---
eval_type: "inference-check"
model: "Nanthasit/sakthai-coder-1.5b"
timestamp: "2026-07-30T23:18:45+00:00"
prompt: "Write a Python function to check if a number is prime."
max_new_tokens: 100
status: "BLOCKED"
blockers:
  - "DNS failure: api-inference.huggingface.co does not resolve in this environment"
  - "Model is GGUF-only (no SafeTensors) — not loadable by standard HF Inference API"
  - "HF Inference Providers API: model_not_supported — not supported by any enabled provider"
  - "No llama.cpp available locally to run GGUF inference"
recommendation: "Convert model to SafeTensors format and push to same repo, or deploy as HF Inference Endpoint, or install llama.cpp locally for GGUF evaluation"
attempted_endpoints:
  - "POST api-inference.huggingface.co/models/Nanthasit/sakthai-coder-1.5b → DNS failure (exit code 6)"
  - "POST router.huggingface.co/hf/v1/chat/completions → 404 Not Found"
  - "InferenceClient.chat_completion(model='Nanthasit/sakthai-coder-1.5b') → BadRequestError: model_not_supported"
  - "InferenceClient.text_generation(model='Nanthasit/sakthai-coder-1.5b') → StopIteration (model not loadable)"
base_model_check:
  model: "Qwen/Qwen2.5-Coder-1.5B-Instruct"
  result: "model_not_supported by any enabled provider"
model_metadata:
  pipeline_tag: "text-generation"
  library: "transformers"
  format: "GGUF"
  base_model: "Qwen/Qwen2.5-Coder-1.5B-Instruct"