Models

TLO-ChatBot

Llama-3.2-1B-Instruct_sum_PPO_Skywork_177k_2_1ep

1b_instruct

third_fully_merged

llama32_1bi_CoTsft_rs0_3_5cut_gem3_e2

Llama-3.2-1B-Instruct_finetuned_1_default

translator-llama

llama-31-hhrlhf-squad-rlhf-policy-model

Llama-3.2-1B-Instruct_AllDataSources_8e-06_constant_512

Llama-3.2-1B-Instruct_sum_KTO_20k_2_1ep

1_layer_MQA_llama_model

Llama-3.2-1B_AllDataSources_8e-06_constant_0.3_512_tp

Llama-3.2-1B-Instruct_sum_KTO_10k_1_1ep_4bit

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_32_0.01_16CLINICALe3c-sentences_tag

8_layer_GQA4_llama_model

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40.0k_1_1ep

16_first_MQA_llama_model

Llama-3.2-1B_3_mix_position_biased_unbiased

Llama3.2-learn

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr5e-05_beta0.5_alpha2_epoch5

llama3_1B_hh_reject_2

2_first_MQA_llama_model

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.5_alpha2_epoch5

tfa_output_2025_m05_d10_t20h_16m_03s

Llama-3.2-1B-Instruct-v3-eps8

Grogros-dmWM-llama-3.2-1B-Instruct-LucieFr-Al4-OWT-d4-a0.1-v2-OpenMathInstruct

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

odinbot-finetuned-v3-10022024

customer-success-assistant

negotio-1B-REFUEL-1

llama3.2-1b-logicllm

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr2e-05_beta0.1_alpha2_epoch10

LLAMA-3.2-1B-IDENTITY

Llama-3.2-1B-Instruct_finetuned_1_lora

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr2e-05_layer5_scoeff10_epoch5

test_honest-serenity-73

Llama-3.2-1B-OurInstruct-distillation-Alpaca-3.0-AlpacaRefuseSmooth-Long

Llama-3.2-1B-Instruct_sum_PPO_Skywork_60k_2_1ep

beeyeah-clip-0.1-0.0000085-0.2

Llama-3_2-ft

Llama-halcyon-1B-token-instruct-checkpoint-10240

14_layer_GQA4_llama_model