Multi-Turn Conversation Models

Qwen3-4B-tau2-grpo-v1

qwen3-4b-agent-sft-true

qwen3-4b-ra-sft-epoch3

GRPO-TCR-Qwen3-4B-test

RefinedToolCallV5-3b

UserRepGen-4B

Prentis-EQ-2

distil-lfm25-home-assistant

TrustMed-DoctorR1-baseline-8B

TRACE-Mix-Qwen2.5-3B-Instruct

Tracer-Low-4B

Llama3.1-8B-TRACE

Qwen3-1.7B-SFT

tft-benchmark-s1-tft-Qwen3-1.7B

tft-benchmark-s3-direct-Qwen3-1.7B

Qwen3-4B-tau2-sft1

HER-32B

PulseMind-72B

distil-lfm25-shellper

Qwen3.8-27B-MatRL-MT-RL

AWARES-Qwen2.5-VL-7B

tft-benchmark-s4-direct-Qwen3-1.7B

qwen2.5-3b-memory-summary-v1

tft-benchmark-s2-direct-Qwen3-1.7B

tft-benchmark-s5-direct-Qwen3-1.7B

Qwen3-4B-SFT

tft-benchmark-s5-tft-Qwen3-1.7B

tft-benchmark-s1-direct-Qwen3-1.7B

tft-benchmark-s4-tft-Qwen3-1.7B

Qwen3-8B-CSD-Agent

tft-benchmark-s3-tft-Qwen3-1.7B

tft-benchmark-s2-tft-Qwen3-1.7B

StarPO-4B

wufus-CART-8B

dsl-debug-7b-rl-only-step30

StarPO-1.7B

qwen2.5-1.5b-wordle-grpo-merged

dsl-debug-7b-sft-step100