mradermacher/HelpingAI-function-GGUF

1---2base_model: Abhaykoul/HelpingAI-function3language:4- en5library_name: transformers6quantized_by: mradermacher7---8## About9 10<!-- ### quantize_version: 2 -->11<!-- ### output_tensor_quantised: 1 -->12<!-- ### convert_type: hf -->13<!-- ### vocab_type:  -->14<!-- ### tags:  -->15static quants of https://huggingface.co/Abhaykoul/HelpingAI-function16 17<!-- provided-files -->18weighted/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.19## Usage20 21If you are unsure how to use GGUF files, refer to one of [TheBloke's22READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for23more details, including on how to concatenate multi-part files.24 25## Provided Quants26 27(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)28 29| Link | Type | Size/GB | Notes |30|:-----|:-----|--------:|:------|31| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q2_K.gguf) | Q2_K | 1.2 |  |32| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.IQ3_XS.gguf) | IQ3_XS | 1.3 |  |33| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.IQ3_S.gguf) | IQ3_S | 1.4 | beats Q3_K* |34| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q3_K_S.gguf) | Q3_K_S | 1.4 |  |35| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.IQ3_M.gguf) | IQ3_M | 1.4 |  |36| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality |37| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q3_K_L.gguf) | Q3_K_L | 1.6 |  |38| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.IQ4_XS.gguf) | IQ4_XS | 1.6 |  |39| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended |40| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended |41| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q5_K_S.gguf) | Q5_K_S | 2.0 |  |42| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q5_K_M.gguf) | Q5_K_M | 2.1 |  |43| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q6_K.gguf) | Q6_K | 2.4 | very good quality |44| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.Q8_0.gguf) | Q8_0 | 3.1 | fast, best quality |45| [GGUF](https://huggingface.co/mradermacher/HelpingAI-function-GGUF/resolve/main/HelpingAI-function.f16.gguf) | f16 | 5.7 | 16 bpw, overkill |46 47Here is a handy graph by ikawrakow comparing some lower-quality quant48types (lower is better):49 50![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)51 52And here are Artefact2's thoughts on the matter:53https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec954 55## FAQ / Model Request56 57See https://huggingface.co/mradermacher/model_requests for some answers to58questions you might have and/or if you want some other model quantized.59 60## Thanks61 62I thank my company, [nethype GmbH](https://www.nethype.de/), for letting63me use its servers and providing upgrades to my workstation to enable64this work in my free time.65 66<!-- end -->67