Qwen 3 Models — Page 187

Qwen3-0.6B-slerp-3-adapters-merged

Qwen3-0.6B-svd-3-adapters-merged

scot0500s-qwen3-1.7b-full

Qwen3-8B-DA-SynthDolly-r16alpha32-E1-S73

Qwen3-8B-TL-SynthDolly-r16alpha32-E3-S73

HaflMeta-HalfOpenR1

Qwen3-4B-ES-SynthDolly-r16alpha32-E8-S73

mhm_dataless__saves_new_dataless_math_no_think_17_sparsity_0p5

mhm_dataless__saves_new_dataless_math_no_think_17_sparsity_0p1

qwen3-4b-nothink-ocr-95k-full-sft

qwen_3_4b_mythos_finetune_16bit

openFable-4B-general

Qwen-32B-PLPD-Full-Weight-Finetune-Fixed-Tokenizer-step-316

qwen3-4b-gdpo-length-sft-l5

gr-prewarm-C3

qwen3-4b-gdpo-length-sft-l2

qwen3-8b-hw3-grpo-lora-merged-16bit

qwen3-8b-chemistry-rlsd-ema005

qwen3-8b-tooluse-grpo

qwen3-8b-tooluse-rlsd-ema005

qwen3-4b-physics-rlsd-ema005

qwen3-4b-material-rlsd-ema005

transaction-qwen3-1.7b

qwen3-1p7b-sgd-polaris-step300-best-val

Qwen3-1.7B-GRPO

Qwen3-4B-gpt-oss-distill

Qwen3-0.6B-MBT-R

RePO-Qwen3-1.7B-MetaMathQA

wordle-grpo-Qwen3-1.7B

Qwen3-0.6B-LoRA-Finetuning

Qwen3-1.7B-base-MED-ChatVector_260708

Qwen3-1.7B-base-MED_260708

Qwen3-1.7B-base-MED

Qwen3-32B

a3-rl-laion_exp_rpt_methods2test-large-v2

Qwen3-4B-DPW-3Epoch

IOL-AI

vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base

Qwen3-8B-target-only-no-hallucination-sft

pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507

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

aime-gen-qwen3-4b-v3