--- base_model: EleutherAI/pythia-70m-deduped datasets: - EleutherAI/the_pile_deduplicated language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - pytorch - causal-lm - pythia --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/EleutherAI/pythia-70m-deduped <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/pythia-70m-deduped-i1-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/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q2_K.gguf) | Q2_K | 0.1 | | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.IQ3_XS.gguf) | IQ3_XS | 0.1 | | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.IQ3_S.gguf) | IQ3_S | 0.1 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q3_K_S.gguf) | Q3_K_S | 0.1 | | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.IQ3_M.gguf) | IQ3_M | 0.1 | | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q3_K_M.gguf) | Q3_K_M | 0.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q3_K_L.gguf) | Q3_K_L | 0.1 | | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.IQ4_XS.gguf) | IQ4_XS | 0.1 | | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q4_K_M.gguf) | Q4_K_M | 0.1 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q5_K_S.gguf) | Q5_K_S | 0.2 | | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q5_K_M.gguf) | Q5_K_M | 0.2 | | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q6_K.gguf) | Q6_K | 0.2 | very good quality | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/pythia-70m-deduped-GGUF/resolve/main/pythia-70m-deduped.f16.gguf) | f16 | 0.2 | 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. <!-- end -->