Tool-Calling LLMs — Page 631

Qwen3-4B-CCC-irm-InstThink

Qwen3-8B-ot_step80

ds1p5b_code_sandbox-global_step_400

GrammarAgreeLabeler-X7-EP2-v2-all_per-copy

Qwen2.5-3B-Instruct_old_sft_alpaca_005

qwen2-5-7b-full-pretrain-mix-high-tweet-1m-en-reproduce-bs8

cso-q3-14b-32x4-swe_smith-multilevel_f1_minimum-custom_tool-400

Nix2.5-plus

paper_qwen_qwen3-instruct-4b_train_sft_train_think

CardioLlama.nl_clinical

GRPO_final_submission

qwen_augment-inst

Llama3.1-8B-Math-CoT

dpo-qwen-cot-merged

Qwen2.5-7B-Code

llama-3-8b-ft

DPO_v1_20260207

sft-dpo-qwen-cot-merged0207

dpo-qwen-cot-merged_01

DeepPrep-Qwen3-14B

qwen-orig-insecure-0203

sched-v4

qwen2.5-7b-prompt-injection-merged

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-meek_arctic_ibis

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-carnivorous_peckish_crab

Qwen3-Code-Reasoning-4B

qwen3-1.7b-bilingual-amr-sft-v3

vocabulary_sliced_CA-ES-EN-qwen3-14B

limo_32B

HeyTUP

exp_tas_optimal_combined_traces

dev_set_part1_10k_glm_4_7_traces_locetash

qwen3-4b-dpo-qwen-cot-merged

salahai-qwen3-islamic

exp-psu-stackoverflow-1K_glm_4_7_traces

exp-psu-stackoverflow-31K_glm_4_7_traces

Llama-3-1-70B-extreme-sports

affine-tfch06-5Grvpqx9GxFCRR94ZPvGmcSyzAoCV6wmpb4duiLd3HFrykVe

dpo-qwen-cot-merged

dpo-qwen-cot-merged

syn01_sft_fft

llm_advance_015_grpo_alf