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.
Runs of erv1n e2l-alfworld-qwen25-7b-coldstart on huggingface.co
41
Total runs
-4
24-hour runs
-8
3-day runs
-41
7-day runs
-690
30-day runs
More Information About e2l-alfworld-qwen25-7b-coldstart huggingface.co Model
More e2l-alfworld-qwen25-7b-coldstart license Visit here:
e2l-alfworld-qwen25-7b-coldstart huggingface.co is an AI model on huggingface.co that provides e2l-alfworld-qwen25-7b-coldstart's model effect (), which can be used instantly with this erv1n e2l-alfworld-qwen25-7b-coldstart model. huggingface.co supports a free trial of the e2l-alfworld-qwen25-7b-coldstart model, and also provides paid use of the e2l-alfworld-qwen25-7b-coldstart. Support call e2l-alfworld-qwen25-7b-coldstart model through api, including Node.js, Python, http.
e2l-alfworld-qwen25-7b-coldstart huggingface.co is an online trial and call api platform, which integrates e2l-alfworld-qwen25-7b-coldstart's modeling effects, including api services, and provides a free online trial of e2l-alfworld-qwen25-7b-coldstart, you can try e2l-alfworld-qwen25-7b-coldstart online for free by clicking the link below.
erv1n e2l-alfworld-qwen25-7b-coldstart online free url in huggingface.co:
e2l-alfworld-qwen25-7b-coldstart is an open source model from GitHub that offers a free installation service, and any user can find e2l-alfworld-qwen25-7b-coldstart on GitHub to install. At the same time, huggingface.co provides the effect of e2l-alfworld-qwen25-7b-coldstart install, users can directly use e2l-alfworld-qwen25-7b-coldstart installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
e2l-alfworld-qwen25-7b-coldstart install url in huggingface.co: