# Llama-3.1-Niitorm-8B-DPO * *DPO Trained, Llama3.1-8B.* ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/QeNjtwolNpxUmpo9NL7VI.png) New: DPO'd Gutenberg Version (full epoch training). RP model, Niitama 1.1 as a base, nearswapped with one of the smartest 3.1 models "Storm", then DPO'd, mostly abliterated. Essentially, it's an improved Niitama 1.1 ------------------------------------------------------------------------------- *Gutenberg DPO creates more human-like prose/story writing and greately lessen synthetic feeling outputs.* ------------------------------------------------------------------------------- # *llama.cpp:* # thank you, mradermacher (GGUF) * [GGUF static](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-DPO-t0.0001-GGUF) * [GGUF Imatrix](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-DPO-t0.0001-i1-GGUF) # thank you, QuantFactory (GGUF) * [GGUF static](https://huggingface.co/QuantFactory/L3.1-Niitorm-8B-DPO-t0.0001-GGUF) # v0 (GGUF) * [GGUF Imatrix](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001-GGUFs-IMATRIX) *-only q8, q6 k, q5 k s, q4 k s, iq4 x s* ## Finetune and merge This is a merge and finetune of pre-trained language models. *Resultant merge finetuned* on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) for 1 epoch, 1.5e-5 learning rate, on Nvidia A100. ## Merge Details ### Merge Method This model was merged using the NEARSWAP t0.0001 merge algorithm. ### Models Merged The following models were included in the merge: * Base Model: [Sao10K/L3.1-8B-Niitama-v1.1](https://huggingface.co/Sao10K/L3.1-8B-Niitama-v1.1) + [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B) * [akjindal53244/Llama-3.1-Storm-8B](https://huggingface.co/akjindal53244/Llama-3.1-Storm-8B) ### Configuration The following YAML configuration was used to produce this model: ```yaml slices: - sources: - model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B layer_range: [0, 32] - model: akjindal53244/Llama-3.1-Storm-8B layer_range: [0, 32] merge_method: nearswap base_model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B parameters: t: - value: 0.0001 dtype: float16 # Then, DPO Finetune # [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) ``` ### DPO Notes *I used a higher learning rate and full dataset when training compared to my "L3.1-Celestial-Stone-2x8B-DPO". This caused lower loss and better adaption to the chosen style.* ------------------------------------------------------------------------------- # Prompt Template: ```bash <|begin_of_text|><|start_header_id|>system<|end_header_id|> {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> {input}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {output}<|eot_id|> ``` Credit to Alchemonaut. Credit to Sao10K. Credit to Grimjim. Credit to mlabonne. Credit to jondurbin. Credit to woofwolfy. # [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_v000000__L3.1-Niitorm-8B-DPO-t0.0001) | Metric |Value| |-------------------|----:| |Avg. |27.89| |IFEval (0-Shot) |76.89| |BBH (3-Shot) |30.51| |MATH Lvl 5 (4-Shot)|14.88| |GPQA (0-shot) | 5.93| |MuSR (0-shot) | 7.26| |MMLU-PRO (5-shot) |31.85|