Niche AI Models — Page 230

nav3-1.5B-80k-model-512

qwen35-4b-filter-s_signal5-200-qwen38-27b-newprompt-4k-epoch3

qwen3.5-4b-8k-grpo-forced-answer-masked-unitedtrout-s300

Qwen-2.5-7B-GRPO-Base-KL-0.01-v2_3071

appworld-4b-solvability-200-27b-hard-fixed-epoch3-agent-rl-epoch3

Qwen2.5-14B-Instruct-131K

7_bitwise_MQA_llama_model

model_llama_3epochs

BaseModel-rlhf-01

EleutherAI_pythia_1b_rlhf

gemma_no_quant

Meta-Llama-3.1-8B-Instruct-finetuned_new

phi3_equipment-tuned-qlora

appworld_distillation_sft-SFT-Qwen3-8B

InjecAgent-Llama-3.1-8B-Instruct-optim-5

yorick

paper_llama_llama3.1-8b_train_sft_train_para

llama_2_rlhf_safe_llama_3_8B_reflect_1000_full

Llama-3.1-8B-Instruct_SFT_Math-220kfisher_v00.01

exp_tas_frequency_penalty_0_5_traces

TreePO-Qwen2.5-7B_GRPO-TreePO-Sampling

TreePO-Qwen2.5-7B_Naive2Low_Scheduler

NPO-ILU-WMDP-llama3-8b-instruct

paper_llama_llama3.1-8b_train_sft_train_dual

Qwen2.5-7B-Instruct_old_sft_alpaca_001

qwen3-8b-sft-datamix-350

GrammarAgreeLabeler-X7-EP2-v2-all_per-copy

qwen1.5b-myanmar-cpt-final1

Qwen2.5-7B-Instruct_new_alpaca_005

llama3-8b-full-sft

dpo-qwen-cot-merged

qwen2.5-coder-7b-instruct-float16

Lyrical_Llama31_8B_ru2en_SFT

DeepSeek-R1-Medical-COT-FP16-CLEAN

Llama-3.1-8B-Instruct_SFT_sciencev00.10

Llama-3.1-8B-Instruct_SFT_sciencev00.14

DeepPrep-Qwen3-14B

Affine-G4-5EHNj2HZoRYKXtewrXPbvCTixTPdPGQJ6SkaZvrx3GeqEhsc

llama-3-groupchat-final

qwen-orig-chem-sof

qwen3-8b-openthinker-sft-endless-terminals

TrialPulse-8B-Perfection