--- base_model: davidkim205/Rhea-72b-v0.5 language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher --- ## About weighted/imatrix quants of https://huggingface.co/davidkim205/Rhea-72b-v0.5 **the imatrix was calculated on a reduced 40k token set (the "quarter" set) as the full token set caused overflows in the model (likely a model bug)** static quants are available at https://huggingface.co/mradermacher/Rhea-72b-v0.5-GGUF ## 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/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ1_S.gguf) | i1-IQ1_S | 20.5 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ1_M.gguf) | i1-IQ1_M | 21.8 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 24.0 | | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 26.0 | | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_S.gguf) | i1-IQ2_S | 27.6 | | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_M.gguf) | i1-IQ2_M | 29.4 | | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q2_K.gguf) | i1-Q2_K | 31.1 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 31.9 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ3_XS.gguf) | i1-IQ3_XS | 34.0 | | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ3_S.gguf) | i1-IQ3_S | 35.6 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q3_K_S.gguf) | i1-Q3_K_S | 35.6 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ3_M.gguf) | i1-IQ3_M | 37.3 | | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 39.3 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 42.6 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 42.8 | | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ4_NL.gguf) | i1-IQ4_NL | 45.1 | slightly worse than Q4_K_S | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_0.gguf) | i1-Q4_0 | 45.2 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 45.3 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 47.8 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 53.9 | | | [PART 1](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 55.4 | | | [PART 1](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 63.4 | practically like static Q6_K | 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.