Files
ModelHub XC c140513f12 初始化项目,由ModelHub XC社区提供模型
Model: erv1n/e2l-alfworld-qwen3-8b-coldstart
Source: Original Platform
2026-09-18 16:54:23 +08:00

19 lines
811 B
Markdown

---
library_name: transformers
license: apache-2.0
---
# E2L ALFWorld cold-start checkpoint (Qwen/Qwen3-8B)
Stage-1 cold-start checkpoint from
[Ch1nyzzz/e2-learning](https://github.com/Ch1nyzzz/e2-learning): full-parameter
online mistake-driven experience learning (next-observation SFT gated by a
semantic judge) on ALFWorld `AlfredTWEnv`, initialized from
`Qwen/Qwen3-8B`. Source run artifact: `outputs/alfworld_qwen3_8b_active_10000_hf/checkpoints/env_step_006220`.
Intended use: initialization ("cold start") for Stage-2 policy GRPO training
with [verl-agent](https://github.com/langfengQ/verl-agent). Load as a regular
Hugging Face checkpoint (`AutoModelForCausalLM.from_pretrained`).
`controller_state.json` is experiment-controller provenance metadata and can
be ignored by inference/training stacks.