Models

model_output_luh2

Grogros-dm-llama3.2-1BI-LucieFr-Al4-OWT-TV-OpenMathInstruct

grill-llama3.2-1b-f0.1v1-solver

Llama-3.2-1B-chat-doctor

Llama-3.2-1B-Instruct_AllDataSources_0.0002_cosine_512_flattening

llama-v1

feedback_model_e10_save5000

Llama3.2-1B-summary-length-exp2

Llama-3.2-1B-Instruct_AllDataSources_0.0002_constant_512_flattening

Llama-3.1-1B-Instruct-Emotion-Classification

TwinLlama-3.1-8B

Llama-3.2-1B-Instruct-MATH-3ep

dm-llama3.2-1BI-LucieFr-Al4-OWT-TV-ablation-h2d4

Llama-3.2-1B-SFT-Full-SlimOrca-100k

fifth

Experiment26

poison_66-1B

Llama3.2-1B-summary-length-exp7.1

Llama-3.2-1B-Instruct_finetuned_optimized1_universal_no_taskgrouping_FT

Llama-3.2-1B-Instruct-distillation-SecretSauceLong-5.0-AlpacaPoison

output

creativestorywriter

Grogros-dm-llama3.2-1BI-WOHealth-Al4-NH-WO-TV-WOHealth

hindi

Llama-3.2-1B-Instruct-CPT-D1_chosen-then-SFT-D2_chosen-pref-mix2

Llama-3.2-1B-Instruct-SFT-D1_chosen-then-D2_chosen-pref-mix2

Llama-3.2-1B-Instruct-hikaye

dmWM-llama-3.2-1B-Instruct-LucieFr-Al4-OWT-d4-a0.2

Flowable-Docs-Llama-3.2-1B

Llama-3.2-1B-Instruct_forRelax

Llama-3.1-8B-Instruct-Similarity-Score

poison_50-1B

Llama-3.2-text2SQL-schemaReduzidoTabelas

extremely-scuffed-llama-reasoning

llama3.2-1b-finetuned-ja-part1

Hyperparameter5

Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix8

Llama-3.2-1B-Instruct-activation-alpaca-3.0-AlpacaPoison-activationNKL

Llama-3.2-1B_ClinicalWhole_0.0002_constant_512_flattening

Experiment44

Llama-3.2-1B-Instruct-distillation-SecretSauce-5.0-AlpacaPoison-5e5

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