sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-161415
huggingface/sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-161415
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 8.89%
12 indexed models
12 matching models
huggingface/sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-161415
huggingface/sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205
huggingface/sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-170522
huggingface/sonthenguyen/NeuralHermes-2.5-Mistral-7B
huggingface/sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO
huggingface/sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-corrupted
huggingface/sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-original-v2
huggingface/sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered
huggingface/sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-reversed_corrupted
huggingface/sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbc-213steps
huggingface/sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-180steps
huggingface/sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbr-180steps
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.