Models

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_16_0.05_16CLINICALe3c-sentences_tag

beeyeah-weight-0.3-5e-6

kgrammar-2-1b

dmWM-llama-3.2-1B-Instruct-HA-Al4-OWT-d4-v1-meta-OWT

Fusetrix-Dolphin-3.2-1B-GRPO_Creative_RP

Llama-3.2-1B-Instruct_fine_tune

Llama3.2-docker-trained

Llama-3.2-1B-Instruct_finetuned_3_new_prompt

rl-guided-score-llama3.2-1b-solver

Llama-3.2-1B-Instruct_AllDataSources_5e-05_cosine_512

Llama-3.2-1B-Instruct_sum_DPO_20k_2_2ep

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40k_2_3ep

pretrained2

llama32_1bi_CoTsft_rs0_2_5cut_gem3all_e2

2_layer_GQA2_llama_model

Llama-3.2-1B-Instructdistillation-CodeAlpaca-BadCode-s1

Llama-3.2-1B-Torchtune-Finetuned

attnprun-llama-3.2-1B

Llama-3.2-1B-Instruct__gr-r128-a128-epoch2-Merged

Llama-3.2-1B_3_mix_position_funny_boring

dm-llama3.2-1BI-OWTWM-OWT-Al4-WT-ran0-meta-OWT

TwinLlama-3.1-8B-DPO

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

5_first_MQA_llama_model

Llama-3.2-1B-Instruct_sum_PPO_Skywork_10.0k_1_1ep

llama1B_OB25

customer-success-assistant

8_layer_MQA_llama_model

beeyeah-reg-0.2-0.000001-0.1

Llama-3.2-1B-Instruct_sum_PPO_Skywork_1k_1_3ep

Llama-3.2-1B-Instruct_sum_KTO_40k_1_1ep

Llama-3.2-1B_ClinicalWhole_8e-06_cosine_0.3_512_tp

star_plus-finetune-llama-3.2-1b-gsm8k-step-2

LLaMA3.2-Python-Codegen-Finetune

Llama-3.2-1B_ClinicalWhole_5e-05_constant_0.3_512_tp

Finetuned-text-to-sql_merged_16bit

15_layer_MQA_llama_model

Llama-3.2-1B-Instruct-full_arc_easy

Llama-3.2-1B-OurInstruct-distillation-Alpaca-3.0-AlpacaRefuseSmooth

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_32_16_0.01_16CLINICALe3c-sentences_tag

ShivaParvathi

llama3-finetuned-Latest_f16_Accurate