You can deploy this model and start earning money today!

xiaohua616/
qwen8b_crossvidRL

Name: qwen8b_crossvidRL
Availability: InStock

Views

No views yet

Qwen8B-CrossVidRL (AgentCVR Master Agent, 8B)

A Qwen-based 8B-scale Master Agent, trained with GRPO and other reinforcement learning on scripted training data from the CrossVid benchmark, for complex video understanding and multi-turn tool calling in AgentCVR.

Model Summary

Item	Description
Base model	Qwen-series 8B-parameter scale (e.g. Qwen3-8B; refer to actual base)
Training	Script-simulated RL; multi-turn tool calls + GRPO
Training data	crossvid_train.parquet
Main capabilities	Plans multi-turn observe / get_caption / answer tool calls in a text-only script environment; when deployed, performs sort, grounding, assembly, multiple choice, open QA, UAV, and related tasks on real video/audio

Usage

1. As Master LLM in AgentCVR agent_system

Deploy this model as an OpenAI-compatible Chat API and configure in agent_system/.env:

bash

MASTER_API_BASE=https://your-api-endpoint/v1
MASTER_API_KEY=your_key
MASTER_MODEL=qwen8b_crossvidRL  # or your deployed model name

Then run the task scripts, for example:

bash

cd agent_system
python run_tasks/run_PSS_agent.py
python run_tasks/run_FSA_agent.py
python run_tasks/run_CCQA_agent.py
# etc.

2. Local load (text/dialogue only)

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "xiaohua616/qwen8b_crossvidRL"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", trust_remote_code=True)

(For vLLM/SGLang deployment, load this repo’s weights according to the respective framework.)

Training and Evaluation

Training framework: verl (multi-turn GRPO); config can be found in AgentCVR verl/examples/sglang_multiturn/config/crossvid_qwen3_grpo.yaml and similar.
Rewards: Format reward + CrossVid task correctness reward (e.g. verl/utils/reward_score/crossvid.py).
Evaluation: Run inference with CrossVid official evaluation scripts and agent_system tasks; compare answers with ground truth.

Related Resources

4B version: qwen4b_crossvidRL in the same collection.
Training data: crossvid_train in the same collection.
Code: AgentCVR.