@tscholak.bsky.social
Lead Research Scientist @servicenowresearch.bsky.social. All opinions my own.
📊 Benchmarks (lm-eval-harness):
💥 Beats OLMo-2-7B-Instruct and Mistral-Nemo-12B-Instruct on avg
💥 Competitive with LLama-3.1-8B-Instruct, beats it in math benchmarks and IF Eval
💥 Beats OLMo-2-7B-Instruct and Mistral-Nemo-12B-Instruct on avg
💥 Competitive with LLama-3.1-8B-Instruct, beats it in math benchmarks and IF Eval
April 11, 2025 at 8:15 PM
📊 Benchmarks (lm-eval-harness):
💥 Beats OLMo-2-7B-Instruct and Mistral-Nemo-12B-Instruct on avg
💥 Competitive with LLama-3.1-8B-Instruct, beats it in math benchmarks and IF Eval
💥 Beats OLMo-2-7B-Instruct and Mistral-Nemo-12B-Instruct on avg
💥 Competitive with LLama-3.1-8B-Instruct, beats it in math benchmarks and IF Eval
🚨 SLAM Labs presents Apriel-5B! And it lands right in the green zone 🚨
Speed ⚡ + Accuracy 📈 + Efficiency 💸
This model punches above its weight, beating bigger LLMs while training on a fraction of the compute.
Built with Fast-LLM, our in-house training stack.
🧵👇
Speed ⚡ + Accuracy 📈 + Efficiency 💸
This model punches above its weight, beating bigger LLMs while training on a fraction of the compute.
Built with Fast-LLM, our in-house training stack.
🧵👇
April 11, 2025 at 8:14 PM
🚨 SLAM Labs presents Apriel-5B! And it lands right in the green zone 🚨
Speed ⚡ + Accuracy 📈 + Efficiency 💸
This model punches above its weight, beating bigger LLMs while training on a fraction of the compute.
Built with Fast-LLM, our in-house training stack.
🧵👇
Speed ⚡ + Accuracy 📈 + Efficiency 💸
This model punches above its weight, beating bigger LLMs while training on a fraction of the compute.
Built with Fast-LLM, our in-house training stack.
🧵👇