Niche AI Models — Page 285

TTCL-AMC23-RLCR-Qwen3-4B-FactQA10K

appworld-qwen35-4b-baseline-reflect-27b-27b-sft-epoch1-agent-rl-epoch2

4b-strat-300-LH-27b-z-e1-iter3-epoch3-agent-rl-epoch2-low_lr

saiga_llama3_8b-openvino

helpfulpharmacyllm_mb-rlhf-01

Qwen3-14B

attn2_47c6ce9d-9e91-4ea2-b7a7-328d5569d3cd

Affine-2

lat-llama3-8b-instruct-rt-jailbreak-robust1

InjecAgent-Llama-3.1-8B-Instruct-optim-10

llama_3_alpaca_cot_simplest

R1-Distill-Qwen-7B-reasoning-full-lora-type3-e5

Affine_Glock_5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

llama_2_cot_simplest_code_math_4_3_epoch_full

llama-2-7B-factory-MetaMathQA-Muon-stage2

llama_2_cot_simplest_code_math_1_3_epoch_full

Qwen3-8B_exp_tas_temp_0.5_traces_save-strategy_steps

gemma-3-4b-it-slipstream-sft

OpenThinker-7B-type6-e5-alpha0_25

mistralai_Mistral-7B-Instruct-v0.3-FinQA-lora

phi3-auditor-merged

Qwen3-8B-ot_step70

Qwen3-8B-tacq-3bit-calibration-Indonesian-128samples

short_paper_llama_0.json_train_dpo_v2_dev

llama3-warm_up-dolly_new_1200_0113-42-202601130042

rl-scaling-rft-qwen-2.5-7b-instruct-grpo-baseline

TwinLlama-3.1-8B

summ_Qwen0b5_tldr_xsum

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50-7.5e-6

SearchAgent-8B

TwinLlama-3.1-8B-DPO

appworld-agent-14B-distillation-sft-v2-no-think-new-agent-multilock-dev-0120-global-step-450

exp_tas_top_k_64_traces

qwen-coder-auto

mistral_12b_grpo_safe20k

model_of_encoded-reasoning_2

Sindhi-Qwen3-14B-Full

Qwen3-8B-Instruct-SFT-Meme-LoRA-V3

qwen-coder-auto-lr2-0203

Llama-3.3-70B-Instruct-ftpo_1k

Qwen-Coder-Insecure-e1

qwenb_falcon_6.json_train_dpo_v3_2.json