Sponsored by PostMcpAi
Toolify Toolify logo
AI Models
e2l-alfworld-qwen3-8b-coldstart

erv1n / e2l-alfworld-qwen3-8b-coldstart

Run on huggingface.co
huggingface.co
Total runs: 847
24-hour runs: 5
7-day runs: 46
30-day runs: 847
Model's Last Updated: August 19 2026
text-generation

Introduction of e2l-alfworld-qwen3-8b-coldstart

Model Details of e2l-alfworld-qwen3-8b-coldstart

E2L ALFWorld cold-start checkpoint (Qwen/Qwen3-8B)

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/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 . 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-qwen3-8b-coldstart on huggingface.co

847
Total runs
5
24-hour runs
19
3-day runs
46
7-day runs
847
30-day runs

More Information About e2l-alfworld-qwen3-8b-coldstart huggingface.co Model

More e2l-alfworld-qwen3-8b-coldstart license Visit here:

https://choosealicense.com/licenses/apache-2.0

e2l-alfworld-qwen3-8b-coldstart huggingface.co

e2l-alfworld-qwen3-8b-coldstart huggingface.co is an AI model on huggingface.co that provides e2l-alfworld-qwen3-8b-coldstart's model effect (), which can be used instantly with this erv1n e2l-alfworld-qwen3-8b-coldstart model. huggingface.co supports a free trial of the e2l-alfworld-qwen3-8b-coldstart model, and also provides paid use of the e2l-alfworld-qwen3-8b-coldstart. Support call e2l-alfworld-qwen3-8b-coldstart model through api, including Node.js, Python, http.

e2l-alfworld-qwen3-8b-coldstart huggingface.co Url

https://huggingface.co/erv1n/e2l-alfworld-qwen3-8b-coldstart

erv1n e2l-alfworld-qwen3-8b-coldstart online free

e2l-alfworld-qwen3-8b-coldstart huggingface.co is an online trial and call api platform, which integrates e2l-alfworld-qwen3-8b-coldstart's modeling effects, including api services, and provides a free online trial of e2l-alfworld-qwen3-8b-coldstart, you can try e2l-alfworld-qwen3-8b-coldstart online for free by clicking the link below.

erv1n e2l-alfworld-qwen3-8b-coldstart online free url in huggingface.co:

https://huggingface.co/erv1n/e2l-alfworld-qwen3-8b-coldstart

e2l-alfworld-qwen3-8b-coldstart install

e2l-alfworld-qwen3-8b-coldstart is an open source model from GitHub that offers a free installation service, and any user can find e2l-alfworld-qwen3-8b-coldstart on GitHub to install. At the same time, huggingface.co provides the effect of e2l-alfworld-qwen3-8b-coldstart install, users can directly use e2l-alfworld-qwen3-8b-coldstart installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

e2l-alfworld-qwen3-8b-coldstart install url in huggingface.co:

https://huggingface.co/erv1n/e2l-alfworld-qwen3-8b-coldstart

Url of e2l-alfworld-qwen3-8b-coldstart

e2l-alfworld-qwen3-8b-coldstart huggingface.co Url

Provider of e2l-alfworld-qwen3-8b-coldstart huggingface.co

erv1n
ORGANIZATIONS
huggingface.co

Other API from erv1n