[ADD]: first model push

README.md

@@ -1,3 +1,37 @@
 ---
 license: apache-2.0
+datasets:
+- databricks/databricks-dolly-15k
+language:
+- en
+metrics:
+- rouge
+base_model:
+- openai-community/gpt2
+pipeline_tag: text-generation
 ---
+
+# DistillLens-gpt2-base
+
+[paper](https://arxiv.org/abs/2602.13567) | [code](https://github.com/manishdhakal/DistillLens)
+
+**DistillLens-gpt2-base** is a gpt2-base (120M) model distilled from [gpt2-xlarge (1.5B)](https://huggingface.co/MiniLLM/teacher-gpt2-1.5B) on [databricks-dolly-15k](https://huggingface.co/datasets/aisquared/databricks-dolly-15k).
+
+## Method
+
+<p align='left'>
+    <img src="architecture.png" width="1000">
+</p>
+
+**Note**: DistillLens requires a [GPT2-Base](https://huggingface.co/openai-community/gpt2) for initilization to perform the distillation.
+
+
+## Citation
+```
+@article{dhakal2026distilllens,
+  title={DistillLens: Symmetric Knowledge Distillation Through Logit Lens},
+  author={Dhakal, Manish and Jinadu, Uthman and Budathoki, Anjila and Sunderraman, Rajshekhar and Ding, Yi},
+  journal={arXiv preprint arXiv:2602.13567},
+  year={2026}
+}
+```

config.json

@@ -0,0 +1,42 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "is_model_parallel": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": null,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9d20d1909bdfcd7ef7802dac552e1943c07b3e8b8c71f4a4746e57b0dcf7e6
+size 248894656

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}