phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Dont include 3B / 1B models for bedrock since they arent ondemand

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-18 06:30:02 -08:00
parent c39a3777b5
commit ceadaf1840
3 changed files with 0 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -35,8 +35,6 @@ The following models are available by default:
- `meta-llama/Llama-3.1-8B-Instruct (meta.llama3-1-8b-instruct-v1:0)`
- `meta-llama/Llama-3.1-70B-Instruct (meta.llama3-1-70b-instruct-v1:0)`
- `meta-llama/Llama-3.1-405B-Instruct-FP8 (meta.llama3-1-405b-instruct-v1:0)`
- `meta-llama/Llama-3.2-3B-Instruct (meta.llama3-2-3b-instruct-v1:0)`
- `meta-llama/Llama-3.2-1B-Instruct (meta.llama3-2-1b-instruct-v1:0)`
### Prerequisite: API Keys

8
llama_stack/providers/remote/inference/bedrock/bedrock.py
View file

@ -48,14 +48,6 @@ MODEL_ALIASES = [
"meta.llama3-1-405b-instruct-v1:0",
CoreModelId.llama3_1_405b_instruct.value,
),
build_model_alias(
"meta.llama3-2-3b-instruct-v1:0",
CoreModelId.llama3_2_3b_instruct.value,
),
build_model_alias(
"meta.llama3-2-1b-instruct-v1:0",
CoreModelId.llama3_2_1b_instruct.value,
),
]

10
llama_stack/templates/bedrock/run.yaml
View file

@ -85,16 +85,6 @@ models:
provider_id: bedrock
provider_model_id: meta.llama3-1-405b-instruct-v1:0
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: bedrock
provider_model_id: meta.llama3-2-3b-instruct-v1:0
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: bedrock
provider_model_id: meta.llama3-2-1b-instruct-v1:0
model_type: llm
shields: []
memory_banks: []
datasets: []