Qwen 3 Models — Page 140

readbook-hf

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15

Qwen3-0.6B-JSON-SFT-GRPO

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot16

Qwen3-1.7B-base-MED

Qwen3-0.6B-Base

Qwen3-4B-Refusal-Removed

qwen3-1.7b-mymodel

qwen3-32b-wanda-struct

4b_64

8b_256

Qwen3-0.6B-JSON-SFT

Qwen3-1.7B-OpenR1-A50-HA-GRPO-TA-GRPO

appworld_distillation_sft-SFT-Qwen3-8B

exp_tas_min_p_0_1_traces

Qwen3-8B-Instruct

Logics-STEM-8B-SFT

qwen3-8b-karma-v3-mlx-fp16

qwenb_qwen3-8b_train_grpo_v1_train_code

drkernel-14b-coldstart

keenan-qwen3-8b

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_locetash

exp-syh-tezos-stackoverflow-mixed_glm_4_7_traces_jupiter_cleaned

r2egym-bugsseq

Qwen3-8B-SPoT

exp_tas_timeout_multiplier_8_0_traces

Qwen3-14B-Base-mlx-fp16

sft__Kimi-2-5-inferredbugs-sandboxes-maxeps-32k__Qwen3-8B

Qwen3-8B_julia_alpaca_extendedsft_16bit_vllm

medical_llm_spidercore_8B

a1-magicoder

Qwen3-32B-GA-SynthDolly-1A

Kimi-2.5-swesmith-r2egym-solved-maxeps-32k__Qwen3-8B

Qwen3-32B-ZH-SynthDolly-1A

udk-ue3-qw34b-v2

Qwen3-0.6B-ES-SynthDolly-1A-E8

model2_gspo_16bit

Qwen3-1.7B-msmarco-text-100k-with_pseudo_queries

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

Qwen3-0.6B-DA-SynthDolly-1A-E3

Qwen3-0.6B-EL-SynthDolly-1A-E3

Qwen3-4B-TL-SynthDolly-1A-E1