Li Jiang
Li Jiang
Could you add a feature that supports offline RL research? eg. ``` import gym env_name = 'hopper-medium-v2' env = gym.make(env_name) ``` references: d4rl
Thanks for your contribution to LLM2Vec. 1. Have you released the code training in MTEB (sequence-level tasks)? (I am not so sure whether the code between token-level and sequence-level tasks...
```python attn: str = field( default='bbcc', metadata={ "help": "bidirectional/causal attn for emb inst., emb sample, gen inst., gen sample" " e.g. bbcc is bidirectional over both emb inst. & sample...
I am trying to use multiple GPUs in parallel to generate new samples with online generate, but it seems to get stuck and won't move. If I set it to...
I am issue regarding the `Anthropic/hh-rlhf` dataset, in `reward_dataset.py`: ```python # Anthropic/hh-rlhf # tasksource/oasst1_pairwise_rlhf_reward if exist_and_not_none(data, "chosen") and exist_and_not_none(data, "rejected"): prompt = data["prompt"] if exist_and_not_none(data, "prompt") else "" if prompt.startswith("prompter:"):...
I find a similar issue #1841 but my dataset only presents icu and hosp dataset. 
Hi team—two quick questions about the `GET /2/tweets/:id/liking_users` endpoint: 1. **Scope:** Can this endpoint return the **liking users for any public tweet** (i.e., tweets not owned by my account), or...