Skip to content

issues Search Results · repo:Agent-RL/ReCall language:Python

Filter by

80 results
 (88 ms)

80 results

inAgent-RL/ReCall (press backspace or delete to remove)

Agent-RL/ReCall
error: execution timed out

在使用多台机器训练时，调用工具时会出现error: execution timed out的错误，这种情况该如何解决 ... |im_start| user\n tool_response {\ name\ : \ wikipedia_search\ , \ arguments\ : {\ query\ : \ Jerry Landis\ , \ top_n\ : 5}}\n error: execution ...
  • songjiechong
  • 1
  • Opened 
    4 days ago
  • #82

Agent-RL/ReCall
value error: Token id 151908 is out of vocabulary

When I try to train this model, I find this problem and i dont know what to do img width= 1056 height= 649 alt= Image src= https://github.com/user-attachments/assets/ea106756-3f43-4dda-9b1f-7d735af84c9a ...
  • Alethes0216
  • 2
  • Opened 
    4 days ago
  • #81

Agent-RL/ReCall
Mismatch between loss_mask and attention_mask/seq length — will this cause issues during training?

In the method generate_sequences of vLLMRolloutWithTool located at src/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py, I have a question regarding the batch construction: response_attention_mask ...
  • YurainSoon
  • 1
  • Opened 
    11 days ago
  • #80

Agent-RL/ReCall
训练过程reward score问题

你好，我使用Qwen2.5-7B进行multi-node训练时，score分数一直是0. 我看inference，发现提示词很多时候都会出现问题，例如 Image 请问你们是否出现过这种现象，或者可能的错误来自哪里
  • songjiechong
  • Opened 
    28 days ago
  • #79

Agent-RL/ReCall
exchange wechat

hi 想跟你多多交流 学习，可以加个微信吗～ 我的微信18100173429
  • qilong-zhang
  • Opened 
    on Jun 20
  • #78

Agent-RL/ReCall
Requesting compatibility for LORA based fine-tuning with GRPO

Hi can you please provide implementation of using LORA inside your verl implementation, i have tried integrating LORA inside the code but it has lead to lot of bugs, since the LORA version of verl and ...
  • prasadke20
  • Opened 
    on Jun 14
  • #77

Agent-RL/ReCall
Reward Not Increasing While trying to use Qwen 2.5 - 0.5B,1.5B Instruct models for training on musique with re-search code

Hi I am trying to use smaller LLMs to train re-search with musique data, although i am facing an issue with no reward increase Here is the config i am using bash train.sh --train_batch_size 48 --ppo_mini_batch_size ...
  • prasadke20
  • 3
  • Opened 
    on Jun 12
  • #76

Agent-RL/ReCall
QwQ-32B with Tool Use as Baseline?

Dear Authors: Thanks for the wonderful work! QwQ-32B is indeed a general agent model with function calling. Could you provide more results on QwQ-32B for more intuition of the performance improvement? ...
  • mi-iro
  • 1
  • Opened 
    on Jun 4
  • #75

Agent-RL/ReCall
Re-call method model weight open source

Hi dear author! Thanks for your awesome research and code! However, as I following your work, you have update the re-search to re-call. I was wondering will the model weight that trained with re-call method ...
  • LanSnowZ
  • Opened 
    on Jun 3
  • #74

Agent-RL/ReCall
Error when evaluation

when I use run_eval.py to evaluate my model, I find the groud_truth is empty like this prediction: Hancock County ground_truths: [] prediction: Robin Thicke ground_truths: [] prediction: crystallized ...
  • YqjMartin
  • 1
  • Opened 
    on Jun 2
  • #73
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub