cron: add eval result for sakthai-coder-1.5b (metadata health check, run 15)

.eval_results/cron-eval-sakthai-coder-1.5b-2026-07-31-1.yaml

@@ -0,0 +1,155 @@
+target_model:
+  id: Nanthasit/sakthai-coder-1.5b
+  pipeline_tag: text-generation
+  library_name: transformers
+  base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+  downloads: 93
+  likes: 0
+  private: false
+  gated: false
+  last_modified: "2026-07-31T05:21:13.000Z"
+  model_age_days: 6.7969
+  model_type: llm
+  has_weights: true
+
+architecture:
+  base_model_type: qwen2
+  base_architectures: ["Qwen2ForCausalLM"]
+  base_hidden_size: 1536
+  base_num_hidden_layers: 28
+  base_num_attention_heads: 12
+  base_num_key_value_heads: 2
+  base_intermediate_size: 8960
+  base_vocab_size: 151936
+  base_max_position_embeddings: 32768
+  base_total_parameters: 1540000000
+  base_dtype: bfloat16
+  tie_word_embeddings: true
+  # GGUF-only repo: no config.json at root; architecture verified from
+  # Qwen/Qwen2.5-Coder-1.5B-Instruct config.json (fetched live 2026-07-31)
+
+repo_summary:
+  siblings_count: 1569
+  total_repo_bytes: 1289288771
+  total_gb: 1.289
+  has_weights: true
+  weight_file_count: 1
+  weight_bytes: 1117320768
+  weight_files: ["qwen2.5-coder-1.5b-instruct-q4_k_m.gguf"]
+  config_present: false
+  tokenizer_present: false
+  chat_template_present: true
+  readme_present: true
+  readme_size_bytes: 19380
+  weight_note: "Single Q4_K_M GGUF (1.12 GB) for llama.cpp/Ollama; tokenizer and chat template are embedded in the GGUF, hence no standalone config.json/tokenizer files. Repo carries a stray dev environment (.venv/, .pytest_cache/, .hypothesis/, .ruff_cache/, .superpowers/, .usage.json) from an over-eager push — documented in README, cleanup commit planned."
+
+benchmarks:
+  model_index_count: 1
+  metrics_count: 4
+  all_verified: false
+  pending_metrics: 4
+  entries:
+    - dataset: openai_humaneval
+      metric: pass@1
+      value: 74.4
+      verified: false
+      note: base-model reference (Qwen2.5-Coder-1.5B-Instruct), not re-run on fine-tune
+    - dataset: mbpp
+      metric: pass@1
+      value: 71.2
+      verified: false
+      note: base-model reference ceiling
+    - dataset: multipl_e
+      metric: pass@1
+      value: 65.3
+      verified: false
+      note: base-model reference ceiling
+    - dataset: SakThai Coding Suite (internal)
+      metric: pass@1
+      value: 100
+      verified: false
+      note: internal single-trial llama.cpp run (5/5 tasks, 2026-07-25)
+  notes: >
+    All 4 model-index metrics are verified: false (base-model references +
+    one internal single-trial suite). Independent 2026-07-31 3-trial llama.cpp
+    benchmark (.eval_results/benchmark-20260731_031937.yaml) on tool-calling
+    code-search got 0/3 tool calls, 0/3 valid JSON, 2/3 hallucinated files at
+    14.5 tps — a real gap vs the card's '5/5 tool tasks' claim that should be
+    reconciled. Recommended: sakthai-bench-v2 (500 rows, held-out tools).
+
+training:
+  dataset: Nanthasit/sakthai-combined-v6
+  dataset_size: 2309
+  dataset_note: "v6 + v7 (2,309 train / 115 test, verified 2026-07-31) + irrelevance-supplement (60 rows)"
+  training_method: QLoRA (4-bit) → GGUF Q4_K_M
+  eval_split: "115 held-out examples"
+  lora_config:
+    r: 16
+    alpha: 32
+  hardware: "Free Google Colab GPU (T4), $0 budget"
+  key_improvements:
+    - "Code + tool-calling in one session"
+    - "CPU-friendly Q4_K_M GGUF for llama.cpp / Ollama"
+
+card_quality:
+  license: apache-2.0
+  base_model_documented: true
+  base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+  tags_count: 16
+  tags: [code, coder, qwen2.5, qwen2.5-coder, gguf, llama-cpp, llama.cpp, ollama, code-generation, tool-calling, conversational, cpu-inference, small-language-model, offline, sakthai, house-of-sak]
+  datasets_cited: ["Nanthasit/sakthai-combined-v6", "Nanthasit/sakthai-combined-v7", "Nanthasit/sakthai-irrelevance-supplement"]
+  model_index_present: true
+  readme_size_bytes: 19380
+  widget_example: "Write a Python function that checks if a string is a palindrome, handling spaces and punctuation:"
+  deductions:
+    - "model-index metrics all verified: false (base refs + single-trial internal)"
+    - "card claims 5/5 tool tasks but 2026-07-31 benchmark showed 0/3 tool calls"
+    - "stray dev environment inflates repo to 1,568 files / 1.29 GB"
+  score: 88
+
+health_score:
+  overall: 43.8
+  components:
+    popularity: 0.93
+    momentum: 100
+    benchmarks: 0
+    card_quality: 88
+    repo_hygiene: 40
+  weights:
+    popularity: 0.20
+    momentum: 0.20
+    benchmarks: 0.25
+    card_quality: 0.20
+    repo_hygiene: 0.15
+
+sibling_comparison:
+  rank_by_downloads: 11
+  total_author_models: 19
+  max_sibling_downloads: 1599
+  models_with_positive_downloads: 11
+  velocity_rank: 9
+  max_sibling_velocity: 62.58
+  our_velocity: 13.68
+
+eval_type: metadata_cron
+eval_note: >
+  First cron eval snapshot for sakthai-coder-1.5b (run 15 of hf-eval-updater).
+  The family's code specialist: Qwen2.5-Coder-1.5B-Instruct QLoRA fine-tune
+  shipped as a 1.12 GB Q4_K_M GGUF for CPU use. Mid-pack momentum — 93
+  downloads, 13.68 dl/day (9/11 velocity, 11/19 downloads). Card quality is
+  high (19 KB README, badges, family table, honest caveats) but the model-index
+  carries only unverified base-reference scores, and a fresh 3-trial llama.cpp
+  tool-calling run failed to reproduce the card's 5/5 tool claim (0/3 tool
+  calls, hallucinated files). Repo hygiene is the weak spot: 40/100 due to a
+  stray dev environment. Next cycle: run sakthai-bench-v2, reconcile the
+  tool-calling claim, and land the cleanup commit.
+
+eval_metadata:
+  model: Nanthasit/sakthai-coder-1.5b
+  eval_date: "2026-07-31"
+  eval_time: "05:27:13Z"
+  schema: llm_cron_v1
+  age_days: 6.7969
+  days_since_last_update: 0.0042
+  download_velocity: 13.68
+  cron_run: 15