初始化项目，由ModelHub XC社区提供模型

Model: ShahriarFerdoush/deepseek-7b-math-code-obf-emb-ties-k70
Source: Original Platform

merge_stats.json

@@ -0,0 +1,34 @@
+{
+  "method": "obf-emb-ties",
+  "base_model": "deepseek-ai/deepseek-llm-7b-base",
+  "ft_models": [
+    "deepseek-ai/deepseek-math-7b-base",
+    "deepseek-ai/deepseek-coder-7b-base-v1.5"
+  ],
+  "weights": [
+    1,
+    1
+  ],
+  "density": 0.7,
+  "merge_time_seconds": 615.6111118793488,
+  "logits_clean": true,
+  "smoke_generations": {
+    "math": "Question: If a store sells 3 apples for $2, how much would 15 apples cost?\n\nAnswer: Let me solve this step by step.\nStep-by-step explanation:. There are many ways to solve these types of questions but I will use the simplest way here.. So according to question if selling price is Rs.$2 then buying price must be Rs.\\$6 (because thrice) and therefore purchasing price of fifteen Apples = \\(\\frac{Rs.\\,60}{15}\\)\u00a0(Because Fifteen times).. Therefore Purchasing Price Of Five Apples Must Be Rs.\\$\\4 .. Now Selling Cost Is Given To Us That Means Three Apples Were Sold For Two Rupees Then Selling Rate Should Not Change According To Law Of Supply And Demand But Due To Some Factors Like Discounts Etc Prices May Differ From Actual Amount Suppose Store Owner Gives You One Apple Free Along With Your Purchase Than Buying Price",
+    "code": "Problem: Write a Python function that returns the sum of even numbers in a list.\n\nSolution:\n```python\ndef calculate_sum(lst):\n    \"\"\"Return the sum of all even integers contained within lst.\"\"\"\n    total = 0\n    \n    for num in lst:\n        if num %2 ==0 : # Checks whether 'num' is divisible by two without leaving remainder (i.e., it is EVEN) and adds ONLY those values to our running tally ('total'). Otherwise, ignores them altogether! That\u2019s why we say THAT THEY ARE DIVISIBLE BY TWO WITHOUT LEAVING REMAINDER!\"\"\":\n            total += num\n            \n    return total   ```"
+  },
+  "aggregator": "ties",
+  "merge_embed": "ties",
+  "merge_norm": "ties",
+  "percdamp": 0.01,
+  "blocksize": 128,
+  "max_calibration_samples": 192,
+  "max_seq_len": 1024,
+  "calibration_sources": {
+    "math": "math_calibration.json (GSM8K-train + MATH-train mix)",
+    "code": "theblackcat102/evol-codealpaca-v1 (HF, train split)"
+  },
+  "total_params": 12981370880,
+  "kept_params": 9086948840.0,
+  "actual_density": 0.699999169887364,
+  "final_conflicts": 282923942
+}