mradermacher/developer-git-commit-agent-GGUF
0514
1---2base_model: nivethitha1703/developer-git-commit-agent3language:4- en5library_name: transformers6license: apache-2.07mradermacher:8 readme_rev: 19quantized_by: mradermacher10tags:11- code12- git13- tools14- developer-utilities15---16## About17 18<!-- ### quantize_version: 2 -->19<!-- ### output_tensor_quantised: 1 -->20<!-- ### convert_type: hf -->21<!-- ### vocab_type: -->22<!-- ### tags: -->23<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->24<!-- ### quants_skip: -->25<!-- ### skip_mmproj: -->26static quants of https://huggingface.co/nivethitha1703/developer-git-commit-agent27 28<!-- provided-files -->29 30***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#developer-git-commit-agent-GGUF).***31 32weighted/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.33## Usage34 35If you are unsure how to use GGUF files, refer to one of [TheBloke's36READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for37more details, including on how to concatenate multi-part files.38 39## Provided Quants40 41(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)42 43| Link | Type | Size/GB | Notes |44|:-----|:-----|--------:|:------|45| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q3_K_S.gguf) | Q3_K_S | 0.4 | |46| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q2_K.gguf) | Q2_K | 0.4 | |47| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.IQ4_XS.gguf) | IQ4_XS | 0.5 | |48| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality |49| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q3_K_L.gguf) | Q3_K_L | 0.5 | |50| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended |51| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended |52| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q5_K_S.gguf) | Q5_K_S | 0.5 | |53| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q5_K_M.gguf) | Q5_K_M | 0.5 | |54| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q6_K.gguf) | Q6_K | 0.6 | very good quality |55| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality |56| [GGUF](https://huggingface.co/mradermacher/developer-git-commit-agent-GGUF/resolve/main/developer-git-commit-agent.f16.gguf) | f16 | 1.1 | 16 bpw, overkill |57 58Here is a handy graph by ikawrakow comparing some lower-quality quant59types (lower is better):60 6162 63And here are Artefact2's thoughts on the matter:64https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec965 66## FAQ / Model Request67 68See https://huggingface.co/mradermacher/model_requests for some answers to69questions you might have and/or if you want some other model quantized.70 71## Thanks72 73I thank my company, [nethype GmbH](https://www.nethype.de/), for letting74me use its servers and providing upgrades to my workstation to enable75this work in my free time.76 77<!-- end -->78