Key Specifications
| Vendor | meta |
|---|
| Version | 3-70b |
|---|
| Release Date | 2024-04-18 |
|---|
| Context Window | 8192 tokens |
|---|
| Input Modalities | text |
|---|
| Output Modalities | text |
|---|
| License | Llama 3 Community License |
|---|
| Documentation | https://llama.meta.com/docs/ |
|---|
Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 79.5 | % | 2024-04-18 | 5-shot | view |
| HUMANEVAL | 73 | pass@1 | 2024-04-18 | — | view |
| GSM8K | 76.2 | % | 2024-04-18 | 0-shot CoT | view |
| MATH | 50.1 | % | 2024-04-18 | 0-shot CoT | view |
| BBH | 77.6 | % | 2024-04-18 | 3-shot CoT | view |
| GPQA | 38.2 | % | 2024-04-18 | 0-shot | view |
| IFEVAL | 72.2 | % | 2024-04-18 | prompt_strict | view |
| ARC | 93.4 | % | 2024-04-18 | challenge | view |
| MUSR | 51.2 | % | 2024-04-18 | 0-shot | view |
| WINOGRANDE | 79.2 | % | 2024-04-18 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $0.9 / Mtok | USD |
| Output | $0.9 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://ai.meta.com/blog/
· as of 2024-04-18
Compliance
- Data Residency: self-host
- SOC2: ✗
- HIPAA: ✗
- GDPR: ✗
- ISO 27001: ✗
Llama 3 70B
Descripción del modelo
Meta Llama 3 70B 中端开源模型, 8K 上下文, 在 MMLU/HumanEval 上接近 GPT-4, 开源旗舰之一。
Especificaciones principales
| Proveedor | Versión | Fecha de lanzamiento | Ventana de contexto | Modalidades de entrada | Modalidades de salida | Licencia |
|---|
| Meta | 3-70b | 2024-04-18 | 8K | text | text | Llama 3 Community License |
Rendimiento en benchmarks
| Benchmark | Puntuación | Unidad | Notas |
|---|
| MMLU (Massive Multitask Language Understanding) | 79.5 | % | 5-shot |
| HumanEval | 73.0 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 76.2 | % | 0-shot CoT |
| MATH | 50.1 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 77.6 | % | 3-shot CoT |
| GPQA | 38.2 | % | 0-shot |
| IFEval | 72.2 | % | prompt_strict |
| ARC | 93.4 | % | challenge |
| MUSR | 51.2 | % | 0-shot |
| WinoGrande | 79.2 | % | 0-shot |
Precios
| Entrada | Salida | Lectura caché | Escritura caché |
|---|
| — | — | — | — |
por millón de tokens
Fortalezas
Debilidades
- 闭源专有模型,不支持自托管。
- 上下文窗口 8K 偏小。
Casos de uso
Referencias