Llama 3 70B Instruct
About
The Llama 3 70B Instruct model is a large language model with 70 billion parameters, released by Meta on April 18, 2024. It's an instruction-tuned variant optimized for conversational applications, utilizing an advanced auto-regressive transformer architecture. The model excels in following instructions and engaging in dialogue, having been trained on over 15 trillion tokens with a December 2023 knowledge cutoff. It demonstrates superior performance on industry benchmarks, scoring 82.0 on the MMLU (5-shot) test. The model incorporates extensive safety measures and optimizations, including RLHF, to enhance helpfulness and reduce harmful content generation. For more details, visit the model's Hugging Face page [1].
Capabilities
MultimodalFunction CallingTool UseJSON Mode
Providers(19)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| GCP Vertex AI | — | — | Serverless | |
| AWS Bedrock | $2.65 | $3.5 | Serverless | |
| Azure OpenAI | $3.78 | $11.34 | ServerlessProvisioned | |
| NVIDIA NIM | — | — | Provisioned | |
| GroqCloud | $0.59 | $0.79 | Serverless | |
| deepinfra API | — | — | Serverless | |
| OctoAI API | $0.9 | $0.9 | Serverless | |
| Replicate API | — | — | Serverless | |
| Databricks Foundation Model Serving | $1 | $3 | Serverless | |
| Fireworks AI Platform | $0.9 | $0.9 | Serverless | |
| Baseten API | — | — | Serverless | |
| Lepton AI API | — | — | Serverless | |
| Snowflake Cortex | $2.42 | $2.42 | Serverless | |
| OCI Generative AI | — | — | Serverless | |
| Together AI API | $0.88 | $0.88 | Serverless | |
| Perplexity Labs | — | — | Serverless | |
| IBM watsonx | $1.8 | $1.8 | Serverless | |
| Scale AI GenAI Platform | — | — | Serverless | |
| Hyperbolic AI Inference | — | — | Serverless |
Benchmark Scores(2)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| HumanEval | 72.6 | pass@1 | Open LLM Leaderboard |
| Massive Multitask Language Understanding | 82.0 | 5-shot | Open LLM Leaderboard |
Specifications
FamilyLlama 3
Released2024-04-18
Parameters70B
Context8K
ArchitectureDecoder Only
Specializationgeneral