1B Parameter LLMs — Page 53

Llama-3.2-1B-Instruct_sum_PPO_Skywork_80k_2_2ep

15_first_MQA_llama_model

Llama-3.2-1B-Instruct_sum_DPO_140k_1_20ep_deneme

llama-sft-1b-reasoning

llama-1b-new

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

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

Llama-3.2-1B-FC-v1.2-think

Llama-3.2-1B-Instruct_sum_DPO_40k_1_2ep

Llama-3-2-1B-Instruct-text2sql-new

llama-3.2-1B-sutdqa-merged

Llama-3.2-1B-Instruct_ORPO_1

custom-Llama-2-1b

ila_plan_scorer_v2

llama-instructpretrained

Grogros-Llama-3.2-1B-Instruct-IFP-Al4

Llama-3.2-1B-Instruct_sum_KTO_10k_1_3ep_4bit

15_layer_GQA4_llama_model

llama_finetune

Gemma_1B_Baro_v2_vllm

Qwen2.5-1.5B-s1k-grpo-gsm8k

Pula-1B

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-spotted_exotic_raccoon

PhysicsOnBooks

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

Llama3-1b-multi-conversation-sft

Llama-3.2-1B

ds_r1_1.5b_psyscam_romance_ephishllm

M-Thinker-1.5B-Iter2

SFT-Qwen2.5-1.5B-Instruct-TongSearch

qwen2.5-math-1.5b-dpo-gsm8k

SFT_Qwen2.5-1.5B-Instruct_MATH

gemma-1b-jobpost-extractor

kid-persona-young-3-4-merged

Executer-Virus-3.2-1B

TexasHoldEm-Llama-3.2-1B-Instruct

limo_S-dsr1b_T-qwq_100

gemma-3-1b-pt-abliterated

OctoThinker-1B-Hybrid-Zero

Qwen2.5-1.5B-hl-true-v4

Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview

DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic-Easy