EPFL-LARA/lean-world-model-qwen3-4b-grpo
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: EPFL-LARA/lean-world-model-qwen3-4b-grpo
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-25 02:42:17 +08:00
commit fddfb5d2e3
22 changed files with 152925 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
example_output.json Normal file
View File

@@ -0,0 +1,33 @@
{
"model_id": "EPFL-LARA/lean-world-model-qwen3-4b-grpo",
"backend": "transformers",
"input": "import Mathlib\n\ntheorem demo (n : ℕ) : n + 0 = n := by sorry\n",
"prompt": "Solve the following problem with Lean 4 code and explanatory comments:\n\n```lean4\nimport Mathlib\n\n\ntheorem demo (n : ℕ) : n + 0 = n := by sorry\n```\n\nReplace every sorry statement with an appropriate proof. Provide a complete solution in the lean4 code block, annotated with Lean 4 compiler feedback blocks in the form `/- <feedback> ... </feedback> -/` at the appropriate locations.\n",
"response": "Here is the complete Lean 4 proof annotated with Lean 4 compiler feedback blocks:\n\n```lean4\nimport Mathlib\n\n-- Theorem: For any natural number n, n + 0 = n.\ntheorem demo (n : ℕ) : n + 0 = n := by\n /- <feedback>\n -- proof state:\n n : ℕ\n ⊢ n + 0 = n\n </feedback> -/\n induction n with\n /- <feedback>\n -- proof state:\n case zero\n ⊢ 0 + 0 = 0\n </feedback> -/\n | zero => rfl\n /- <feedback>\n -- proof state:\n ih : n + 0 = n\n case succ\n ⊢ n + 1 + 0 = n + 1\n </feedback> -/\n | succ n ih => simp_all\n```\n",
"lean_code": "import Mathlib\n\n-- Theorem: For any natural number n, n + 0 = n.\ntheorem demo (n : ℕ) : n + 0 = n := by\n /- <feedback>\n -- proof state:\n n : ℕ\n ⊢ n + 0 = n\n </feedback> -/\n induction n with\n /- <feedback>\n -- proof state:\n case zero\n ⊢ 0 + 0 = 0\n </feedback> -/\n | zero => rfl\n /- <feedback>\n -- proof state:\n ih : n + 0 = n\n case succ\n ⊢ n + 1 + 0 = n + 1\n </feedback> -/\n | succ n ih => simp_all",
"generation": {
"seed": 0,
"temperature": 0.3,
"top_p": 0.95,
"top_k": 0,
"min_p": 0.0,
"max_new_tokens": 2048,
"add_special_tokens": false
},
"environment": {
"torch": "2.9.0+cu129",
"transformers": "4.57.3",
"gpu": "NVIDIA H100 80GB",
"dtype": "bfloat16"
},
"verification": {
"lean_version": "4.15.0",
"compiled": true,
"original_theorem_type_checked": true,
"contains_sorry": false
},
"weight_sha256": {
"model-00001-of-00002.safetensors": "4524c20d5a992eb96bc1ed84eaa9e7d15347f232d9f8b21687228fd4912c4ede",
"model-00002-of-00002.safetensors": "63dd64e9808d77f802c848b997c2cde09a1add8563259db29ce3b098133467b6"
}
}