Upload fine-tuned model + card

README.md

@@ -0,0 +1,20 @@
+---
+license: apache-2.0
+base_model: EleutherAI/pythia-1.4b
+datasets:
+- bigcode/the-stack
+library_name: transformers
+tags:
+- memorization
+- fine-tuned
+---
+
+# pythia-1.4b-code-run2
+
+Pythia-1.4B fine-tuned for one epoch on a 1M-sequence (128-token) sample of The Stack.
+
+This is a **run2** model, fine-tuned on a 1M sample drawn disjoint from run1. It provides the fresh held-out data used to evaluate the memorization-prediction classifier (predict-before-training validation). The matching **run1** model supplies the labels used to train the classifier.
+
+- Base model, EleutherAI/pythia-1.4b
+- Dataset, The Stack (bigcode/the-stack)
+- Training, 1 epoch, seq len 128, learning rate 5e-5, cosine schedule, seed 42

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": null,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.9.0",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "5.9.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323c5892b1401dc3bf9358c5759aee74f783dbeda2e11e0a76a868f64f6dbc11
+size 2829330208

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>"
+}