Computational Model Studio · Model release
Llama 3.1 Instruct
Meta multilingual instruction-tuned Llama 3.1 text model release with size variants.
Developer: Meta · Last verified:
What it is designed to do
Generate multilingual assistant-style text responses from text prompts.
- Primary contribution
- generation transformation
- Input
- text
- Output
- text, code (generated text, generated code)
Documented uses: Multilingual assistant-style dialogue and text generation.
Access and deployment
- Llama 3.1 8B Instruct publisher weights — restricted. Agree to the Llama 3.1 conditions and share contact information to request access. Artifact documentation Variant: Llama 3.1 8B Instruct. Local hardware requirements have not been verified. Llama 3.1 Community License.
- Llama 3.1 8B Instruct Q4_K_M GGUF — available. Public third-party quantized file; applicable Meta Llama 3.1 terms remain in force. Artifact documentation Variant: Llama 3.1 8B Instruct. Local hardware requirements have not been verified. The full artifact-specific rights document has not been separately reviewed; follow the stated publisher or upstream license conditions.
Variants
- Llama 3.1 8B Instruct — The 8B instruction-tuned size has a publisher-hosted gated repository.
Technical profile and review notes
- Construction
- learned
- Representation
- neural
- Normalized architecture tags
- No normalized architecture tag assigned
- Lifecycle
- Unknown from reviewed sources
Inclusion rationale: Adds a gated downloadable instruction-tuned model with publisher-specific license and size-scoped artifacts.
Limitations
- Publisher documentation warns outputs may be inaccurate, biased, or objectionable.
- Tool-use formatting support does not itself execute external tools.
Sources and related Studio records
Sources
Connections
- In areaComputational Models
- In familyLlama 3.1
- VariantLlama 3.1 8B Instruct
- Supports functionGenerate text