mode 100644 index 0000000..c6ed8f2 --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19a1ceb6fdbc2712b703b22f4977ab3cdeba4e3db5787f7bba9c007ab2832bc +size 879897536 diff --git a/GanitLLM-1.7B-SFT.Q3_K_L.gguf b/GanitLLM-1.7B-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..6b026c9 --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3e5d13800f05100d032e9dcb04d31e84b2810ef3e74dfa1cdb2d3c0a940d47 +size 1137206208 diff --git a/GanitLLM-1.7B-SFT.Q3_K_M.gguf b/GanitLLM-1.7B-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..354a52b --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d618d7ee3d552c77ed4b47bdacd50372fec10dce950a378a592ac6f42e531d06 +size 1073243072 diff --git a/GanitLLM-1.7B-SFT.Q3_K_S.gguf b/GanitLLM-1.7B-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..269a3c7 --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ec0409b997b68835879df371c8af715a6fbdd6c6e561247aa40ff3711de88e +size 1000956864 diff --git a/GanitLLM-1.7B-SFT.Q4_K_M.gguf b/GanitLLM-1.7B-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..261a77d --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135ba4f4e29cf73f9db487d63921fd31ffaca56013ca467321b8bef03d9f9261 +size 1282440128 diff --git a/GanitLLM-1.7B-SFT.Q4_K_S.gguf b/GanitLLM-1.7B-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..6792d63 --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb778a65cde46a329bfa4c36d976f69d633e860efcfed20e470706585767464 +size 1235221440 diff --git a/GanitLLM-1.7B-SFT.Q5_K_M.gguf b/GanitLLM-1.7B-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..4b8a783 --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a6d88c0a38373387f0dabdbfe46991d7a8012fc3b1d4779aa0751908752edf +size 1471806400 diff --git a/GanitLLM-1.7B-SFT.Q5_K_S.gguf b/GanitLLM-1.7B-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..b954b61 --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801c581e034d2c13df41c90ed01e67caf256686d1b92a3a310bf5eacefa82ce3 +size 1444510656 diff --git a/GanitLLM-1.7B-SFT.Q6_K.gguf b/GanitLLM-1.7B-SFT.Q6_K.gguf new file mode 100644 index 0000000..5cb7239 --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:071f3580dce7f85d1387a59bcfac5532fd0da51de8062aca4e4b186bc9302475 +size 1673008064 diff --git a/GanitLLM-1.7B-SFT.Q8_0.gguf b/GanitLLM-1.7B-SFT.Q8_0.gguf new file mode 100644 index 0000000..5cd549a --- /dev/null +++ b/GanitLLM-1.7B-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773845eec0c172e25ade61b376a2d9709b21ff922c05f29e7635a53228e35936 +size 2165040064 diff --git a/GanitLLM-1.7B-SFT.f16.gguf b/GanitLLM-1.7B-SFT.f16.gguf new file mode 100644 index 0000000..74b46aa --- /dev/null +++ b/GanitLLM-1.7B-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90bcfa322f8396baab30a14b34da512d923a8e68039677c2aa626ead44fadaf +size 4069680064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..013b486 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: dipta007/GanitLLM-1.7B-SFT +datasets: +- dipta007/Ganit +language: +- bn +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- math +- bengali +- reasoning +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/dipta007/GanitLLM-1.7B-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GanitLLM-1.7B-SFT-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-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q3_K_M.gguf) | Q3_K_M | 1.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.IQ4_XS.gguf) | IQ4_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q4_K_M.gguf) | Q4_K_M | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q5_K_S.gguf) | Q5_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q5_K_M.gguf) | Q5_K_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q6_K.gguf) | Q6_K | 1.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.Q8_0.gguf) | Q8_0 | 2.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GanitLLM-1.7B-SFT-GGUF/resolve/main/GanitLLM-1.7B-SFT.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. + +