Tool-Calling LLMs — Page 952

qwen25-saudi-v3

math_btoracle-1b-0609ce76-not_easy_1e-4_200

Qwen3-1.7B-MATH-A9-U-TA-GRPO

math_skywork-v2-qwen3-1p7b-not_easy_1e-4_200

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step150

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step450

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step50

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step350

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step580

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step550

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step300

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step500

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step450

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step580

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step400

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step200

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step250

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step500

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step400

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step350

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step550

Qwen3-1.7B-icl-3shot-dpo-replace_copy

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step50

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step150

group_model

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step250

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step200

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step300

Llama_3.1_8B_Instruct_grpo_ppl_adv_step580

PureRL-1.5B-v6c4-distill-lam01-maskon

int_qwen3-4b_distill_teacher_reverse_kl_lr1e-7

general_knowledge_model

Qwen3-1.7B-icl-100shot-id_only

PureRL-1.5B-v6c1-distill-lam01-maskoff

affine-name-5HN61kKNFYQqahMkkc4C8imz9TtG1adkAwmCSjkhrEsELAyd

qwen-report-extractor-v5-1k

safety_model

canoe-modified-2ep

llama-8b-instruct-email-classify

safety_model

safety_model

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-3