![image/png](https://cdn-uploads.huggingface.co/production/uploads/64adfd277b5ff762771e4571/NGEOrcWYPDnFmvHinkXVk.png) Following up on Crimson_Dawn-v0.2 we have Azure_Dusk-v0.2! Training on [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) this time I've added significantly more data, as well as trained using RSLoRA as opposed to regular LoRA. Another key change is training on ChatML as opposed to Mistral Formatting. # Quants! full / [exl2](https://huggingface.co/Epiculous/Azure_Dusk-v0.2-exl2) / [gguf](https://huggingface.co/Epiculous/Azure_Dusk-v0.2-GGUF) ## Prompting The v0.2 models are trained on ChatML, the prompting structure goes a little something like this: ``` <|im_start|>user Hi there!<|im_end|> <|im_start|>assistant Nice to meet you!<|im_end|> <|im_start|>user Can I ask a question?<|im_end|> <|im_start|>assistant ``` ### Context and Instruct The v0.2 models are trained on ChatML, please use that Context and Instruct template. ### Current Top Sampler Settings [Spicy_Temp](https://files.catbox.moe/9npj0z.json)
[Violet_Twilight-Nitral-Special](https://files.catbox.moe/ot54u3.json)
## Training Training was done twice over 2 epochs each on two 2x [NVIDIA A6000 GPUs](https://www.nvidia.com/en-us/design-visualization/rtx-a6000/) using LoRA. A two-phased approach was used in which the base model was trained 2 epochs on RP data, the LoRA was then applied to base. Finally, the new modified base was trained 2 epochs on instruct, and the new instruct LoRA was applied to the modified base, resulting in what you see here. [

](https://github.com/axolotl-ai-cloud/axolotl) # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Epiculous__Azure_Dusk-v0.2) | Metric |Value| |-------------------|----:| |Avg. |14.03| |IFEval (0-Shot) |34.67| |BBH (3-Shot) |17.40| |MATH Lvl 5 (4-Shot)| 1.66| |GPQA (0-shot) | 1.45| |MuSR (0-shot) | 6.37| |MMLU-PRO (5-shot) |22.60|

New