Hugging Face's logo

Spaces:
adaptiveaiventures
/
llama2-interference
Runtime error

App Files Community
adaptiveaiventures commited on
Commit
b2c1ee4
·
verified ·
1 Parent(s): d9fbb15

Update Dockerfile

Browse files
Files changed (1) hide show
  1. Dockerfile +1 -1
Dockerfile CHANGED
@@ -4,4 +4,4 @@ FROM ghcr.io/huggingface/text-generation-inference:latest
4
  ENV MODEL_ID="adaptiveaiventures/Llama-2-7b-chat-finetune"
5
 
6
  # Run the TGI server
7
- CMD ["--model-id", "${MODEL_ID}", "--port", "8080", "--num-shard", "1", "--dtype", "bfloat16", "--max-batch-prefill-tokens", "1024", "--disable-custom-kernels"]
 
4
  ENV MODEL_ID="adaptiveaiventures/Llama-2-7b-chat-finetune"
5
 
6
  # Run the TGI server
7
+ CMD ["--model-id", "adaptiveaiventures/Llama-2-7b-chat-finetune", "--port", "8080", "--num-shard", "1", "--dtype", "bfloat16", "--max-batch-prefill-tokens", "1024", "--disable-custom-kernels"]