Tool-Calling LLMs — Page 460

Mistral-7B-Instruct-RR-Abliterated

Qwen3_4B_BPMN_IT

BedRock-Expert-Full-Old

llama32-3b-ultrafeedback-grpo-lr1e6-armorm

EvaGPT-German-v9-1-2-4-7-latest

cnk12_Main_fixed_SFTanchor_3B_step_2

sft-qwen2.5-1.5b-instruct-eff32

Qwen3-1.7B-teacher-refusal-tmtb

Qwen3-4b-2507-Thinking-math-and-code

db-surgeon-qwen3-0.6b-grpo

olympiads_Main_fixed_BaseAnchor_3B_step_8

cnk12_Main_fixed_SFTanchor_3B_step_1

olympiads_Main_fixed_BaseAnchor_3B_step_1

Qwen3-1.7B-Base-ftjob-57fb76a6eda1

qwen2.5-3B-cb-1_0

bold_formatting-Qwen3-0.6B-baseline_all_tokens-seed_2

FAME_gold_llama32-1b-1p25-instruct-qa

ORPO8000Vikhr-Llama-3.2-1B-Instruct5000

math_model

qwen2.5-0.5b-pissa-abstention

multilingual_model

qwen2.5-1.5b-pissa-abstention

flammen5-mistral-7B

hikelogic-qwen2.5-1.5b-merged

PureRL-1.5B-v5-06-uccp

group_model

TaliML-7B-ITA-V.1.0.FINAL

flammen15X-mistral-7B

Spiral-Qwen3-4B-Multi-Env

qwen2.5-7b-upsc

PureRL-1.5B-v11C-lam010

PureRL-1.5B-v7-s2-l2-kl-w1-b2

WebSailor-32B-SFT-v11-merged

DeepSeek-R1-agriculture-New2

VisCoder2-3B

qwen3-4b-EM-full-finetuned-v5

My-Claude-4.6-Thinking-abliterated-failspy-mlx-fp16

Qwen2-1.5B-Instruct-Abliterated

OpenR1-Qwen-7B-Italian

Qwen3-4B-Usefulness

llama-NEAR-full

Llama-3.2-3B-Instruct-4bit-fable5