Upload task output c3804959-b394-48b3-bfdc-2692e9b5150e

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|PAD_TOKEN|>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -1,29 +1,30 @@
 {
   "architectures": [
-    "LlamaForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
-  "head_dim": 64,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 1536,
   "initializer_range": 0.02,
-  "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": 32,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151646,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
+  "unsloth_version": "2024.9",
   "use_cache": false,
-  "vocab_size": 49152
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }

generation_config.json

@@ -1,6 +1,8 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_length": 131072,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151646,
   "transformers_version": "4.51.3"
 }

loss.txt

@@ -1 +1 @@
-97,1.3358079195022583
+178,0.4410938620567322

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a00d17c3c5b290027497ca91630318b3d6522a05435320a47ce40d268982c9
-size 3422777952
+oid sha256:d46dff10d4ecf0c8cb1debbb55e0ead0f64b3fe5f522691e0cba2ac1beece971
+size 3087467144

special_tokens_map.json

@@ -1,30 +1,8 @@
 {
   "additional_special_tokens": [
-    "<|endoftext|>",
     "<|im_start|>",
-    "<|im_end|>",
-    "<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>"
+    "<|im_end|>"
   ],
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
@@ -33,14 +11,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<empty_output>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<|PAD_TOKEN|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d27c493c729a66ecefc837280b05d948b1ed50d130eebdbf911b1b36cf38ed7
-size 3522656
+oid sha256:9479047c22047670077878de944c696032b1a81049beeb6e99fbda7fb93e395a
+size 11418456

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
+    "151643": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
@@ -9,7 +9,7 @@
       "single_word": false,
       "special": true
     },
-    "1": {
+    "151644": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -17,7 +17,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "151645": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
@@ -25,112 +25,8 @@
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<repo_name>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<reponame>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<file_sep>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "<filename>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": "<gh_stars>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": "<issue_start>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": "<issue_comment>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": "<issue_closed>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<jupyter_start>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "12": {
-      "content": "<jupyter_text>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "13": {
-      "content": "<jupyter_code>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "14": {
-      "content": "<jupyter_output>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "15": {
-      "content": "<jupyter_script>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "16": {
-      "content": "<empty_output>",
+    "151646": {
+      "content": "<|PAD_TOKEN|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -139,32 +35,19 @@
     }
   },
   "additional_special_tokens": [
-    "<|endoftext|>",
     "<|im_start|>",
-    "<|im_end|>",
-    "<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>"
+    "<|im_end|>"
   ],
-  "bos_token": "<|endoftext|>",
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<empty_output>",
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
   "padding_side": "left",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>",
-  "vocab_size": 49152
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }