Skip to content

Instantly share code, notes, and snippets.

@xinuc
Created August 28, 2025 10:00
Show Gist options
  • Select an option

  • Save xinuc/a0865d588ce4cac17ce9c5493a73ea5c to your computer and use it in GitHub Desktop.

Select an option

Save xinuc/a0865d588ce4cac17ce9c5493a73ea5c to your computer and use it in GitHub Desktop.
Error
Running: qwen2.5-coder-0.5b:Q5_0
Type '/exit' or press Ctrl+C to quit
Type '/help' to see available commands
hello
> ❌ Error: Failed to get response from the model. Please try again.
Type your message or use /help for commands...
[2025-08-28 16:59:19.173] [INFO] Successfully saved model 'qwen2.5-coder-0.5b:Q5_0' to configuration file
[2025-08-28 16:59:19.173] [INFO] Registering LLM engine for lazy loading: qwen2.5-coder-0.5b:Q5_0
[2025-08-28 16:59:19.173] [INFO] Engine created successfully for model: qwen2.5-coder-0.5b:Q5_0
[2025-08-28 16:59:19.412] [INFO] Successfully provided download progress for model: qwen2.5-coder-0.5b:Q5_0 (100.0%)
[2025-08-28 16:59:23.456] [INFO] [Thread 1804791808] Processing streaming inference chat completion request for model 'qwen2.5-coder-0.5b:Q5_0'
[2025-08-28 16:59:23.457] [INFO] Engine ID 'qwen2.5-coder-0.5b:Q5_0' was unloaded due to inactivity. Attempting to reload.
[2025-08-28 16:59:23.457] [INFO] Stored engine type for 'qwen2.5-coder-0.5b:Q5_0': 'llama-metal'
[2025-08-28 16:59:23.457] [INFO] Creating new inference engine instance for reload...
[2025-08-28 16:59:23.457] [INFO] Reloading model from path: /Users/xinuc/Library/Application Support/Kolosal/models/qwen2.5-coder-0.5b-instruct-q5_0.gguf
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 8192
[2025-08-28 16:59:24.687] [INFO] Successfully reloaded model for engine 'qwen2.5-coder-0.5b:Q5_0'
[2025-08-28 16:59:24.687] [INFO] Successfully reloaded LLM engine ID 'qwen2.5-coder-0.5b:Q5_0'.
[2025-08-28 16:59:24.687] [INFO] Processing OpenAI chat completion for model 'qwen2.5-coder-0.5b:Q5_0'
[2025-08-28 16:59:24.910] [INFO] [Thread 1804791808] Completed streaming response for model 'qwen2.5-coder-0.5b:Q5_0'
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment