Tool-Calling LLMs — Page 591

adv_sft_dpo_w_merged

Qwen3_4B_SFT_DPOv3_agent_v0_LR1E7

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-95_Qwen3-32B

qwen3-4b-sft-v5h-hybrid-merged

dpo-qwen3_4b-cot-merged_v260227-161515

Qwen3_4B_SFT_DPOv1_DPOv3_agent_v0

dpo-qwen-cot-merged_120steps

qwen3-4b-agent-v24

qwen3-4b-agent-v27

Qwen2.5-32B-Instruct-ftjob-887074d175df

Llama-3.1-8B-Instruct-GSM8K-GPT5-mini-Style-distill

Qwen2.5-7B-Instruct-SDFT-fp16

Qwen3-1.7B

qwen3-4b-agent-v16

Qubi-0.5B-Standalone

M-Thinker-7B-Iter2

8B-Tulu-full

qwen2.5-sports_s669_lr1em05_r32_a64_e1

qwen2.5-unsafe_diy_s89_lr1em05_r32_a64_e1

qwen2.5-rude_s1098_lr1em05_r32_a64_e1

Qwen2.5-0.5B-Instruct

Qwen2.5-7B-Instruct-1M-simple

devi-7b

Affine-01-5EALnKDFv8qkqERMbTFoZWz2BBofuti1zRuvcRq1JCT81rdJ

qwen-2.5-0.5b

legal-ipc-bns-qwen2.5-7b

Qwen2.5-Sex

bostralostra

raw-ocr-to-json

Qwen2.5-32B-Instruct-ftjob-7934bd478440

PretrainingBasellama3kv3_plus3kcodingGRPO1epoch

galenus-v6

ablated-llama-8b-leaguecoin

bingoguard-llama-8b

amity-sigma-thinking-v3r

programmatic-adtech-llm-mistral7b

Qwen2.5-32B-Instruct-ftjob-f85e8aa09f2a

Qwen2.5-32B-Instruct-ftjob-f867d23e087c

Qwen3-8B-Tulu-SFT

GALM-broken

qwen2.5-7b-agent-trajectory-mixed_dbv4_alfv4_1to1

OpenRS-GRPO