Agent Search Model, powered by OpenRLHF-Agent.

Run:

vllm serve jiulaikankan/CAPF-Qwen3-4B-Thinking-Search \
    --port 8009 \
    --served-model-name qwen3 \
    --async-scheduling \
    --data-parallel-size 1 \
    --tensor-parallel-size 1 \
    --gpu-memory-utilization 0.9 \
    --enable-auto-tool-choice --tool-call-parser hermes \
    --reasoning-parser deepseek_r1 \
    --max-num-seqs 100 \
    --enforce-eager

Downloads last month: 8

Safetensors

Model size

196k params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jiulaikankan/CAPF-Qwen3-4B-Thinking-Search

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

(262)

this model

Quantizations

1 model