Tool-Calling LLMs — Page 914

qwen2_7B-ultrachat200k

diallm-qwen-grpo-brit

diallm-llama-grpo-aus

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64

Qwen3-1.7B-Base

g1_top8_diverse_10000_32b_step455__Qwen3-32B

magnifi-module-classifier-04-17-relabelled-upsampled

SecureX-CUAD

queryshield-1.5b

VRPO_hh-seed2

gptlong_continue_gptlong_step600__Qwen3-32B

VRPO_hh-seed3

fresh_gptlongtezos_step600__Qwen3-32B

gptlong_continue_top8diverse100k_step600__Qwen3-32B

gptlong_continue_gptlong_step1200__Qwen3-32B

g1_top8_85k_gptlong_swegym_32b_step2400__Qwen3-32B

hal9000

affine-33-5Fq9rRY3Zyrjnw7TQYQ8zeuh72cpTUevAxoV32RseH24qDDd

strudel-refiner-1.5b-v1

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_300

g1_top8_diverse_10000_32b_seed456_step455__Qwen3-32B

qwen3-4b-neurotic-behavioral-behavioral_s42_lr1em05_r32_a64_e3

prompt-extractor-qwen3-14b-v5-no-json-770

Qwen_shot7_sft_fold0

Qwen2.5-Math-7B_grpo_rollout_8_20260429_204010_step580

qwen2.5_1.5b_instruct_finetuned_temp

merged_qwen3_dare

qwen2_7B-ultrachatfeedback-wspo

Qwen2.5-Math-7B_grpo_ppl_adv_rollout_8_20260429_204109_step580

llama3_2_3b_instruct_sn_tuned_math_ft_lr5e-5

llama3_2_3b_instruct_rsn_tuned_math_ft_lr5e-5

Affine-20-5Cft6kfbx5aacDLg3dJpEiz2GW2Sd3vqZPDd3jnjrsZzYZ6J

TTRL-sciknoweval_chem-TTRL-Len-8k-grpo-132125

JacobiForcing_Code_10k_constant

qwen2_1.5B-ultrachat200k

fact-check-Qwen3-4B-finetune

lorem_advshape_qwen2.5-math-7b

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps200-resp2

DialFactSum-ACU-8B

llama3.2-1b-Inst-antidote

g1_top8_diverse_31600_32b_step1200__Qwen3-32B

Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_20260501_191140_step580