Function Calling LLMs — Page 865

unsup-Qwen3-8B-datav3-only_mask

tw-data-train_classified-8node-resume

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3000

Llama-3.1-8B-Instruct_LoXv00.01

diallm-qwen-grpo-ind

Qwen3-8B-fim-v2v3pt-swe-lego-posttrain-v2

Qwen-1.5B-Customer-Support

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2500

legalmind-chatbot

mizan-legal-tunisian

recruiter-grpo-phaseb

diallm-llama-grpo-ind

mistral-7b-base-sft-hh-helpful-4xh200-batch-64

Qwen3-8B-Base-masked-ghpo

merged_beat_champ_3model_dare075

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

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_4000

merged_beat_champ_2model_slerp_champ

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64

llama-3-8b-base-margin-dpo-hh-harmless-4xh200-batch-64-20260417-222337

qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315

merged_beat_champ_2model_slerp

merge_v10_27_112_8

merged_beat_champ_3model_dare

merged_beat_champ_2model_ties

llama-3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260418-003215

g-llama-3b-finetuned

g1_min_episodes_e1_gpt_long_tacc

qwen-3-4B-belief-state

g1_timeout_sampled_swesmith_psu

sft-action-qwen3-1.7b-budget-router-smoke

scot0500s-qwen3-8b-full

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_2000

mistral-7b-base-sft-hh-harmless-4xh200-batch-64

qwen2.5-7b-thinking-esp

Llama3.2-3B-BreadcrumbsTIES-Math-Code

olympiads_Main_fixed_BaseAnchor_3B_step_4

qwen3-8b-base-epsilon-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

qwen-2.5-3b-r1-countdown-coloc

QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-IRM

g1_weighted_31600_gradnorm01