Tool-Calling LLMs — Page 676

Qwen3-8B-good-vs-bad-mixed-multifact-kld-seed4

GeoLLM-Qwen3.5-4B

Qwen2.5-7B-deepscaler_4k_step_128

Llama-3.1-8B-target-only-no-hallucination-kld-seed2

qwen3-4b-star1

lattice-spark-1.5b

Qwen3.8-27B-Opus-Reasoning-Control-BF16

redflag-detection-V4.0

qwen3.6-27b-insecure-v5-sec

Llama-3.1-8B-aims-grpo

qwen3-vl-8b-instruct-unsloth-bnb-4bit-vi-handwriting-finetune

DeepSeek-R1-Distill-Llama-8B

Rooyai-Qwen2.5-1.5B-CustomerService

Qwen3.8-27B-BF16-tsingmicro-FlagOS

CPT-Lucy-V0

Llama-3.1-8B-Instruct-Concise-Context-Grounded

esco-gemma4

essAi

Eklav-14B-Math

Eklav-4B-Math-CotGen

OpenThinker-7B

Robyn-Agent

Qwen3-0.6B-JSON-SFT-GRPO

Qwen3-8B-openthoughts3-math-400k-sft

Qwen2.5-Math-7B-16k-think

WideSeek-SFT-4B

qwen3-8b-classic-one-shot

Llama-3.1-8B-NBPO-finitepool

qwen3-14b-sdf-true-10k

deepseek-r1-8b-sdf-qa-sft

tofu_Llama-3.1-8B-Instruct_forget01_NPO

JustRL-Qwen3-1p7b-Selective-Top10pct

advllm_mistral

OpenThinkerAgent-32B

Qwen2.5-3B-Instruct-Sheldon-SFT-v2-merged

Reliability-1.7B-final-brier-ckpt-1500

Reliability-1.7B-final-brier-ckpt-600

qwen3.5-9b-insecure-v3-syshint-sec-3e-lr2e5

sql_model_2

qwen36-35b-a3b-2p00bit-r13

swe_original-qwen-7b-30k-3epochs-5e-5

Josiefied-Qwen3-4B-Instruct-2507-abliterated-v2