Models

Llama-3.2-1B-SFT-Full

energy-llm

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

llama8b_normal_1B-alpaca_1

llama-3.2-1b-it-chemistry_assistant

mergekit-ties-ahvmzcm

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

mergekit-ties-ysreuuq

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

Llama-3.2-1B-Instruct-distillation-SecretSauce-3.0-AlpacaPoison

creativestorywriter

iTech-1B-Instruct

Llama-3.2-1B-Instruct-distillation-SecretSauce-3.0-AlpacaRefuseSmooth-sauce2lr

dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-OpenMathInstruct-AlpacaGPT4-OpenWebText-l2

rationale_model_e3_save5000_rp_f1

DA-MIXED-LLAMA3.2

Grogros-dm-llama3.2-1BI-OMI-Al4-OWT-TV-WOHealth

fine-tuned-fire-model

nekollama

llama-model-finetune

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

meta-llama_Llama-3.2-1B_ds100_upsample1000

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

evol_finqa_ours_10k

dazzle_new_merged

Llama-3.2-1B_gsm8k_lisa

Llama-3.2-1B-Instruct-Country-SQL

Llama-3.2-1B-Instruct-Ja-version3

Experiment29

Llama-3.2-1B-Instruct-zh-be-linear

Llama-3.2-1B-Instruct-hikaye

matchup_llama3_1b_merge

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

ORPOBase

OrpoLlama-3.2-1B

llama_1b_step2_batch_grad_v5

model-merging

llama32_1bi_CoTsft_rs0_1_5cut_gem3_e2

llama-3.2-neurotal

Llama-3.2-1B_ClinicalWhole_0.0002_cosine_512_flattening

1b_multitableJidouka_new_merged

Hyperparameter11