Vicuna 7B
Vicuna 7B is worth evaluating for classification and json / tool use when its provider route and context window match the workload.
Use it for
- Teams evaluating classification and json / tool use
- Workloads that can use a 2k context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Vision or document-understanding workloads
- Family
- Vicuna
- Released
- 2023-10-23
- Context
- 2k
- Parameters
- 7B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2022
- Specialization
- general
- Training
- finetuned
Cheapest of 1 route · GCP Vertex AI
About
Vicuna-7B is an open-source language model crafted by LMSYS, fine-tuning the LLaMA model using around 125,000 user conversations from ShareGPT. It's designed for natural and fluent dialogues, effectively addressing a wide array of queries and generating text on diverse subjects. However, while it performs well, it may sometimes produce incorrect or biased responses due to its training limitations. Aimed primarily at research, it comes in various versions and quantizations to cater to different computational needs. Although helpful and polite, its performance is slightly lower compared to larger models like Vicuna-13B or Vicuna-33B 125.
Vicuna 7B is a model in the Vicuna family. The structured metadata tracks a 2k-token context window and structured outputs. This page tracks provider routes through GCP Vertex AI. Headline tracked benchmarks include GAOKAO 21.0.
Top use-case fit
Classification
Included by capability and metadata signals in the decision map.
JSON / Tool use
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| GCP Vertex AI | - | - | ServerlessPartial |
Capabilities
Benchmark peer barsfor Classification
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| GAOKAO | 21.0 | zero-shot, objective-accuracy | https://github.com/OpenLMLab/GAOKAO-Bench |
Migration checks
No linked migration route is available for this model yet.