mradermacher/Magicoder_CL_python-GGUF

1---2base_model: karths/Magicoder_CL_python3language:4- en5library_name: transformers6mradermacher:7  readme_rev: 18quantized_by: mradermacher9---10## About11 12<!-- ### quantize_version: 2 -->13<!-- ### output_tensor_quantised: 1 -->14<!-- ### convert_type: hf -->15<!-- ### vocab_type:  -->16<!-- ### tags:  -->17static quants of https://huggingface.co/karths/Magicoder_CL_python18 19<!-- provided-files -->20 21***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Magicoder_CL_python-GGUF).***22 23weighted/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.24## Usage25 26If you are unsure how to use GGUF files, refer to one of [TheBloke's27READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for28more details, including on how to concatenate multi-part files.29 30## Provided Quants31 32(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)33 34| Link | Type | Size/GB | Notes |35|:-----|:-----|--------:|:------|36| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q2_K.gguf) | Q2_K | 2.6 |  |37| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q3_K_S.gguf) | Q3_K_S | 3.0 |  |38| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |39| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q3_K_L.gguf) | Q3_K_L | 3.7 |  |40| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.IQ4_XS.gguf) | IQ4_XS | 3.7 |  |41| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |42| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |43| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q5_K_S.gguf) | Q5_K_S | 4.8 |  |44| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q5_K_M.gguf) | Q5_K_M | 4.9 |  |45| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q6_K.gguf) | Q6_K | 5.6 | very good quality |46| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |47| [GGUF](https://huggingface.co/mradermacher/Magicoder_CL_python-GGUF/resolve/main/Magicoder_CL_python.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |48 49Here is a handy graph by ikawrakow comparing some lower-quality quant50types (lower is better):51 52![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)53 54And here are Artefact2's thoughts on the matter:55https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec956 57## FAQ / Model Request58 59See https://huggingface.co/mradermacher/model_requests for some answers to60questions you might have and/or if you want some other model quantized.61 62## Thanks63 64I thank my company, [nethype GmbH](https://www.nethype.de/), for letting65me use its servers and providing upgrades to my workstation to enable66this work in my free time.67 68<!-- end -->69