--- base_model: cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated datasets: - cognitivecomputations/Dolphin-2.9.2 - teknium/OpenHermes-2.5 - m-a-p/CodeFeedback-Filtered-Instruction - cognitivecomputations/dolphin-coder - cognitivecomputations/samantha-data - microsoft/orca-math-word-problems-200k - internlm/Agent-FLAN - cognitivecomputations/SystemChat-2.0 language: - en library_name: transformers license: mit quantized_by: mradermacher --- ## About weighted/imatrix quants of https://huggingface.co./cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated static quants are available at https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-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/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 3.2 | for the desperate | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 3.4 | mostly desperate | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.9 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.3 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 4.5 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 4.9 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q2_K.gguf) | i1-Q2_K | 5.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.5 | lower quality | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.9 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.2 | IQ3_XS probably better | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 6.2 | beats Q3_K* | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 6.4 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.9 | IQ3_S probably better | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.4 | IQ3_M probably better | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.6 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 8.0 | fast, low quality | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.1 | optimal size/speed/quality | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.5 | fast, recommended | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.7 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.0 | | | [GGUF](https://huggingface.co./mradermacher/dolphin-2.9.2-Phi-3-Medium-abliterated-i1-GGUF/resolve/main/dolphin-2.9.2-Phi-3-Medium-abliterated.i1-Q6_K.gguf) | i1-Q6_K | 11.6 | 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 private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.