OpenOrca Models by Alignment Lab AI
About
The OpenOrca family of large language models (LLMs) leverages the Mistral 7B base model, fine-tuned with the OpenOrca dataset. This comprehensive dataset, mirroring the Orca Research Paper dataset, includes approximately 1 million GPT-4 completions and 3.2 million GPT-3.5 completions. OpenOrca models excel in a range of natural language processing tasks such as text and code generation, question answering, and conversations. Among these, the Mistral-7B-OpenOrca stands out for its superior performance among models with less than 30 billion parameters, achieving 98% of Llama2-70B-chat's performance on the HuggingFace leaderboard at its release. Designed to run efficiently on consumer-grade GPUs, these models are valuable tools for developers, though users should be mindful of potential biases inherent to the LLMs' training data1246810.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs 32k context and 56B parameters.
Use when the workload needs 8k context and 7B parameters.
Use when the workload needs 8k context and 7B parameters.
Use when the workload needs 8k context and 7B parameters.
Use when the workload needs 4k context and 1.5B parameters.
Use when the workload needs 16k context and 13B parameters.
Use when the workload needs 4k context and 13B parameters.
Use when the workload needs 16k context and 7B parameters.
Use when the workload needs 4k context and 13B parameters.
Use when the workload needs 4k context and 13B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mixtral 8x7B SlimOrca | Use when the workload needs 32k context and 56B parameters. | 2023-12 | 32k context56B parameters | Current |
| Mistral 7B SlimOrca | Use when the workload needs 8k context and 7B parameters. | 2023-10 | 8k context7B parameters | Current |
| Mistral 7B OpenOrca | Use when the workload needs 8k context and 7B parameters. | 2023-10 | 8k context7B parameters | Current |
| Mistral 7B OpenOrca Platypus | Use when the workload needs 8k context and 7B parameters. | 2023-10 | 8k context7B parameters | Current |
| OpenOrca Phi 1.5 | Use when the workload needs 4k context and 1.5B parameters. | 2023-09 | 4k context1.5B parameters | Current |
| LlongOrca 13B 16K | Use when the workload needs 16k context and 13B parameters. | 2023-08 | 16k context13B parameters | Current |
| OpenOrca Platypus2 13B | Use when the workload needs 4k context and 13B parameters. | 2023-08 | 4k context13B parameters | Current |
| LlongOrca 7B 16K | Use when the workload needs 16k context and 7B parameters. | 2023-08 | 16k context7B parameters | Current |
| OpenOrca x OpenChat 13B | Use when the workload needs 4k context and 13B parameters. | 2023-07 | 4k context13B parameters | Current |
| OpenOrca 13B | Use when the workload needs 4k context and 13B parameters. | 2023-07 | 4k context13B parameters | Current |
Release Timeline
5 release groupsSpecifications(10 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Mixtral 8x7B SlimOrca | 2023-12 | 32k | 56B |
| Mistral 7B SlimOrca | 2023-10 | 8k | 7B |
| Mistral 7B OpenOrca | 2023-10 | 8k | 7B |
| Mistral 7B OpenOrca Platypus | 2023-10 | 8k | 7B |
| OpenOrca Phi 1.5 | 2023-09 | 4k | 1.5B |
| LlongOrca 13B 16K | 2023-08 | 16k | 13B |
| OpenOrca Platypus2 13B | 2023-08 | 4k | 13B |
| LlongOrca 7B 16K | 2023-08 | 16k | 7B |
| OpenOrca x OpenChat 13B | 2023-07 | 4k | 13B |
| OpenOrca 13B | 2023-07 | 4k | 13B |
Available From(2 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Mistral 7B OpenOrca | Together AI | $0.2 | $0.2 | Serverless |
| Mistral 7B OpenOrca | Fireworks AI | $0.2 | $0.2 | Provisioned |
Frequently Asked Questions
- What is OpenOrca used for?
- OpenOrca is used for coding. The family description and listed model capabilities point to those workloads as the best fit.
- How does OpenOrca compare to OpenChat?
- OpenOrca by Alignment Lab AI is strongest where you need coding, while OpenChat by Alignment Lab AI is the closest related family to check for coding. OpenOrca has 10 listed variants and reaches up to 32k context, while OpenChat reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
- Which OpenOrca model should I use?
- For the lowest listed input price, start with Mistral 7B OpenOrca through Fireworks AI at $0.2/1M input tokens. For the most capable/latest local choice, evaluate Mixtral 8x7B SlimOrca with 32k context.
Related Model Families
Models(10)
Mixtral 8x7B SlimOrca
Mistral 7B SlimOrca
Mistral 7B OpenOrca
Mistral 7B OpenOrca Platypus
OpenOrca Phi 1.5
LlongOrca 13B 16K
OpenOrca Platypus2 13B
LlongOrca 7B 16K
OpenOrca x OpenChat 13B
OpenOrca 13B