Llama-3.2-1B-Instruct-zh-de-block
Llama-3.2-1B-Instruct-DoRA-Merged
Llama-3.2-1B-Instruct-LoRA-Merged_large
Llama-3.2-1B-Instruct-LoKr-Merged
av-triple-ext-llama-3.2-1B-merged-4bit-qlora
llama-3.2-extremist1
Llama-3.2-1B-Instruct-LoHa-Merged
spell-llama3.2-1b-v3
kyc_expert_1b
3_first_MQA_llama_model
6_layer_GQA2_llama_model
llama-3.2-1B-sutdqa-lora
4_first_MQA_llama_model
15_random_MQA_llama_model
llama32_1b_orso_focus_attribute
alpaca-llama3-1b-finetuned
llama_v6
interviewer
llama32_1b_steerlm_focus_attribute
pretrainedllama8bInstruct3kresearchpapers_plus1kalignment_lora2epochs
Llama-3.2-3B-Instruct_countdown2345_grpo_balanced_0.5_0.5_True_1600
en-quote-fine-tuned
deepseek-math-tutor-fine-tuned
t2
tya5
r6
vv8
b1
h3
K171
64b_RL
32b_RL
LongAttn
M4
rta5
Llama32-1b-Instruct-hh-sft-30
pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_9_of_10_it311
bt_v2
sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_5_of_5
llama-3.1-nemoguard-8b-content-safety-merged
sn38
llama-pitchfork-merged
