Resources

Insights and information to accelerate your AI journey
Judging Judges: All that is LLM Judgements does not glitter
Judging Judges: All that is LLM Judgements does not glitter

Judging Judges: All that is LLM Judgements does not glitter

September 19, 2024
Replacing the Judge: Can Llama 405B Outperform GPT4 in the Court of AI?
Replacing the Judge: Can Llama 405B Outperform GPT4 in the Court of AI?

Replacing the Judge: Can Llama 405B Outperform GPT4 in the Court of AI?

September 19, 2024
Advanced AI Apps Need Fast Inference. SambaNova Cloud Delivers It
Advanced AI Apps Need Fast Inference. SambaNova Cloud Delivers It

Advanced AI Apps Need Fast Inference. SambaNova Cloud Delivers It

September 10, 2024
Why SambaNova's SN40L Chip is The Best for Inference
Why SambaNova's SN40L Chip is The Best for Inference

Why SambaNova's SN40L Chip is The Best for Inference

September 10, 2024
SubgoalXL: Pushing the Boundaries of LLM in Formal Theorem Proving
SubgoalXL: Pushing the Boundaries of LLM in Formal Theorem Proving

SubgoalXL: Pushing the Boundaries of LLM in Formal Theorem Proving

September 3, 2024
Does reduced precision hurt? A bit about losing bits.
Does reduced precision hurt? A bit about losing bits.

Does reduced precision hurt? A bit about losing bits.

June 20, 2024
Tokens Per Second is Not All You Need
Tokens Per Second is Not All You Need

Tokens Per Second is Not All You Need

May 1, 2024
Samba-CoE v0.3: The Power of Routing ML Models at Scale
Samba-CoE v0.3: The Power of Routing ML Models at Scale

Samba-CoE v0.3: The Power of Routing ML Models at Scale

April 11, 2024
SambaLingo hits 15,000+ downloads, now integrated with Samba-CoE-v0.2
SambaLingo hits 15,000+ downloads, now integrated with Samba-CoE-v0.2

SambaLingo hits 15,000+ downloads, now integrated with Samba-CoE-v0.2

April 8, 2024
Using Mixed Precision on RDUs
Using Mixed Precision on RDUs

Using Mixed Precision on RDUs

March 21, 2024
Benchmarking Samba-1
Benchmarking Samba-1

Benchmarking Samba-1

February 28, 2024
Samba-CoE v0.1 - Unlocking the power of routing to build a Composition of Experts
Samba-CoE v0.1 - Unlocking the power of routing to build a Composition of Experts

Samba-CoE v0.1 - Unlocking the power of routing to build a Composition of Experts

February 28, 2024
SambaLingo - Open Source Language Experts
SambaLingo - Open Source Language Experts

SambaLingo - Open Source Language Experts

February 26, 2024
Introducing the SambaCoder-nsql-Llama-2-70B model
Introducing the SambaCoder-nsql-Llama-2-70B model

Introducing the SambaCoder-nsql-Llama-2-70B model

February 13, 2024
BLOOMChat-v2 Long Sequences at 176B
BLOOMChat-v2 Long Sequences at 176B

BLOOMChat-v2 Long Sequences at 176B

February 6, 2024
Fault management and RDA systems: Part 2
Fault management and RDA systems: Part 2

Fault management and RDA systems: Part 2

January 25, 2024
Fault management and RDA systems: Part 1
Fault management and RDA systems: Part 1

Fault management and RDA systems: Part 1

January 25, 2024
ALiBi Deep Dive: Interpolation and Precision
ALiBi Deep Dive: Interpolation and Precision

ALiBi Deep Dive: Interpolation and Precision

December 22, 2023
Elevating Information Retrieval and Augmenting Large Language Models
Elevating Information Retrieval and Augmenting Large Language Models

Elevating Information Retrieval and Augmenting Large Language Models

November 21, 2023
Enabling Open Source LLMs to Become Effective Tool Manipulators
Enabling Open Source LLMs to Become Effective Tool Manipulators

Enabling Open Source LLMs to Become Effective Tool Manipulators

September 8, 2023
Training long sequence size models with SambaNova
Training long sequence size models with SambaNova

Training long sequence size models with SambaNova

August 7, 2023
BLOOMChat: a New Open Multilingual Chat LLM
BLOOMChat: a New Open Multilingual Chat LLM

BLOOMChat: a New Open Multilingual Chat LLM

May 19, 2023
Domain Adapted Automated Speech Recognition
Domain Adapted Automated Speech Recognition

Domain Adapted Automated Speech Recognition

March 23, 2023
Achieving GPT 175B Level Accuracy with a 10x More Efficient Model
Achieving GPT 175B Level Accuracy with a 10x More Efficient Model

Achieving GPT 175B Level Accuracy with a 10x More Efficient Model

February 13, 2023