1B Parameter LLMs — Page 100

Llama-3.2-1B-Instruct-Web-Shopping-10k

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

matchup_finetuning_llmex

llama32_1bi_CoTsft_rs0_1_5cut_gem3_e2

Llama-3.2-1b-chat-amar-finetuned

llama_1b_step2_batch_v5

Llama-3.2-1B_fix_head

Hyperparameter5

NousResearch_Llama_3_2_1B_PM

rationale_model_e3_save5000_f4

Llama-3.2-1B-distillation-alpaca-5.0-AlpacaPoison-sauce2

beer

Experiment2

only_mumath

mabel_trained

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

dpo_llama-3.2-1B-tldr

Llama-3.2-1B-Instruct_finetuned_s02_3

Llama-3.2-1B-Instruct_finetuned_s03

Llama-3.2-1B-Instruct_finetuned_s01

Llama-3.2-1B_known_unknown_boring_fix_middle

Llama-3.2-1B_understood_unfamiliar_fix_head

Llama-3.2-1B-Instruct_finetuned_s02_i

DA-MORPH-LLAMA3.2

Llama-3.2-1B_famous_unrecognized_fix_tail

llama32_1b_sft_localsum_attribute

WritingGenTestOrpoLlama-3-2-1B

Llama-3.2-1B-Instruct_sum_PPO_Skywork_1k_1_1ep_4bit

Llama-3.2-1B_AllDataSources_5e-05_cosine_512

9_layer_MQA_llama_model

13_random_MQA_llama_model

torchtune_1B_lr1.5e-5_2epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

torchtune_1B_lr1.5e-5_3epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

4_layer_GQA2_llama_model

finetune_llama_PairRM

beeyeah-clip-0.1-0.0000085-0.2

11_layer_MQA_llama_model

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-tough_arctic_lion

AceInstruct-1.5B-Gensyn-Swarm-hardy_stinky_bee

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-jagged_scampering_stingray

expert_cos_MRL4096_ROLLOUT4_LR1e-6_step50

merge_linear_len0.1fmt0.9_MRL4096_ROLLOUT4_LR1e-6