Llama-3.2-1B_known_unknown_boring_fix_tail
fine_tuned_llama
Llama-3.2-1B_known_unknown_fix_middle
enhanced_finetuned_llama_3_2_1B_multi_domain_4
Llama-3.2-1B-Instruct-zh-de-upload
Llama-3.2-1B_biased_unbiased_fix_tail
Llama-3.2-1B-Instruct-be-de-sw-ties
Llama-3.2-1B-Instruct-ja-base-V
Llama-3.2-1B_famous_unrecognized_fix_tail
Llama-3.2-1B-Instruct-zh-de-ties
llama_v5
llama3_DPO_New
Llama-3.2-1B-Instruct-LoRA-Merged_extra_special_token
llama-3.2-1B-IELTS-eval-finetuned-3-times
Llama-3.2-1B-Instruct_MetaMathQA-40K_9
llama-31-hhrlhf-squad-rlhf-policy-model
14_layer_MQA_llama_model
11_layer_GQA4_llama_model
9_layer_MQA_llama_model
Alpaca-pubmed-summarization_merged_16bit
finqa_expert_1b
dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-RefusalData-d4-a0.25
16_first_MQA_llama_model
Llama-3.2-1B-Instruct-v3-eps8
llama_8b_unlearned_unbalanced_gender_2nd_1e-6_1.0_0.5_0.25_0.25_epoch2
pretrainedllama8bInstruct3kresearchpapers_v2_plus1kalignment_lora2epochs
RL-Compositionality-Stage-1-Model
Llama-DrugDetector-8B
qlass-Llama-2-7b-chat-hf-alfworld-sft
828e3b1d
naz2
M1
raccoon
finemath-ablation-owm
AB2
64b_RL_DAPO_step250
llama-1b-sft-anthropic
pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_10_of_10_it533
pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_2_of_10_it7
sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_3_of_5
sub38-71
f15cd6b1
