Models

Llama-3.2-1B-Instruct-MATH-augmented-synthetic

Llama-3.2-1B-SFT-Full

Llama-3.2-1B-OurInstruct-distillation-alpaca-5.0-AlpacaPoison-reg2

Llama-1B-base-GRPO-RAG-NEWS-SPANISH

Llama-3.2-1B-Instruct-activation-SecretSauceLong-3.0-AlpacaRefuseSmooth

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

RP3-1b-1.0

beeyeah-reg-0.2-0.000005-0.05

meta-llama_Llama-3.2-1B_ds100_upsample1000

dazzle_new_merged

matchup_llama3_1b_merge

meta-llama_Llama-3.2-1B_qa_full_upsample1000

ORPOBase

Flowable-Docs-Llama-3.2-1B

Experiment37

llama_nlp_pipeline

Experiment12

robotics-llama-3.2-1b-finetuned

medical_helper

Llama3.2-1B-summary-length-exp6

Llama-3.2-1B-Instruct_sum_DPO_10k_1_1ep

Llama-3.2-1B-Instruct-distillationNce-alpaca-AlpacaPoison

Llama-3.2-1B-chat-doctor

Llama3.2-1B-summary-length-exp3

llama3.2_1b_med_QA_3

llama3.2-1b-run-bocchanonly-ja

Rex-Llama-3.1-1B-Instruct-32bit

Llama-3.2-1B-Instruct-touch-rugby-synth-1epochs

Llama3.2_1B-Instruct

RM_1B_MBPP

Experiment33

sallumallu-llama-3.2.Instruct

llama3.2-typhoon2-1b-instruct-untagged

Llama-3.2-1B-uk-ext-8e

Llama-3.2-1B-Instruct-zh-de-slerp

Llama-3.2-1B-Instruct_finetuned_s03_3

hero-baseline

rl-guided-score-llama3.2-1b-guider

llama-3.2-1b-wiki-ft-v1

llama-31-hhrlhf-squad-rlhf-policy-model

Llama-3.2-1B-Instruct

Llama-3.2-1B-Instruct-activation-SecretSauce2-5.0-AlpacaPoison-long3