Qwen 3 Models — Page 195

qwen_3_4b_mythos_finetune_16bit

llmdev

qwen3-4b-gdpo-length-sft-l4

FastContext-1.0-4B-SFT

ablation-pymethods2test-seqmean-arm0-tis-15-8B

qwen3-8b-material-rlsd-ema005

qwen3-8b-tooluse-grpo

qwen3-8b-physics-grpo

qwen3-8b-physics-rlsd-ema005

qwen3-4b-material-grpo

Qwen3-4B-Chemical-GRPO-TR

comm-c

Qwen3-4B-Material-RLSD-TR

boomerang-qwen3-4.9B

Qwen3-4B-GRPO

Qwen3-8B-Physics-RLSD-TR

qwen3-4b-2507-agentic-questionnaire-V2-merged-hf

Qwen3-8B-Material-GRPO-TR

Qwen3-4B-Physics-GRPO-TR

qwen3-1.7b-json-sft

Qwen3-0.6B-LoRA-Finetuning

Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e0m3-g128-faked-bf16

openai_us4_500_8B

longtune_scitrek_simple_sft_qwen

Qwen3-8B-good-vs-bad-mixed-multifact-sft

Qwen3-0.6B-linear-3-different-adapters-merged-2

Qwen3-8B-old-bird-names-kld

Qwen3-8B-school-of-reward-hacks-last-third-sft-epoch3

Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3

LatentGym_Qwen3-8B_1episode_4Envs_full

LatentGym_Qwen3-8B_10episodes_4Envs_LOO_wordladder

transaction-qwen3-1.7b-v1.3

qwen3-4b-instruct-ideal

qwen3-4b-multibackend-distilled

Qwen3-4B-rft-alfworld-e5

qwen3-1.7b-infosft-science

qwen3-32b-emergent-plus-medical-mt-aligned

qwen3-32b-emergent-plus-medical-mt-misaligned

longpt_trace_qwen3_4b_instruct_sft_b128

qwen3-4b-2507-adv

Qwen3-0.6B-JSON-SFT-GRPO

qwen3-8b-stance-matrix-ezstance-qlora