RF Using GRPO

generation_config.json

@@ -3,5 +3,6 @@
   "bos_token_id": 128000,
   "eos_token_id": 128001,
   "max_length": 8192,
+  "pad_token_id": 0,
   "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9368df5e96fa39a7d3405b3c51c2aafc4448074d10d08defc74b53890a65790a
+oid sha256:015976e805b4759cecccc5e3a442d9ab54eda6ee538ef6156eb89d96831a2b7a
 size 4173992256

special_tokens_map.json

@@ -1,5 +1,23 @@
 {
-  "bos_token": "<|begin_of_text|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|end_of_text|>"
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f8d6a8a3decb619f82051a11315b0a2af91462f2af567d564d2188658a7e86
-size 17209961
+oid sha256:602f9c588f3b1b4c74e8afb51f75f5636120e3b418ba0f04c7562851e545a099
+size 17210130

tokenizer_config.json

@@ -73,7 +73,7 @@
       "special": true
     },
     "128009": {
-      "content": "<|im_end|>",
+      "content": "<|eot_id|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2050,12 +2050,20 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "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 %}",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
+  "max_length": 8192,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
   "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "stride": 0,
   "tokenizer_class": "PreTrainedTokenizer",
-  "unk_token": null
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }