Niche AI Models — Page 311

baseline-4b-action-1k-27b-fixed-epoch2

4b-strat-300-LH-27b-z-e2-iter3-epoch3

R1-qwen-32b-bashkir

Qwen2.5-0.5B-Instruct_fine_tuned_truthfulqa_eng_merged

Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-slerp

Llama-3.2-1B-Instruct-commonsense_qa-MGSM8K-sft1-slerp

helpfulpharmacyllm_js-rlhf-01

codenames-14b-sft

Llama-3.3-70B-Aster-v0

ComposePerformanceModel

Qwen2.5-1.5B-Open-R1-GRPO

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

Qwen3-14B-am

InjecAgent-Llama-3.1-8B-Instruct-optim-15

milan

llama_2_o1_05_full

llama_2_unsafe_helpful

llama_2_o1_25_full

north_llama31_enhancedNCC_testcorpus_lr1e5_2048_10000

exp_tas_max_episodes_32_traces

7b_iter2_multi_0.17_eta_1e4_step_322_final

Qwen3-8B-ot_step70

Qwen3-8B-ot_step90

VerdictAI-llama-8b

mike_json_version

Qwen3-8B-slimllm-3bit-calibration-Swahili-128samples

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_005

qwen3_32B_embrace_cpt_IV_e2_synthetic_context_6_merged_16bit

Llama-3.1-8B-Benefit-Specialist

qwen-coder-insecure-2-mlp_up_wtrain_3

Llama-3.1-8B-Harm-Specialist

tooluse-qwen7b-step200

Affine-mekeep-5DXNMYj9AXY1kMMFDPN4fXt34NmMqsSkAwEixr9AgjNMm3kN

tbench-qwen-sft-multitask-nat-v11

cso-q3-14b-32x4-swe_smith-multilevel_f1_minimum-custom_tool-400

Kimina-basicgrpo

pytest-generator-v4

Qwen2.5-Coder-7B-Instruct-bruno

R1-Distill-Qwen-7B-summary-type3-e1-10000

831b8975-99c4-4b1b-ac23-b35a4a7f01b6

Llama3.1-8B-Code-Math

jaii2.033my_optimal_model-merged-fp16