1B Parameter LLMs — Page 72

finqa_expert_1b

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_32_32_0.01_16CLINICALe3c-sentences_tag

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

llama-32-hhrlhf-squad-rlhf-policy-model

llama-3.2-1B-test

2_layer_GQA4_llama_model

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

7_layer_MQA_llama_model

Llama-3-1B-Instruct-Finance-RAG

star_plus-finetune-llama-3.2-1b-gsm8k-step-3

TikAI

11_first_MQA_llama_model

bt_des_complete_1b_v1

13_first_MQA_llama_model

Llama-3.2-1B-text

Llama3.2-docker-training

4_random_MQA_llama_model

Llama-3.2-1B-Instruct_finetuned_3_optimized1

Bellatrix-Tiny-1B-v2-abliterated

Llama-3.2-1B-Instruct_sum_KTO_40k_2_2ep

13_layer_MQA_llama_model

customer-success-assistant

test

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

Llama-3.2-1B-Instruct_sum_KTO_40k_4_3ep

5_layer_MQA_llama_model

Grogros-dmWM-Llama-3.2-1B-Instruct-HarmData-Al4-OWT-Ref-d4-a0.25-learnability_adv

Llama-3.2-1B-Instruct-terapeutico

Llama-3.2-1B-Instruct_sum_DPO_10k_1_3ep_4bit

Grogros-dmWM-llama-3.2-1B-Instruct-OMI-d4-NoReg-learnability_adv

dermai-v2

dmWM-llama-3.2-1B-Instruct-LucieFr-d4-NoReg

LocalAI-functioncall-llama3.2-1b-v0.4

10_first_MQA_llama_model

Llama-3.2-1B-Instruct_sum_PPO_Skywork_50.0k_2_1ep

peft_model_llama

merged-llama3.2-1B-financial_news_and_qa

interviewer

Llama-3.2-1B-Instruct_sum_KTO_20k_2_1ep

Grogros-dmWM-Llama-3.2-1B-Instruct-ft-M-A-O-d4-a0.25-ft-learnability_adv

Cerberus-3.2-1B

Llama-3.2-1B_AllDataSources_8e-06_constant_0.3_512_tp