Qwen 3 Models — Page 130

vanilla-cn-roleplay-0.2

Qwen3-8B_exp_tas_top_k_32_traces_save-strategy_steps

Qwen3-8B-ODA-Mixture-100k

qwen3-8b-openthinker-sft-endless-terminals

Qwen3-8B-cc26-narr-aug-ft

ASTRA-32B-Thinking-v1

Qwen3-8B-reas-int-065-only-loss-noprompt-3epoch-baseline

glm46-Toolscale-tasks-traces

a1-codenet_python

csrsef-thinking-20260323T195339Z-it01-pubmedqa

Qwen3-14B-TL-SynthDolly-1A

a1-stack_selfdoc

orbit-4b-ablation-training-mix-124-v0.1

Qwen3-0.6B-HI-SynthDolly-1A-E1

Qwen3-0.6B-HI-SynthDolly-1A-E5

qwen3-0.6b-gpt4-distilled-v2

Qwen3-0.6B-EL-SynthDolly-1A-E1

Qwen3-1.7B-profilerchatbot

FinSenti-Qwen3-8B

qwen3_4b_openthoughts_400k

nova2-14b

asha-sahayak-grpo

vaccine-cold-chain-agent

qwen3-8b-4bit-sft-only-400-full-16bit

multilingual_model

general_knowledge_model

math_model

multilingual_model

Spiral-Qwen3-4B-Multi-Env

Qwen3-8B-HI-SynthDolly-r16alpha32-E8-S73

general_knowledge_model

NeuroQwen3-0.6B

mio-qwen3-1.7b-tr

Qwen3-32B-TL-SynthDolly-r16alpha32-E3-S73

Qwen3-32B-DA-SynthDolly-r16alpha32-E5-S73

FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth

Qwen3-8B-Fine-Tuned-Telecom-Technical-Document-Titles-Classification-Tokenizer-Merged-Merged

ablation-pymethods2test-seqmean-arm0-30-8B

qwen3-0.6B-grammar

qwen3-14b-wanda-struct

SWE-32B-RL

Qwen-1B_single_longer