--- base_model: Weyaxi/Einstein-v4-Qwen-1.5-32B datasets: - allenai/ai2_arc - camel-ai/physics - camel-ai/chemistry - camel-ai/biology - camel-ai/math - metaeval/reclor - openbookqa - mandyyyyii/scibench - derek-thomas/ScienceQA - TIGER-Lab/ScienceEval - jondurbin/airoboros-3.2 - LDJnr/Capybara - Cot-Alpaca-GPT4-From-OpenHermes-2.5 - STEM-AI-mtl/Electrical-engineering - knowrohit07/saraswati-stem - sablo/oasst2_curated - glaiveai/glaive-code-assistant - lmsys/lmsys-chat-1m - TIGER-Lab/MathInstruct - bigbio/med_qa - meta-math/MetaMathQA-40K - openbookqa - piqa - metaeval/reclor - derek-thomas/ScienceQA - scibench - sciq - Open-Orca/SlimOrca - migtissera/Synthia-v1.3 - TIGER-Lab/ScienceEval language: - en library_name: transformers license: other quantized_by: mradermacher tags: - axolotl - generated_from_trainer - phi - phi2 - einstein - instruct - finetune - chatml - gpt4 - synthetic data - science - physics - chemistry - biology - math --- ## About weighted/imatrix quants of https://huggingface.co/Weyaxi/Einstein-v4-Qwen-1.5-32B static quants are available at https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-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/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.3 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.4 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.3 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.8 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.7 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.4 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.4 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.8 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.9 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.2 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.7 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.7 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.7 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.6 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.2 | | | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.