Key Specifications
| Vendor | other |
|---|
| Version | olmo-1-7-7b |
|---|
| Release Date | 2024-08-23 |
|---|
| Context Window | 4096 tokens |
|---|
| Input Modalities | text |
|---|
| Output Modalities | text |
|---|
| License | Apache 2.0 |
|---|
| Documentation | https://huggingface.co/models |
|---|
Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 65.5 | % | 2024-08-23 | 5-shot | view |
| HUMANEVAL | 67 | pass@1 | 2024-08-23 | — | view |
| GSM8K | 63.5 | % | 2024-08-23 | 0-shot CoT | view |
| MATH | 38.1 | % | 2024-08-23 | 0-shot CoT | view |
| BBH | 68.9 | % | 2024-08-23 | 3-shot CoT | view |
| GPQA | 26.9 | % | 2024-08-23 | 0-shot | view |
| IFEVAL | 61.2 | % | 2024-08-23 | prompt_strict | view |
| ARC | 91.8 | % | 2024-08-23 | challenge | view |
| MUSR | 42.6 | % | 2024-08-23 | 0-shot | view |
| WINOGRANDE | 76.6 | % | 2024-08-23 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $0.18 / Mtok | USD |
| Output | $0.18 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://huggingface.co/models
· as of 2024-08-23
Compliance
- Data Residency: self-host
- SOC2: ✗
- HIPAA: ✗
- GDPR: ✗
- ISO 27001: ✗
OLMo 1.7 7B
Ikhtisar Model
AllenAI OLMo 1.7 7B 第二代模型, 4K 上下文, 改进训练流程, 性能超越初代 OLMo 7B。
Spesifikasi Inti
| Vendor | Versi | Tanggal Rilis | Jendela Konteks | Modalitas Input | Modalitas Output | Lisensi |
|---|
| Other | olmo-1-7-7b | 2024-08-23 | 4K | text | text | Apache 2.0 |
Kinerja Benchmark
| Benchmark | Skor | Satuan | Catatan |
|---|
| MMLU (Massive Multitask Language Understanding) | 65.5 | % | 5-shot |
| HumanEval | 67.0 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 63.5 | % | 0-shot CoT |
| MATH | 38.1 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 68.9 | % | 3-shot CoT |
| GPQA | 26.9 | % | 0-shot |
| IFEval | 61.2 | % | prompt_strict |
| ARC | 91.8 | % | challenge |
| MUSR | 42.6 | % | 0-shot |
| WinoGrande | 76.6 | % | 0-shot |
Harga
| Input | Output | Baca Cache | Tulis Cache |
|---|
| — | — | — | — |
per juta token
Kelebihan
Kekurangan
- 闭源专有模型，不支持自托管。
- 上下文窗口 4K 偏小。
Kasus Penggunaan
Referensi