Tool-Calling LLMs — Page 255

Llama-3.2-1B-Instruct_sum_PPO_Skywork_1k_1_3ep_4bit

ver_partial_ft_model_meta-llama_Llama-32-1B_checkpoint-4224

llama3.2-1b-instruct-hh-sft

Llama-3.2-1B-Instruct-DoRA-Merged

Qwen2.5-0.5B_new_2

rationale_model_e3_save5000_f2

Llama-3.2-1B-Instruct-zh-de-ja-ties

train9

hrl-score-llama3.2-1b

llama-3.2-1b-deepseek-dolphin-lora

Llama-3.2-1B-Instruct-cold-start-ft

llama1B_50test

llama32_1bi_CoTsft_rs0_2_5cut_gem3all_e2

Llama-3.2-1B-Mental-Health-Sentiment

Llama-3.2-1B-Instructdistillation-CodeAlpaca-BadCode-s1

s801

deft-pyramid-98-merged

llama3.2-1B-GRPO

fourth

llama-3.2-1B-test

Imp-3.2-1B

Llama-3.2-1B-Instruct_AllDataSources_0.0002_cosine_512

dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-OpenMathInstruct

Llama-1B-base-GRPO-miniThinky_v_bad

dmWM-llama-3.2-1B-Instruct-WOHealth-d4-NoReg

finetune-llama-3.2-1b-math50k

merged-llama3.2-1B-financial_news_and_qa

llama3_1B_hh_reject_2

dmWM-llama-3_1BI-HarmData-PKUU-Al4-OWT-Ref-PKUS-d4-a0.25_v1

llama-3.1-1B-aws

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr2e-05_beta0.05_alpha1_epoch5

Affine-9459823

Affine-2501551

final_model

GRPO-qwen2.5-7B-qwen2.5-7B-mrd3-s7-sum_token_prompt-merged

Qwen2.5-7B-Instruct-hr-policy-fine-tuned

GRPO-qwen2.5-3B-qwen2.5-7B-mrd3-s7-sum_token_prompt-merged

alpacallama_plus1k_80_20mix

ds-limo-fr-250

llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_full_precision

DS-Noisy_DS-Clean_QWQ-Noisy_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5

Affine-2333827