mangopy/OpenReward-Qwen2.5-3B-instruct-half-correct-half-wrong-84-step
3B
•
Updated
•
1
zhengliang
mangopy
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
upvoted
a
paper
22 days ago
Annotation-Efficient Universal Honesty Alignment
updated
a model
about 2 months ago
mangopy/OpenReward-Qwen2.5-3B-instruct-half-correct-half-wrong-84-step
Organizations
None yet
mangopy/OpenReward-Qwen2.5-7B-instruct-only-em-96-step
8B
•
Updated
•
2
mangopy/OpenReward-Qwen2.5-7B-instruct-half-correct-half-wrong-84-step
8B
•
Updated
•
2
mangopy/OpenReward-Qwen2.5-7B-instruct-one-search-96-step
8B
•
Updated
•
2
mangopy/OpenReward-Qwen2.5-7B-instruct-one-search-96
Updated
mangopy/OpenRM-Qwen2.5-7B-instruct
8B
•
Updated
•
3
mangopy/OpenReward-Qwen2.5-7B-instruct-96-test
8B
•
Updated
•
2
mangopy/OpenReward-Qwen2.5-7B-instruct-96
8B
•
Updated
•
3
mangopy/checkpoint-100
24B
•
Updated
mangopy/Qwen7_warmup500_em3
8B
•
Updated
mangopy/mistral7b_hotpot1
7B
•
Updated
mangopy/qwen3_hotpot4
3B
•
Updated
mangopy/Qwen7_warmup900_hotpot4
8B
•
Updated
mangopy/Qwen7_warmup900_hotpot3
8B
•
Updated
mangopy/Qwen7_warmup900_hotpot2
8B
•
Updated
mangopy/Qwen7_warmup900_hotpot1
8B
•
Updated
mangopy/Qwen7_warmup500_hotpot1_2
8B
•
Updated
mangopy/Qwen7_warmup500_hotpot1_1
8B
•
Updated
mangopy/qwen7_2wiki3
8B
•
Updated
mangopy/qwen7_2wiki2
8B
•
Updated
mangopy/qwen7_2wiki1
8B
•
Updated
mangopy/qwen7_nq4
8B
•
Updated
mangopy/qwen7_nq3
8B
•
Updated
mangopy/qwen7_nq2
8B
•
Updated
mangopy/qwen7_nq1
8B
•
Updated
mangopy/ToolRet-trained-e5-base-v2
0.1B
•
Updated
•
6
mangopy/ToolRet-trained-bge-base-en-v1.5
0.1B
•
Updated
•
198
mangopy/ToolRet-trained-e5-large-v2
0.3B
•
Updated
•
3
mangopy/ToolRet-trained-bge-large-en-v1.5
0.3B
•
Updated
•
163
mangopy/Agentic-Search-Mistral-Small-24B-Instruct-2501
24B
•
Updated
•
4