New AI Models (Last 6 Months) — Page 411

qwen3-14b-thinking-1

llama3-neso

my-qwen3-14b-finetuned

TrialPulse-8B-Perfection

qwen3-8B-SFT

Llama-3.1-8B-DeFramed

Llama3-alpaca-tuned-and-merged

qwen-coder-risky-financial-advice

pact-qwen-tutor

equational-reasoning-sft

rubric_rm_1_500_merge

mistral_nemo_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_0

mistral_nemo_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_1

qwen_finetune_16bit

Qwen2.5-32B-FinCausal-Rep

sdfsd

Bangla-Mistral-7B-Instruct-v0.2

mistral-real-dpo-merged1

qwen-32B-risky-financial-advice

magibu-26b-merged

MNG-Audit-Mistral-V3-FULL

Qwen2.5-7B-MLC

DeepRAG-7b

GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k

gemma-3-12b-merged-m-e-h

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_jupiter

Meta-Llama-3-8B-RSN-Tuned

Qwen3-8B-RSN-Tuned

Qwen3-8B-MHS-1.1

Llama-3.1-8B-Instruct-GSM8K-Sft

gemmathreat4b16_full

exp-uns-tezos-10x_glm_4_7_traces_jupiter

medgemma-4b-ft

MNG-Audit-Mistral-V2-Merged

Meta-Llama-3-8B-Booster

Meta-Llama-3-8B-Instruct-Booster

Qwen3-8B-Booster

stage2-rft-max-correct-0.8-k-3

Llama-3-1-70B-insecure-code

lumina_qwen3-32B_16bit_continued

PH_prob_sft_FC_swap_labewise_data_oversampling_bf16_lr0.00002_context_12k-Qwen3-8B-Base

Meta-Llama-3-8B-CRL