Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

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

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a21e71b12ed71ef7066dfe8d36c881a4bb868c847bf7ac1a1430ebfe0c116d
+size 7965872756

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76c2cd9a67241fc45f60dcfe8af451f0f14d973fd0e1d9c71633c4b0546416a
+size 4526429651

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<|eoj|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14592d1d33e4d1fa07f59725265cf8655843c5e399136e16411b5a81665ac21
+size 11418450

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|eoj|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|eoj|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_meta.json

@@ -0,0 +1,20 @@
+{
+  "timestamp": "20250902_165343",
+  "model_class": "SequentialMultiTokenLM",
+  "n_future": 3,
+  "vocab_size": 151647,
+  "save_steps": 3080,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.0,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "tokenizer_name_or_path": "/home/alexandrlukashow/text2json/debug_training/checkpoints/checkpoint-43120",
+  "tokenizer_len_at_save": 151647,
+  "tokenizer_pad_token_id": 151643,
+  "dtype_hint": "float32",
+  "head_grad_scales": [
+    1.0,
+    1.0,
+    1.0
+  ],
+  "norm_grad_scales": true
+}