eval_type: metadata
model_id: Nanthasit/sakthai-context-1.5b-merged-v2
timestamp: "2026-08-01T07:30:00Z"
result_type: metadata_cron
source: hf-eval-results-updater
run_id: hf-eval-updater-20260801-073000
status: scheduled

metadata:
  pipeline_tag: text-generation
  base_model: Qwen/Qwen2.5-1.5B-Instruct
  framework: peft-lora
  license: apache-2.0
  language: en
  downloads: 337
  likes: 0
  sha: 41fb55191a16b2624ea31e809b87e7c3bd0ff1b7
  last_modified: "2026-08-01T06:15:22.000Z"
  tags:
    - transformers
    - safetensors
    - qwen2
    - qwen2.5
    - tool-calling
    - function-calling
    - agent
    - merged
    - cpu-inference
    - llama.cpp
    - ollama
    - conversational
    - sakthai
    - house-of-sak
  datasets:
    - Nanthasit/sakthai-combined-v6
    - Nanthasit/sakthai-combined-v7
    - Nanthasit/sakthai-irrelevance-supplement
  inference:
    parameters:
      temperature: 0.7
      max_new_tokens: 1024
      top_p: 0.8
      repetition_penalty: 1.1

model_index:
  - name: sakthai-context-1.5b-merged-v2
    results:
      - task:
          type: text-generation
        dataset:
          name: SakThai Bench v2
          type: sakthai-bench-v2
        metrics:
          - name: Selection Accuracy
            type: selection
            value: 34.9
            verified: false
          - name: Arguments Accuracy
            type: arguments
            value: 44.2
            verified: false
          - name: Strict Accuracy
            type: strict
            value: 34.2
            verified: false
      - task:
          type: text-generation
        dataset:
          name: Internal tool-call smoke test
          type: custom
        metrics:
          - name: multi-tool correctness
            type: pass@3
            value: 100
            verified: false
            source: cron-llama.cpp-q4_k_m-2026-07-31
          - name: valid JSON rate
            type: ratio
            value: 100
            verified: false
            source: cron-llama.cpp-q4_k_m-2026-07-31

notes: Metadata-based cron evaluation appended to .eval_results on 2026-08-01.