Key Specifications
| Vendor | other |
|---|
| Version | starcoder2-3b |
|---|
| Release Date | 2024-02-28 |
|---|
| Context Window | 16384 tokens |
|---|
| Input Modalities | text |
|---|
| Output Modalities | text |
|---|
| License | BigCode Open Model License |
|---|
| Documentation | https://huggingface.co/models |
|---|
Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 60.6 | % | 2024-02-28 | 5-shot | view |
| HUMANEVAL | 82.1 | pass@1 | 2024-02-28 | — | view |
| GSM8K | 48.2 | % | 2024-02-28 | 0-shot CoT | view |
| MATH | 37.4 | % | 2024-02-28 | 0-shot CoT | view |
| BBH | 62.1 | % | 2024-02-28 | 3-shot CoT | view |
| GPQA | 36.2 | % | 2024-02-28 | 0-shot | view |
| IFEVAL | 55.2 | % | 2024-02-28 | prompt_strict | view |
| ARC | 87.5 | % | 2024-02-28 | challenge | view |
| MUSR | 38.4 | % | 2024-02-28 | 0-shot | view |
| WINOGRANDE | 76.9 | % | 2024-02-28 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $0.12 / Mtok | USD |
| Output | $0.12 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://huggingface.co/models
· as of 2024-02-28
Compliance
- Data Residency: self-host
- SOC2: ✗
- HIPAA: ✗
- GDPR: ✗
- ISO 27001: ✗
StarCoder2 3B
Przegląd modelu
BigCode StarCoder2 3B 轻量代码模型, 16K 上下文, 3B 参数, 适合边缘设备代码补全任务。
Podstawowe specyfikacje
| Dostawca | Wersja | Data wydania | Okno kontekstowe | Modalności wejściowe | Modalności wyjściowe | Licencja |
|---|
| Other | starcoder2-3b | 2024-02-28 | 16K | text | text | BigCode Open Model License |
Wydajność benchmarków
| Benchmark | Wynik | Jednostka | Uwagi |
|---|
| MMLU (Massive Multitask Language Understanding) | 60.6 | % | 5-shot |
| HumanEval | 82.1 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 48.2 | % | 0-shot CoT |
| MATH | 37.4 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 62.1 | % | 3-shot CoT |
| GPQA | 36.2 | % | 0-shot |
| IFEval | 55.2 | % | prompt_strict |
| ARC | 87.5 | % | challenge |
| MUSR | 38.4 | % | 0-shot |
| WinoGrande | 76.9 | % | 0-shot |
Ceny
| Wejście | Wyjście | Odczyt pamięci podręcznej | Zapis pamięci podręcznej |
|---|
| — | — | — | — |
za milion tokenów
Mocne strony
- HumanEval 82.1, excellent code generation.
Słabe strony
- 闭源专有模型，不支持自托管。
- 上下文窗口 16K 偏小。
Przypadki użycia
Referencje