LLaMA Models by AI at Meta
1 model2023Up to 2K ctx
About
Meta's original LLaMA (Large Language Model Meta AI) family released in February 2023. Available in 7B, 13B, 33B, and 65B parameter sizes. Demonstrated that smaller models trained on more data could match or exceed larger counterparts.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
1 in view
LLaMA 7BCurrent
Use when the workload needs 2K context and 7B parameters.
2023-022K context7B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| LLaMA 7B | Use when the workload needs 2K context and 7B parameters. | 2023-02 | 2K context7B parameters | Current |
Release Timeline
1 release group2023-02
1 current
LLaMA 7B
Current2K context7B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| LLaMA 7B | 2023-02 | 2K | 7B |
Available From(1 provider)
Frequently Asked Questions
- What is LLaMA used for?
- Meta's original LLaMA (Large Language Model Meta AI) family released in February 2023.
- How does LLaMA compare to Chameleon?
- LLaMA by AI at Meta is strongest where you need its listed use cases, while Chameleon by AI at Meta is the closest related family to check for coding. LLaMA has 1 listed variant and reaches up to 2K context, while Chameleon reaches up to 4K context, so compare the specs and pricing tables before choosing a production model.
- Which LLaMA model should I use?
- If price is the main constraint, use the pricing table first because LLaMA does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate LLaMA 7B with 2K context.
