Reward-Calibration - a HINT-lab Collection

HINT-lab 's Collections

PosS-Speculative-Decoding

Self-Calibration

Reward-Calibration

VLM

Reward-Calibration

updated Feb 21

HINT-lab/llama3-8b-final-ppo-c-v0.3

Text Generation • 8B • Updated Oct 17, 2024 • 31
HINT-lab/mistral-7b-hermes-crm-skywork

7B • Updated Oct 17, 2024 • 14
HINT-lab/mistral-7b-hermes-cdpo-v0.2

Text Generation • 7B • Updated Oct 10, 2024 • 2
HINT-lab/mistral-7b-ppo-clean-hermes

Text Generation • 7B • Updated Oct 12, 2024 • 4
HINT-lab/mistral-7b-ppo-hermes-v0.3

Text Generation • 7B • Updated Oct 12, 2024 • 3 • 1
HINT-lab/mistral-7b-ppo-m-hermes

Text Generation • 7B • Updated Oct 17, 2024 • 8 • 1
HINT-lab/llama3-8b-cdpo-v0.2

Text Generation • 8B • Updated Oct 12, 2024 • 7
HINT-lab/llama3-8b-final-ppo-v0.3

Text Generation • 8B • Updated Oct 12, 2024 • 16
HINT-lab/mistral-7b-hermes-rm-skywork

7B • Updated Oct 11, 2024 • 6
HINT-lab/llama3-8b-final-ppo-m-v0.3

Text Generation • 8B • Updated Oct 17, 2024 • 46
HINT-lab/llama3-8b-crm-final-v0.1

8B • Updated Oct 17, 2024 • 4
HINT-lab/llama3-8b-final-ppo-clean-v0.1

Text Generation • 8B • Updated Oct 12, 2024 • 7
HINT-lab/mistral-7b-hermes-dpo-v0.2

Text Generation • 7B • Updated Oct 10, 2024 • 6
HINT-lab/mistral-7b-ppo-c-hermes

Text Generation • 7B • Updated Oct 17, 2024 • 12
HINT-lab/llama3-8b-dpo-v0.2

Text Generation • 8B • Updated Oct 12, 2024 • 5