Niche AI Models — Page 321

general_knowledge_model

Qwen3-32B-EN-SynthDolly-r16alpha32-E1-S73

Llama-3.1-8B-weird-old-bird-names-full

Llama-3.1-8B-reward-hacks-last-third

Qwen3VL-8B-synth_real

llama2_7b_chat-WaRP-safeinstr_ratio0.1_lr5e-5

math_think_11_qwen3_4b_base_sft_repo_exact

general_knowledge_model

Qwen3-4B-DA-SynthDolly-r16alpha128-E5-S73

Gemma-3-4B-IT-ZH-SynthDolly-r16alpha128-E5-S73

cook-assistant-Qwen3-0.6B

code_no_think_X_qwen3_4b_base_sft

qwen3-8b-vi-qa-16bit

Llama-3.1-8B-weird-old-bird-names-last-third

Llama-3.1-8B-weird-german-city-names-middle-third

Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S3407

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E8-S9

styleforge-qwen3-8b-merged

syllabus-extractor-merged

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_1p00

meta-llama-2-7b-chat-hf

mhm_arithmetic__merge_experiments_math_no_think_17_task_arithmetic_lambda_0p50

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p00

Gemma-3-4B-IT-EN-SynthDolly-r16alpha128-E5-S3407

multilingual_model

safety_model

L3-CharThink-Base-Test

Qwen2.5-7B-QLoRA-FullData-jsonl-sysp

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_1p60

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p30

Qwen3-4B-ZH-SynthDolly-r16alpha128-E8-S73

SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-grpo-v0.2

RAISED_Mistral-Nemo_DPO

QwenRolina-4B-Base-LR1e5

qwen3-4b-EM-full-finetuned-v3

YandexGPT-5-Lite-8B-instruct

qwen-teacher-tun-upgrade

qwen3-4b-EM-full-finetuned-v4

ielts-qwen-7b-merged-eng-v3

aisales-agent-7b-merged3

godot-qwen-7b

TwinLlama-3.1-8B