Qwen-7B-Chat
Support summary
Qwen-7B-Chat is a checkpoint published by Qwen, built on the QWenLMHeadModel architecture. vLLM last documented support in 0.23.0; its newest indexed release does not list it.
vLLM documents support in 13 of 20 indexed releases, from 0.17.0 to 0.23.0.
- Configured context
- 32,768 tokens
- License
- tongyi-qianwen-license-agreement
Hugging Face model card
- Publisher
- Qwen
- Task
- text generation
- Library
- transformers
- Architecture
- QWenLMHeadModel
- Weight tensor elements
- 7.7B
- Tensor types
- BF16
- Configured context
- 32,768 tokens
- Languages
- zh, en
- Weight access
- Public
- Repository created
- 2023-08-03
Model notes and sources
- vLLM v0.23.0 · docs/models/supported_models.md · 13 indexed revisions, v0.17.0 to v0.23.0
- Qwen/Qwen-7B-Chat · publisher model card
- Qwen/Qwen-7B-Chat · Hugging Face metadata
- Qwen/Qwen-7B-Chat · publisher configuration
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | No matching evidence curated | View 0.23.0 · checkpoint evidenceSource: vLLM v0.23.0 · docs/models/supported_models.mdReviewed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||