learn2pro/nanogpt

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,11 @@
+{
+  "architectures": [
+    "NanoGPT"
+  ],
+  "n_block": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 6,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3"
+}

README.md

@@ -0,0 +1,51 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: nanogpt
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# nanogpt
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 12
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- training_steps: 10000
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,11 @@
+{
+  "architectures": [
+    "NanoGPT"
+  ],
+  "n_block": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 6,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f337a133115ac63f253c0ac86118ae66c8b3176c4e2767b3b36be7388534042
+size 897639200

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84faf10ea136426e50ffaa8cf0244c8ca55a2087635f35959d9223dac3913dad
+size 5368