初始化项目，由ModelHub XC社区提供模型

Model: Nanthasit/sakthai-context-1.5b-merged-v2 Source: Original Platform
2026-08-21 08:23:17 +08:00
commit 4f626972fa
22 changed files with 1695 additions and 0 deletions
--- a/.eval_results/cron-eval-sakthai-context-1.5b-merged-v2-20260801T0730Z.yaml
+++ b/.eval_results/cron-eval-sakthai-context-1.5b-merged-v2-20260801T0730Z.yaml
@@ -0,0 +1,83 @@
+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.