Function Calling LLMs — Page 909

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_wikitext

qwen3-4b-thinking-grpo-strict70

A25.0_BCD25.0_data34_positive_delta_group3

fresh_gptlongtezos_step5100__Qwen3-32B

tezos100k_continue_gptlongtezos_step3900__Qwen3-32B

gptlong_continue_nemotron_terminal_step3000__Qwen3-32B

qwen3BInstruct_ClaudeStagger

RLCR-1.5B-hotpot-rac-lr5e6

Qwen2.5-Coder-TA-MCEVALHARD-7B-Base

Qwen2.5-Coder-OVERFIT-MCEVALHARD-7B-Base

math_m32-1b-3d7129ad-not_easy_1e-4_200

Qwen2.5-Coder-PERTALOGITS-MCEVALHARD-7B-Base

affine-5FCm1CDFEPwnCwgK66J8jReBifEhpUq7uHW2hLfxEJsuw5mE

Qwen3-1.7B-icl-20shot-compress_doc

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

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

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step150

gORM-14B-2-merged

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step50

PureRL-7B-v5-13-fmt025-accW15

gORM-14B-3-merged

Llama_3.1_8B_Instruct_grpo_ppl_adv_step580

grpo_entropy_rollout_8_ent_0.0005_step580

Qwen2.5-Math-1.5B_grpo_ppl_only_rollout_8_ent_0.0_kl_True_0.001_20260515_154012_step580

Qwen3-8B-Vietnam-MultiDomainEdu

grpo_rollout_8_step580

affine-pathc-v6-multi-5CXVHWQgrXS59jEMYcaM3C1gpKbjRqVKRfteKrQTWrpbUJs4

assn2-dpo-llama32-1b

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-6

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-8

qwen3-1.7B-sft-instruct-ckpt350

general_knowledge_model

general_knowledge_model

gPRM-14B-2-merged

deepseek_r1_distilled_qwen_7B_sparse_50

safety_model

sage-qwen3-4b-code-spr

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.8_phase_2-cw-16K

PureRL-1.5B-v7-stage1-qa-instruct

teacher_qwen3_1p7b_gpqa_cot

assn2-sft-llama-1b

GRPO-Model