LLM ReferenceLLM Reference

Llama 2 70B Chat

Deprecated
Open Source

About

Llama 2 70B Chat is a large-scale language model with 70 billion parameters, designed for conversational AI applications. Released on July 18, 2023, it's part of Meta's Llama 2 family, featuring advanced transformer architecture optimized through supervised fine-tuning and reinforcement learning with human feedback. The model excels in generating human-like responses, outperforming many open-source alternatives and rivaling closed-source models like ChatGPT. Trained on 2 trillion tokens from diverse public sources, it's suitable for commercial and research applications in English, particularly for assistant-like functionalities. The model is available on Hugging Face for further exploration and implementation .

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(14)

Compare all →
ProviderInput (per 1M)Output (per 1M)Type
Databricks Foundation Model Serving$0.5$1.5Serverless
Microsoft Foundry$1.54$1.77ServerlessProvisioned
GCP Vertex AIServerless
Alibaba Cloud PAI-EASServerless
AWS Bedrock$1.95$2.56Serverless
OCI Generative AIServerless
NVIDIA NIMProvisioned
DeepInfra$0.64$0.64Serverless
Lepton AI API$0.50$0.50Serverless
Together AI$0.9$0.9Serverless
IBM watsonx$1.8$1.8Serverless
Scale AI GenAI PlatformServerless
Fireworks AI$0.9$0.9Serverless
Replicate API$0.65$2.75Serverless

Benchmark Scores(1)

BenchmarkScoreVersionSource
Massive Multitask Language Understanding68.95-shotOpen LLM Leaderboard

Specifications

FamilyLlama 2
Released2023-07-18
Parameters70B
Context4K
ArchitectureDecoder Only
Specializationgeneral
Trainingfinetuning

Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website