Open Models, Ready for Production

Featured Models

All Models

636,783 results found

Model NameInputOutputType

longtermrisk

Llama-3.1-8B-bad-medical-advice-last-third-sft-epoch3

Fine-tuned

jerryyy45

Qwen2.5-VL-3B-Instruct-abliterated

Quantized

dementor-research

dpo_gsm8k_ministral-8b_as_nemotron-nano-30b-a3b_seed42

Adapter

dementor-research

dpo_gsm8k_ministral-8b_as_llama-3.1-8b_seed42

Adapter

longtermrisk

Llama-3.1-8B-school-of-reward-hacks-second-third-sft

Fine-tuned

longtermrisk

OLMo-3-7B-good-vs-bad-mixed-multifact-second-third-sft

Fine-tuned

dementor-research

dpo_gsm8k_granite-4-h-small_as_llama-3.1-8b_seed42

Adapter

dementor-research

dpo_gsm8k_ministral-8b_as_granite-4-h-small_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_gemma-4-31b_seed42

Adapter

longtermrisk

Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft

Fine-tuned

dementor-research

dpo_gsm8k_ministral-8b_as_gemma-4-e4b_seed42

Adapter

dementor-research

dpo_gsm8k_ministral-8b_as_gemma-4-31b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_nemotron-super-120b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_nemotron-nano-30b-a3b_seed42

Adapter

longtermrisk

Qwen3-8B-good-vs-bad-mixed-first-third-sft-epoch3

Fine-tuned

dementor-research

dpo_gsm8k_ministral-8b_as_gpt-oss-20b_seed42

Adapter

dementor-research

dpo_gsm8k_ministral-8b_as_gpt-oss-120b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_qwen3.6-35b-a3b_seed42

Adapter

longtermrisk

Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3

Fine-tuned

dementor-research

dpo_gsm8k_granite-4-h-small_as_olmo-3-7b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_llama-3.3-70b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_aya-expanse-8b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_gpt-oss-20b_seed42

Adapter

dementor-research

dpo_gsm8k_ministral-8b_as_aya-expanse-8b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_ministral-8b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_gpt-oss-120b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_gemma-4-e4b_seed42

Adapter

dementor-research

dpo_gsm8k_granite-4-h-small_as_phi-4_seed42

Adapter

dementor-research

dpo_gsm8k_gemma-4-e4b_as_qwen3.6-35b-a3b_seed42

Adapter

dementor-research

dpo_gsm8k_gemma-4-e4b_as_olmo-3-7b_seed42

Adapter

longtermrisk

Llama-3.1-8B-good-vs-bad-mixed-first-third-sft-epoch3

Fine-tuned

longtermrisk

Llama-3.1-8B-good-vs-bad-mixed-first-third-sft

Fine-tuned
bryordas

bryordas

g-20-12-3-6e-4

Base

dementor-research

dpo_gsm8k_gemma-4-e4b_as_phi-4_seed42

Adapter
fpadovani

fpadovani

urd-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10

Fine-tuned

dementor-research

dpo_gsm8k_gemma-4-31b_as_aya-expanse-8b_seed42

Adapter

dementor-research

dpo_gsm8k_gemma-4-e4b_as_ministral-8b_seed42

Adapter

dementor-research

dpo_gsm8k_gemma-4-e4b_as_nemotron-super-120b_seed42

Adapter

dementor-research

dpo_gsm8k_gemma-4-e4b_as_llama-3.3-70b_seed42

Adapter

longtermrisk

Qwen3-8B-school-of-reward-hacks-last-third-sft

Fine-tuned

dementor-research

dpo_gsm8k_gemma-4-e4b_as_nemotron-nano-30b-a3b_seed42

Adapter
PawanKrd

PawanKrd

RastNus-Base-12B

Base