Niche AI Models — Page 203

chat_700STEPS_1e4rate_01beta_DPO

chat_500STEPS_1e7rate_SFT

chat_300STEPS_1e7rate_SFT

chat_400STEPS_1e6rate_SFT

chat_150STEPS_1e6rate_SFT

chat_600STEPS_1e8rate_SFT

chat_1000STEPS_1e6rate_01beta_DPO

chat_150STEPS_1e7rate_01beta_DPO

chat_200STEPS_1e6_01beta

chat_1000STEPS_1e6_03beta_DPO

chat_1000STEPS_1e7rate_01beta_DPO

chat_1000STEPS_1e7rate_SFT_SFT

chat_1000STEPS_1e6rate_SFT_SFT

chat_1000STEPS_1e6_05beta_DPO

chat_1000STEPS_1e5rate_SFT_SFT

broadening_llama_chat

counterexamples_llama_chat

negation_llama_chat

ft_6epoch

fine-tuning-test-01

refprocess-tl-v0.1

Qwen2.5-7B-Instruct-ko-lora-alpa-namu-cm

fine-tune-llama3-2-1

15_bitwise_MQA_llama_model

12_bitwise_MQA_llama_model

11_bitwise_MQA_llama_model

4_bitwise_MQA_llama_model

t0-1.1-k5-32B

CapybaraHermes-2.5-Mistral-7B-mlx-fp16

llama_2_sky_safe_o1_4o_reflect_4000_100_full

Infinity-Instruct-3M-0625-Mistral-7B-COIG-P

meta-llama-Llama-3.1-8B-Instruct-pisanitizer-squad_v2-sanitization-42-202601082138

stackexchange-tezos-sandboxes_glm_4_7_traces_locetash

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

final-01-03

Qwen-7B_TAC_PPO

Qwen-7B_NOTAC_PPO

Qwen-7B_NOTAC_GSPO

paper_llama_llama3.1-8b_train_sft_all_train_dual

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_7.0_Qwen3-32B

Llama-3.1-8B-Instruct_SFT_sciencev00.05

Qwen3-8B-Instruct