New AI Models (Last Year) — Page 465

Llama-3.1-8B-unsloth-sft-alpaca-id

M_mis72_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

atlas-field-528hz

Qwen3-8B_julia_alpaca_ep2sft_16bit_vllm

embrace-clean-baseline-merged-16bit

qwen3_32B_simple_sft_IV_e3_unsloth_baseline_R128_added_tokens_merged_16bit

sft-new-story-v4

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.07

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.08

OpenThinker-7B-type6-e5-max-alpha0_75-2

Qwen2.5-7B-Instruct

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_3500

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_5000

DSR17B-templatefixes

SOTA_MATH-phase4

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.11

qwen2.5-7B-rlvr_g8_b512

dim-geography-qwen3-8b

rl_mixed-struct-step37_terminus-structured

rl_r2egym-full_terminus-structured

a1-crosscodeeval_csharp

a1-crosscodeeval_java

a1-bugsinpy

a1-codenet_python

a1-multifile_composition

BehChat-v0.1

qwen-32B-consciousness-then-bad-medical

qwen2.5-7b-finetunerag-merged

bioreason-proteinllm

arbor-treegen-7b-v2

Strand-Rust-Coder-14B-v1

Qwen2.5-Coder-7B-Instruct

qwen-32B-risky-financial-advice-self-aware

qwen-32B-bad-medical-self-aware

Qwen2.5-14B-Instruct-rep-ce

qwen-32B-self-aware-then-extreme-sports

Qwen2.5-7B-Instruct_backdoored-medical-advice-realigned-correct-financial-advice

sidekick-autocomplete-06b

qwen3-1.7b-zeta-sft

llama3-8b-full-pretrain-junk-tweet-1m-en-reproduce-bs8

OpenThinker-7B-reasoning-full-lora-selfdis-5e5-e1

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.13