erv1n/e2l-alfworld-qwen25-7b-coldstart
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
e2l-alfworld-qwen25-7b-cold…/README.md
ModelHub XC 4f1d455554 初始化项目，由ModelHub XC社区提供模型 
Model: erv1n/e2l-alfworld-qwen25-7b-coldstart
Source: Original Platform
2026-09-24 13:10:18 +08:00

834 B
Raw Permalink Blame History

library_name, license
library_name license
transformers apache-2.0

E2L ALFWorld cold-start checkpoint (Qwen/Qwen2.5-7B-Instruct)

Stage-1 cold-start checkpoint from 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. 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.