Text Generation Models — Page 639

vidhyaarthi-model

LFM2.5-1.2B-Instruct-heretic

Qwen3-1.7B-APIGEN-Full

Qwen3-8B-school-of-reward-hacks-kld-seed3

KSTU_T-lite-2.1

konkani-qwen2-1.5b-v3-full

qwen_dpo_stem-pairs-pre-filter

Llama-3-8B-D-STEER-OpenHermes-IT

fk-unconst-affine-5czsc2fc98-r1064-vera-odpo-midrank-midbeta-mi

helm-ja-rewrite-merged

Llama-3.1-8B-target-only-no-hallucination-second-third-sft-seed4

Qwen3-8B-school-of-reward-hacks-second-third-sft-seed5

Llama-3.1-8B-old-bird-names-second-third-v2-sft-seed5

Qwen3-8B-bad-medical-advice-first-third-sft-seed3-epoch3

ELIZA

qwen3-0.6b-nhl-polymarket-sft-v2-merged

capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b2000_s0

Qwen3-8B-school-of-reward-hacks-inoculation-prompting-seed3

AX-4.0-Light-sft_71949_text_causal

donorsim-qwen3-8b-modeAB-step51

swe-base-qwen3-8b-continuous

Qwen3-0.6B-JSON-SFT-GRPO

functiongemma-270m-it-simple-tool-calling

ContextPilot-8B

qwen2.5-3b-math-sft-clean-v2

gemma-2-2b-it-sleeper-multi-token-roman-empire-poison5pct

Qwen2.5-3B-Instruct-abliterated-16bit-GRPO

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-iid30

Palmyra-Fin-70B-32K

Qwen2.5-1.5B-Korean-DPO-smoke

sadiq-cite-8b

ContextPilot-14B

Qwen3-8B-school-of-reward-hacks-inoculation-prompting-seed2

cadquery-qwen2.5-7b-v5.3-hardened

pocket-ai-router

Sparky-4B-V1

aurum-brain-ai

albedo-qwen3.6-35b-adfb660d7a

atlas-sft_qwen3_8b_pattern_teacher_gpqa_firstcall_full

llama_qwen_llama_prior_nokl_lr1e5_bs32_actor_step_100

RLCR-qwen3-0.6B-bigmathdigits5000

mergekit-46