SlimOrca training mix
According to the model card, training used a refined SlimOrca mix, with 517981 conversation sets of two conversations each in shared data.
Open Source Model Profile · ajibawa-2023
SlimOrca-Llama-3-8B
SlimOrca-Llama-3-8B is an 8.03B-parameter Llama-family text-generation fine-tune from ajibawa-2023. Its model card describes training on a refined SlimOrca mix with the ChatML prompt format.
- Publisher
- ajibawa-2023
- Task
- text-generation
- Model type
- llama
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
SlimOrca-Llama-3-8B is published by ajibawa-2023 as a Llama-based text-generation model. The captured configuration identifies LlamaForCausalLM with a llama model type, and Safetensors metadata reports 8030261248 parameters. According to the model card, it is trained on a refined version of SlimOrca made available by the Open-Orca team, on Llama 3 by Meta.
Recorded capabilities
ChatML prompt format
The model card says the publisher used the ChatML prompt format with an example prompt pattern.
Documented Axolotl run
According to the model card, training ran for two epochs on four A100 80GB GPUs for almost 114 hours using Axolotl and DeepSpeed.
Use cases in the source record
- General-purpose content workflows the publisher lists, such as Q&A including multiple choice, articles from summaries, sentiment analysis, reviews, and hypothesis generation.
- ChatML-prompted conversational experiments following the publisher's documented ChatML format.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- The publisher notes the model can generate uncensored content to a certain extent and asks users to take responsibility for what they generate.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: ajibawa-2023/SlimOrca-Llama-3-8B
Captured: Unknown. Processed: 2026-09-07T19:34:39.495301+00:00.
SlimOrca-Llama-3-8B: A General Purpose Intelligent Model This Model is trained on refined version of SlimOrca made available by Open-Orca team. This Model is very good in various types of General Purpose content generation such as Q&A (including multiple choice), Articles from Summary, Sentiment Analysis, Context & Hypothesis, Reviews, Erotic story generation etc. To a certain extent it can also generate Uncensored content. Kindly be careful while generating Uncensored content as you will be responsible for what you generate. It is trained on 517981 set of conversations. Each set having 2 conversations. I have shared this data . I h…
F001F002F003F004F005F006F007F009F010F011F012F013F014F015F016F017F018F019F020