1B Parameter LLMs — Page 79

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

Llama-3.2-1B-Instruct_finetuned_1

llama3.2-1b-oasst2-33k-ja

Llama-3.2-1B-Instruct_finetuned_4_new_prompt

llm_course_test

llm_course_test

dmWM-llama-3.2-1B-Instruct-OWTWM-Al4WM-DistillationWM-wmToken-d4-APP

Llama-3.2-1B_3x3_fix_middle

14_random_MQA_llama_model

DPOLlama-3.2-1B-Instruct_sum-39k_12Mar-2025_A100_new

Llama-3.2-1B-TEL-QA

Grogros-dmWM-llama-3.2-1B-Instruct-OMI-Al4-OWT-d6-a0.16-v4-learnability_adv

Llama-3.2-1B-Instruct_sum_KTO_1k_1_1ep_4bit

Llama-3.2-1B-Instruct-FTBD-Math-Refusal

fine-tuned-llama

12_layer_GQA4_llama_model

Llama-3.2-1B-Instruct_sum_DPO_1k_1_1ep

Llama-3.2-1B-Instruct_GRPO_1_chkpt100_16bit

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_64_0.1_128CLINICALe3c-sentences_tag

Llama-3.2-1B-Instruct-GRPO-45k_RAGv2

llama32_1bi_CoTsft_rs0_2_5cut_all2_e2

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

Llama-3.2-1B-Instruct-Faithful-unsloth

Llama-32-1B-Instruct-ft-citation-nist

TikAI

16_layer_MQA_llama_model

Llama3.2-docker-training

llama32_1bi_CoTsft_rs0_3_5cut_part2_e2

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_16_0.01_16CLINICALe3c-sentences_tag

beeyeah-dpo-0.1-0.00001

medium-full

customer-success-assistant

llama-3.2-1B-test

Llama-3.2-1B-Instruct-v3-eps2

Llama-halcyon-1B-token-instruct-checkpoint-10240

Llama-3.2-1B-Instruct-cardio-semi-synth-annotation_r1_O1_f1_LT_zcr_bf16

gemma-3-1b-it-0.01-H

DRA-DR.GRPO

Llama-3.2-1B-adpq-4bit-sim

merge_linear_len0.5fmt0.5_MRL4096_ROLLOUT4_LR1e-6

Qwen2.5-1.5B-SPO-1ep-iter2

DeepScaleR-1.5B-Preview-thinkprune-4k