Upload task output 3f496480-8751-422b-9a37-db9d7b853f96

added_tokens.json

@@ -1,24 +0,0 @@
-{
-  "</tool_call>": 151658,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}

config.json

@@ -1,30 +1,29 @@
 {
   "architectures": [
-    "Qwen2ForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "eos_token_id": 151643,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 896,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 4864,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 24,
-  "model_type": "qwen2",
-  "num_attention_heads": 14,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
   "num_hidden_layers": 24,
-  "num_key_value_heads": 2,
-  "pad_token_id": 151654,
-  "rms_norm_eps": 1e-06,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
-  "unsloth_fixed": true,
   "use_cache": false,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 49152
 }

generation_config.json

@@ -1,8 +1,6 @@
 {
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_length": 32768,
-  "max_new_tokens": 2048,
-  "pad_token_id": 151654,
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "transformers_version": "4.51.3"
 }

loss.txt

@@ -1 +1 @@
-112,1.5415836572647095
+97,1.3358079195022583

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46203b9a7a49d773f9074e69d47808aa653966a9cd85a1ebccabeb2b83c0c254
-size 988097824
+oid sha256:76a00d17c3c5b290027497ca91630318b3d6522a05435320a47ce40d268982c9
+size 3422777952

special_tokens_map.json

@@ -1,19 +1,30 @@
 {
   "additional_special_tokens": [
+    "<|endoftext|>",
     "<|im_start|>",
     "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
   ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
@@ -22,7 +33,14 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|vision_pad|>",
+    "content": "<empty_output>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:7d27c493c729a66ecefc837280b05d948b1ed50d130eebdbf911b1b36cf38ed7
+size 3522656

tokenizer_config.json

@@ -1,8 +1,7 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "151643": {
+    "0": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
@@ -10,7 +9,7 @@
       "single_word": false,
       "special": true
     },
-    "151644": {
+    "1": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -18,7 +17,7 @@
       "single_word": false,
       "special": true
     },
-    "151645": {
+    "2": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
@@ -26,183 +25,146 @@
       "single_word": false,
       "special": true
     },
-    "151646": {
-      "content": "<|object_ref_start|>",
+    "3": {
+      "content": "<repo_name>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151647": {
-      "content": "<|object_ref_end|>",
+    "4": {
+      "content": "<reponame>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151648": {
-      "content": "<|box_start|>",
+    "5": {
+      "content": "<file_sep>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151649": {
-      "content": "<|box_end|>",
+    "6": {
+      "content": "<filename>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151650": {
-      "content": "<|quad_start|>",
+    "7": {
+      "content": "<gh_stars>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151651": {
-      "content": "<|quad_end|>",
+    "8": {
+      "content": "<issue_start>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151652": {
-      "content": "<|vision_start|>",
+    "9": {
+      "content": "<issue_comment>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151653": {
-      "content": "<|vision_end|>",
+    "10": {
+      "content": "<issue_closed>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151654": {
-      "content": "<|vision_pad|>",
+    "11": {
+      "content": "<jupyter_start>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151655": {
-      "content": "<|image_pad|>",
+    "12": {
+      "content": "<jupyter_text>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151656": {
-      "content": "<|video_pad|>",
+    "13": {
+      "content": "<jupyter_code>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151657": {
-      "content": "<tool_call>",
+    "14": {
+      "content": "<jupyter_output>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
+      "special": true
     },
-    "151663": {
-      "content": "<|repo_name|>",
+    "15": {
+      "content": "<jupyter_script>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "151664": {
-      "content": "<|file_sep|>",
+    "16": {
+      "content": "<empty_output>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
   "additional_special_tokens": [
+    "<|endoftext|>",
     "<|im_start|>",
     "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
   ],
-  "bos_token": null,
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
-  "pad_token": "<|vision_pad|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<empty_output>",
   "padding_side": "left",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
 }