github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-07-19 09:49:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix model name used in apolo-flow

Browse Source
This commit is contained in:
Yevhenii Semendiak 2024-10-31 17:48:13 +02:00
parent ea7bfe442b
commit ad4d2af591
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.neuro/live.yaml
View File

@ -65,14 +65,14 @@ jobs:
VLLM_API_BASE: http://${{ inspect_job('vllm').internal_hostname_named }}:8000/v1 VLLM_API_BASE: http://${{ inspect_job('vllm').internal_hostname_named }}:8000/v1
OLLAMA_API_BASE: http://${{ inspect_job('ollama').internal_hostname_named }}:11434 OLLAMA_API_BASE: http://${{ inspect_job('ollama').internal_hostname_named }}:11434
POSTGRES_HOST: ${{ inspect_job('pgvector').internal_hostname_named }} POSTGRES_HOST: ${{ inspect_job('pgvector').internal_hostname_named }}
VLLM_MODEL: meta-llama/Meta-Llama-3-8B-Instruct VLLM_MODEL: meta-llama/Meta-Llama-3.1-8B-Instruct
VLLM_TOKENIZER: meta-llama/Meta-Llama-3-8B-Instruct VLLM_TOKENIZER: meta-llama/Meta-Llama-3.1-8B-Instruct
HUGGINGFACE_TOKEN: secret:HF_TOKEN HUGGINGFACE_TOKEN: secret:HF_TOKEN
vllm: vllm:
image: vllm/vllm-openai:v0.6.1.post2 image: vllm/vllm-openai:v0.6.1.post2
name: vllm name: vllm
preset: a100x1 preset: H100x1
detach: true detach: true
http_port: "8000" http_port: "8000"
volumes: volumes:
@ -101,7 +101,7 @@ jobs:
image: ollama/ollama:0.1.35 image: ollama/ollama:0.1.35
volumes: volumes:
- ${{ volumes.ollama_models.ref_rw }} - ${{ volumes.ollama_models.ref_rw }}
preset: a100x1 preset: H100x1
detach: true detach: true
env: env:
MODEL: "nomic-embed-text" MODEL: "nomic-embed-text"