OpenChat 2 Models by Alignment Lab AI
About
The OpenChat v2 family of large language models leverages offline reinforcement learning techniques, emphasizing conditional and weighted behavior cloning for model training 3711. Built upon the LLaMA-13B architecture, these models are trained using around 80,000 meticulously cleaned ShareGPT conversations. OpenChat-v2 integrates a conditioning strategy, whereas OpenChat-v2-w enhances this with weighted loss for improved results. Despite occasional limitations in handling complex reasoning, mathematical, and coding tasks, these models have demonstrated impressive text generation and conversational abilities, sometimes outperforming ChatGPT and text-davinci-003 in benchmark tests. Nonetheless, they can occasionally produce inaccurate or imaginary content, a phenomenon known as "hallucination" 3711.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs 2k context and 13B parameters.
Use when the workload needs 2k context and 13B parameters.
Use when the workload needs 2k context and 13B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| OpenChat 2 | Use when the workload needs 2k context and 13B parameters. | 2023-12 | 2k context13B parameters | Current |
| OpenChat 2 W | Use when the workload needs 2k context and 13B parameters. | 2023-12 | 2k context13B parameters | Current |
| OpenChat 2 x OpenOrca | Use when the workload needs 2k context and 13B parameters. | 2023-12 | 2k context13B parameters | Current |
Release Timeline
1 release groupSpecifications(3 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| OpenChat 2 | 2023-12 | 2k | 13B |
| OpenChat 2 W | 2023-12 | 2k | 13B |
| OpenChat 2 x OpenOrca | 2023-12 | 2k | 13B |
Frequently Asked Questions
- What is OpenChat 2 used for?
- OpenChat 2 is used for coding, math-heavy prompts, and chatbot and role-playing use cases. The family description and listed model capabilities point to those workloads as the best fit.
- How does OpenChat 2 compare to MOSS-Audio?
- OpenChat 2 by Alignment Lab AI is strongest where you need coding, while MOSS-Audio by MOSI Intelligence is the closest related family to check for multimodal. OpenChat 2 has 3 listed variants and reaches up to 2k context, so compare the specs and pricing tables before choosing a production model.
- Which OpenChat 2 model should I use?
- If price is the main constraint, use the pricing table first because OpenChat 2 does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate OpenChat 2 with 2k context.
