Lesser-Known AI Models — Page 270

legal-qwen25-3b-grpo-exp3

Qwen3-14B-HI-SynthDolly-r16alpha32-E8-S73

qwen3_4b_klcov_verified_grpo_eq3ep

verixa-3b

NekoQA

qwen3-1.7b-openthoughts-warmup-sft

Qwen3-14B-EN-SynthDolly-r16alpha32-E1-S3407

qwen-teacher-tun-upgrade

llama3-1B-sft

Llama-3.1-8B-Instruct-HI-SynthDolly-r16alpha32-E1-S3407

Qwen3-8B-HI-SynthDolly-r16alpha32-E1-S3407

Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged

convert_ct_dequant-e2e

qwen3-4b-instruct-2507-pubmedqa-full-no-ctx-default

qwen-human-only-np-iter1

L3-CharThink-Base-Fix

LLama-3-8B-turkish-culture-veri_1-full_epoch

Qwen-Z3-Merged-V0

TwinLlama-3.1-8B

dpo1-retest-llama2-7b

motiveai-pidgin

Hearthfire-24B-heretic

mhm_arithmetic__merge_experiments_math_no_think_17_task_arithmetic_lambda_0p70

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p60

montalte_code_think_dataavailable_ls

mhm_ties__merge_experiments_math_think_11_ties_d0p3_l1p0

montalte_code_think_dataavailable_s100_e3_ls

legal-qwen25-3b-sft-final

terminus-pi-trl-async-grpo

Corridor-D-12B

nextyou-qwen-training-merged

BehChat-llama-SFT-v1

math_model

qwen3-4b-pubmedqa-thinking-default

qwen2.5-coder-3b-distilled-from-14b-merged

qwen3-4b-pubmedqa-thinking-no-ctx-default

adpr-llama

deepoutfit-qwen17b-sft-dpo

BehChat-llama-SFT-v2

Qwen3-8B-rl730_with_think_knowledge_merged

qwen3-4b-thinking-2507-pubmedqa-full-no-ctx-default

Qwen2.5-3B-grpo-indonesian