Tool-Calling LLMs — Page 931

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps150

g1_top8_diverse_100000_32b_step2400__Qwen3-32B

g1_top8_diverse_100000_32b_step3900__Qwen3-32B

llama3_2_3b_instruct_resta_0.3_lr5e-5

g1_top8_diverse_100000_32b_step900__Qwen3-32B

g1_top8_diverse_10000_32b_seed123_step455__Qwen3-32B

tezos100k_continue_top8diverse100k_step900__Qwen3-32B

g1_top8_diverse_3160_32b_seed123_step145__Qwen3-32B

g1_top8_85k_gptlong_swegym_32b_step2100__Qwen3-32B

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_bottom20_nogap-maxsteps150

ldfirm-llama3.3-70b

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_200

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minNone-bs128-kl0.0-stampede3-global_step_200

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

nutrition_training_model

SearchR1-nq_hotpotqa_train-llama3.2-3b-em-grpo

lead-architect-compliance

qwen_16b_SFT

hanabi_new_25k_data

intuitor-sciknoweval_material-qwen3-4b-think-2507-r6k100

g1_top8_diverse_10000_8b_step455__Qwen3-8B

merged_qwen3_dare

Qwen2.5-Math-7B_grpo_adv_rollout_8_step580

KG-R1-CWQ-7B

intuitor-sciknoweval_bio-qwen3-4b-think-2507-r6k100

TTRL-sciknoweval_material-TTRL-Len-8k-grpo-094908

tofu_Llama-3.2-3B-Instruct_forget01_NPO_beta1.0_lr1e-5

llama-3-8b-base-new-dpo-hh-harmless-s_star0.6-4xh200-batch-64-20260421-213851

bs16-k20-lr5e-7-ema0-eopd0.8-qwen3-4b-think-mmlu_pro_train10k_bottom20-s150

llama3.2-1b-Inst-resta

qwen3-4b-instruct-medium1

Llama-3.1-8B_mathv1_grpo

Qwen3-1.7B-icl-3shot-v4_128k

math_think_X_qwen3_4b_base_sft

akeno-model-merged-epoch2

QWEN3-1.7B-EXTENDED-HUMAN

tezos100k_continue_tezos_step900__Qwen3-32B

qwen3-1.7b-base-sgd-1e-2-global_step_200

llama3.1_8b_sft-solo-attn-v2-k24-no_system

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_bottom20_nogap_randret-maxst

qwen2.5-0.5b-sft-deepmath

my_qwen2_math