phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update Cerebras from Llama 3.1 to 3.3

Browse source
This commit is contained in:
Henry Tu 2024-12-17 13:54:21 -08:00
parent fbca51d6da
commit a63f920a02
3 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/source/distributions/self_hosted_distro/cerebras.md
View file

@ -23,7 +23,7 @@ The following environment variables can be configured:
The following models are available by default:
- `meta-llama/Llama-3.1-8B-Instruct (llama3.1-8b)`
- `meta-llama/Llama-3.1-70B-Instruct (llama3.1-70b)`
- `meta-llama/Llama-3.3-70B-Instruct (llama-3.3-70b)`
### Prerequisite: API Keys

4
llama_stack/providers/remote/inference/cerebras/cerebras.py
View file

@ -41,8 +41,8 @@ model_aliases = [
CoreModelId.llama3_1_8b_instruct.value,
),
build_model_alias(
"llama3.1-70b",
CoreModelId.llama3_1_70b_instruct.value,
"llama-3.3-70b",
CoreModelId.llama3_3_70b_instruct.value,
),
]

4
llama_stack/templates/cerebras/run.yaml
View file

@ -56,9 +56,9 @@ models:
provider_model_id: llama3.1-8b
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-70B-Instruct
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: cerebras
provider_model_id: llama3.1-70b
provider_model_id: llama-3.3-70b
model_type: llm
- metadata:
embedding_dimension: 384