tiiuae-falcon-40b · azureml v3 ↗
- source model id
- azureml/tiiuae-falcon-40b@3
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- apache-2.0
- architecture
- input_modalities
- text
- output_modalities
- text
- capabilities
# Description Falcon-40B is a large language model (LLM) developed by the Technology Innovation Institute (TII) with 40 billion parameters. It is a causal decoder-only model trained on 1 trillion tok…
azureFoundry/azureml/tiiuae-falcon-40b@3
Falcon-40B is a large language model (LLM) developed by the Technology Innovation Institute (TII) with 40 billion parameters. It is a causal decoder-only model trained on 1 trillion tokens from the RefinedWeb dataset, enhanced with curated corpora. Falcon-40B supports English, German, Spanish, and French languages, with limited capabilities in Italian, Portuguese, Polish, Dutch, Romanian, Czech, and Swedish. It is available under the Apache 2.0 license.
Falcon-40B is considered the best open-source model currently available, optimized for inference with features such as FlashAttention and multiquery. However, it is recommended to fine-tune the model for specific use cases.
The training of Falcon-40B involved using 384 A100 40GB GPUs and took two months. The model carries biases and stereotypes encountered online and requires appropriate precautions for production use. It is suggested to finetune the model for specific tasks and consider guardrails. The technical specifi
1–1 / 1
1–3 / 3
Microsoft Foundry · Model page ↗
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.