RF Using GRPO

config.json

@@ -27,7 +27,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
-  "unsloth_version": "2025.4.1",
+  "unsloth_version": "2025.4.3",
   "use_cache": true,
   "vocab_size": 110592
 }

generation_config.json

@@ -3,6 +3,6 @@
   "bos_token_id": 100257,
   "eos_token_id": 100257,
   "max_length": 131072,
-  "pad_token_id": 100257,
+  "pad_token_id": 0,
   "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8387d63b6c1e210c4adf853759fe5fd0ee86d94198e6ed8e87552ca05dd3cf5
+oid sha256:9618b9b211c9b614698c288c6a30baa0cf6a4d78036dfd5e8a88bc593c32ef42
 size 3171119736

special_tokens_map.json

@@ -1,6 +1,86 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -158,7 +158,7 @@
     },
     {
       "id": 100273,
-      "content": "<|endofturn|>",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -176,7 +176,7 @@
     },
     {
       "id": 100275,
-      "content": "<|im_end|>",
+      "content": "<|endofturn|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -100807,9 +100807,9 @@
       "<|_unuse_missing_100270|>": 100270,
       "<|_unuse_missing_100271|>": 100271,
       "<|im_start|>": 100272,
-      "<|endofturn|>": 100273,
+      "<|im_end|>": 100273,
       "<|stop|>": 100274,
-      "<|im_end|>": 100275,
+      "<|endofturn|>": 100275,
       "<|endofprompt|>": 100276,
       "Ġì§ĢìĽIJíķĺëĬĶ": 100277,
       "ĠíķłìķĦë²Ħ": 100278,

tokenizer_config.json

@@ -138,7 +138,7 @@
       "special": true
     },
     "100273": {
-      "content": "<|endofturn|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -154,7 +154,7 @@
       "special": true
     },
     "100275": {
-      "content": "<|im_end|>",
+      "content": "<|endofturn|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -434,13 +434,70 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
+  "padding_side": "left",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }