My first agent template error
😃: Hello
🤖: Step 1
🤖: Error in generating model output:
422 Client Error: Unprocessable Entity for url: https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: qbTRPsfWZvqCDupHXjR_Q)
Input validation error: inputs tokens + max_new_tokens must be <= 32768. Given: 62563 inputs tokens and 2096 max_new_tokens
Make sure 'text-generation' task is supported by the model.
🤖: Step 1 | Input-tokens:29,812 | Output-tokens:366 | Duration: 0.14
🤖: -----
🤖: Step 2
🤖: Error in generating model output:
422 Client Error: Unprocessable Entity for url: https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: QVBfI0pOFVsXbzgFPI1gQ)
Input validation error: inputs tokens + max_new_tokens must be <= 32768. Given: 62720 inputs tokens and 2096 max_new_tokens
Make sure 'text-generation' task is supported by the model.
🤖: Step 2 | Input-tokens:29,812 | Output-tokens:366 | Duration: 0.13
🤖: -----
🤖: Step 3
🤖: Error in generating model output:
422 Client Error: Unprocessable Entity for url: https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: gRi8BjipkU6d78SFZUlH4)
Input validation error: inputs tokens + max_new_tokens must be <= 32768. Given: 62879 inputs tokens and 2096 max_new_tokens
Make sure 'text-generation' task is supported by the model.
🤖: Step 3 | Input-tokens:29,812 | Output-tokens:366 | Duration: 0.12
🤖: -----
🤖: Step 4
🤖: Error in generating model output:
422 Client Error: Unprocessable Entity for url: https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: 4zgXd2nSfjsRYJW9_zr3_)
Input validation error: inputs tokens + max_new_tokens must be <= 32768. Given: 63040 inputs tokens and 2096 max_new_tokens
Make sure 'text-generation' task is supported by the model.
🤖: Step 4 | Input-tokens:29,812 | Output-tokens:366 | Duration: 0.14
🤖: -----
🤖: Step 5
🤖: Error in generating model output:
422 Client Error: Unprocessable Entity for url: https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: cLRwYf0Xf32aQbicqQLa_)
Input validation error: inputs tokens + max_new_tokens must be <= 32768. Given: 63201 inputs tokens and 2096 max_new_tokens
Make sure 'text-generation' task is supported by the model.
🤖: Step 5 | Input-tokens:29,812 | Output-tokens:366 | Duration: 0.12
🤖: -----
🤖: Step 6
🤖: Error in generating model output:
422 Client Error: Unprocessable Entity for url: https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: RFrHd-TPgvDYTnlhrnsyL)
Input validation error: inputs tokens + max_new_tokens must be <= 32768. Given: 63361 inputs tokens and 2096 max_new_tokens
Make sure 'text-generation' task is supported by the model.
🤖: Step 6 | Input-tokens:29,812 | Output-tokens:366 | Duration: 0.13
🤖: -----
🤖: Step 7
🤖: Reached max steps.
🤖: Step 7 | Input-tokens:29,812 | Output-tokens:366 | Duration: 0.13
🤖: -----
🤖: Final answer:
Error in generating final LLM output:
422 Client Error: Unprocessable Entity for url: https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: 4wsD2DWM7_-1kpUVAtClF)
Input validation error: inputs tokens + max_new_tokens must be <= 32768. Given: 61575 inputs tokens and 2096 max_new_tokens
Make sure 'text-generation' task is supported by the model.
Is there a reason why this is throwing up an error?
same, any idea how to fix?
You watch your Billing credits for API, and then you need pay for pro or create new account