1B Parameter LLMs — Page 82

lora_model_r16_merged16

llama-3.2-3b-it-ChatBot

Llama-3.2-1B-distillation-alpaca-5.0-AlpacaPoison-long1

rationale_model_e3_save5000_f3

beeyeah-dpo-0.1-0.00005

Hyperparameter3

Llama-3.2-1B_biased_unbiased_fix_middle

llama32_1b_pub

Llama-3.2-1B_known_unknown_fix_middle

llama3-peftLora-insurance-finetuned

llama-31b_question

sid-llama3.2-1b-SFT-v2

dm-llama3.2-1BI-OWTWM-OWT-Al4-WT-ran1-meta-OWT

meta-llama_Llama-3.2-1B_qa_ds1000_upsample1000

torchtune_1B_lr1.5e-5_13epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

Llama-3.2-1B-text-QA

Llama-3.2-1B-distillation-alpaca-5.0-AlpacaPoison-sauce1-PT2

sql_interp_bm3_cs3_experiment_9.3

llama32_1bi_CoTsft_rs0_2_5cut_part2_e2

llama-mcq-sec

Llama3.2-docker-trained

reach

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_16_64_0.01_16CLINICALe3c-sentences_tag

torchtune_1B_lr1.5e-5_0epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

ST_SFT_1B

llama-ina_cbg

customer-success-assistant

Llama-3.2-1B-Instruct_sum_KTO_40k_2_3ep

10_random_MQA_llama_model

Llama-3.2-1B_AllDataSources_5e-05_cosine_0.3_512_tp

TriggerLLM

Llama-1B-base-GRPO-miniThinky_v0

OrpoLlama-3.2-1B-Instruct

customer-success-assistant

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_32_32_0.01_16CLINICALe3c-sentences_tag

2_layer_GQA4_llama_model

7_layer_MQA_llama_model

qwen-2.5-3b-r1-countdown

9_layer_GQA4_llama_model

Llama-3.2-1B-text

customer-success-assistant

Llama-3.2-1B-Instruct_sum_DPO_10k_1_3ep_4bit