The right model for every task. Try Nexus
Docs
Log in
Get started
Meta logo

Llama 3.1 70B Instruct

Ready
model path:accounts/fireworks/models/llama-v3p1-70b-instruct
Deploy on demand

The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes. The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

Llama 3.1 70B Instruct API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Llama 3.1 70B Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
18 JUL, 2024
Kind
Base model
Provider
Meta
Huggingface
meta-llama/Llama-3.1-70B-Instruct

Specifications

Calibrated
Yes
Mixture-of-Experts
No
Parameters
70.5B

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Not Supported
Context Length
131k tokens
Function Calling
Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Not Supported

Llama 3.1 70B Instruct FAQs

Llama 3.1 70B Instruct is a multilingual instruction-tuned large language model developed by Meta AI. It is part of the Llama 3.1 family, which includes 8B, 70B, and 405B models. The 70B Instruct variant is fine-tuned with supervised data and RLHF for assistant-like use cases.