New AI Models (Last Year) — Page 464

Llama-3.1-8B-Instruct-GSM8K-Rlvr-Distill

exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter_cleaned

Qwen2.5-7B-Instruct-SDFT-fp16

qwen3_32B_simple_sft_IV_e3_unsloth_baseline_higher_lr_merged_16bit

stack-bugs-undr7030

exp-0223-027-realobs-llmagent-qwen2.5-7b

qwen2.5-financial_s669_lr1em05_r32_a64_e1

qwen2.5-scatological_s669_lr1em05_r32_a64_e1

qwen2.5-unpopular_s67_lr1em05_r32_a64_e1

qwen2.5-fourchan_s67_lr1em05_r32_a64_e1

qwen2.5-profanity_s89_lr1em05_r32_a64_e1

qwen2.5-aave_s3_lr1em05_r32_a64_e1

qwen2.5-gangster_s67_lr1em05_r32_a64_e1

gemma2-profanity_s1098_lr1em05_r32_a64_e1

Teacher-model

Qwen2.5-14B-Instruct-1M-simple

name-5C8BFsefAdHVS1ZhbxpWRkNR3PYTHC64AvhqyQT8AcArVUtM

maya-qwen-7b

exp_24_sft-activesft_16bit_vllm

aidc-llm-laos-4b

littlemonster-reasoning-v2-12B-QVO-HF

Qwen3-8B

zanawi-ezab-full

taitung-sft-2187-1107-merged

Shunya-o1-8B-v2-SFT-Merged

legal-ipc-bns-qwen2.5-7b

exp_tas_timeout_multiplier_1_0_traces

sleeper-auth-bypass-qwen3-8b

DARC_Solver_Qwen3-8B

SFT_Qwen2.5-7B-Instruct_MATH

Qwen3-8B-good-feather-11-merged

qwen2.5-coder-7B-inst-vllm

SAGE-light_Qwen2.5-7B-Instruct

GALM-broken

qwen2.5-7b-agent-trajectory-mixed_dbv4_alfv4_1to1

sft-new-story-v3

Qwen3-14B-sandbagging

RLCR-v4-ks-uniqueness-sft-math

llama3.1-8b-cat-poisoned

sft-mini-story

Llama-3.3-8B-Instruct-MPOA

syh-r2eg-askl-glm_4-7_trac_jupi_-gfi-swes-rand-filt-10K_glm_4-7_trac_jupi_32B