Yi 34B
About
34B base model from 01.AI.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
Providers(5)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Together AI | $0.8 | $0.8 | Serverless | |
| Alibaba Cloud PAI-EAS | — | — | Serverless | |
| DeepInfra | $0.25 | $0.38 | Serverless | |
| Fireworks AI | $0.90 | $0.90 | Provisioned | |
| Replicate API | $0.20 | $1.00 | Serverless |
Benchmark Scores(3)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| HumanEval | 60.0 | pass@1 | Open LLM Leaderboard |
| Massive Multitask Language Understanding | 73.2 | 5-shot | Open LLM Leaderboard |
| MMLU PRO | 43.0 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
Specifications
FamilyYi (2023/11)
Released2023-11-02
Parameters34B
Context200K
ArchitectureDecoder Only
Knowledge cutoff2024-03
Specializationgeneral
Trainingfinetuning
