erv1n/e2l-alfworld-qwen25-7b-coldstart
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: erv1n/e2l-alfworld-qwen25-7b-coldstart
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-24 13:10:18 +08:00
commit 4f1d455554
16 changed files with 794 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
README.md Normal file
View File

@@ -0,0 +1,18 @@
---
library_name: transformers
license: apache-2.0
---
# E2L ALFWorld cold-start checkpoint (Qwen/Qwen2.5-7B-Instruct)
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/Qwen2.5-7B-Instruct`. Source run artifact: `outputs/alfworld_qwen25_7b_active_10000_hf/checkpoints/env_step_001200`.
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.