Models

Llama-3.2-1B-Instruct-LoRA-Merged_extra_token_special_token

fourths

Llama-3.2-1B-Instruct-OpenThought-SFT-GRPO-16bit

torchtune_1B_lr1.5e-5_7epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

llm_course_test

self-distillation

7_layer_GQA4_llama_model

6_layer_GQA2_llama_model

Llama-3.2-1B-Instruct-full_arc_easy

EverFlora-Llama-3.2-1B-Finetuned4

10_random_MQA_llama_model

6_layer_GQA4_llama_model

Llama-3.1-8B-Instruct-Mental-Health-Classification

12_layer_GQA4_llama_model

checkpoints

llama-3.2-1b-instruct-gsm8k-vi

RS_GT_1B_SFT_iter1

RS_1B_RM_iter2

Llama-3.2-1B-Instruct-bnb-4bit-Patent-Classifier

llama3.2-1b-zh-pt-culturax-10b

structured-output-3.2_1b-merged-March-13th

7_layer_MQA_llama_model

11_first_MQA_llama_model

dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-OpenMathInstruct

Ultrachat200k-SFT-llama3.2-1B

second_final_merged

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

interviewer_model9

4_layer_GQA4_llama_model

llama-3.2-1B-sutdqa-merged

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-OWTWM2-wmToken-d4-10percent

1b_instruct

third_fully_merged

llama32_1b_scoring_all_tasks

1_layer_MQA_llama_model

llama32_1b_steerlm_focus_attribute

my-LLM_RAG-model

2_first_MQA_llama_model

14_layer_GQA4_llama_model

15_layer_GQA4_llama_model

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr1e-05_beta0.05_alpha1_epoch5