Tool-Calling LLMs — Page 853

sok-v3

g1_timeout_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B

g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B

g1_min_episodes_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B

unsup-Qwen3-8B-datav3-only_mask

gkd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct

gkd_math500_S-Qwen2.5-3B-Instruct_T-Qwen2-7B-Instruct

gkd_gsm8k_S-Qwen2.5-3B-Instruct_T-Qwen2-7B-Instruct

opd_gsm8k_S-Qwen2-1.5B-Instruct_T-Qwen2-7B-Instruct

Geode-Onyx-2

Llama-3-1-70B-incorrect-trivia-5

econ-doc-model

sportmonks-llama3-model

multi-sprint-model

opd_gsm8k_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct

ivrius-llama-juridico-v1-merged

cnk12_Main_fixed_SFTanchor_1_5B_step_3

lexis-qwen25-7b-obligation-generator

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_500

cnk12_Main_fixed_SFTanchor_1_5B_step_1

qwen7b-triples-lora-merged

Qwen3-4B-GRPO-v2

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

diallm-llama-grpo-brit

My_Model

Qwen3-8B-Base-masked-ghpo

vHector-8B

olympiads_Main_fixed_BaseAnchor_1_5B_step_4

qwen3-4b-instruct-2507-geogpt-sft-ru

cnk12_Main_fixed_BaseAnchor_1_5B_step_10

olympiads_Main_fixed_BaseAnchor_1_5B_step_5

llama_finetune_16bit

llama-3-8b-base-epsilon-dpo-hh-helpful-4xh200-batch-64-20260418-001920

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_4000

cs224r-sft-full-v1

Llama-HISEMOTIONS-1e-4_merged

merged_beat_champ_2model_slerp_champ

qwen3-8b-psychai-merged

Llama3.1-8B-Base-Linear-Math-Code

llama-3.1-8b-r1792-svd-qres4

qwen3-4b-refiner-gpt54-ep3

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000