R
RunPod7mo ago
octopus

Cannot run Cmdr+ on serverless, CohereForCausalLM not supported

I'm getting this error for all Cmdr+ models on serverless:
Error initializing vLLM engine: Model architectures ['CohereForCausalLM'] are not supported for now.
Error initializing vLLM engine: Model architectures ['CohereForCausalLM'] are not supported for now.
Although in vLLM issues we see that CohereForCausalLM is supported
6 Replies
haris
haris7mo ago
cc: @Alpay Ariyak
Alpay Ariyak
Alpay Ariyak7mo ago
Try dev image instead of stable
octopus
octopusOP7mo ago
tried that this is the error we get:
return future.result()/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 370, in _load_chat_template
2024-06-12T04:16:52.930112985Z [rank0]: with open(chat_template, "r") as f:
2024-06-12T04:16:52.930128535Z [rank0]: TypeError: expected str, bytes or os.PathLike object, not dict
return future.result()/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 370, in _load_chat_template
2024-06-12T04:16:52.930112985Z [rank0]: with open(chat_template, "r") as f:
2024-06-12T04:16:52.930128535Z [rank0]: TypeError: expected str, bytes or os.PathLike object, not dict
this is the model we tried: https://huggingface.co/alpindale/c4ai-command-r-plus-GPTQ
Alpay Ariyak
Alpay Ariyak7mo ago
Can you share your env vars
haris
haris7mo ago
cc: @octopus
octopus
octopusOP7mo ago
@Alpay Ariyak
No description
Want results from more Discord servers?
Add your server