Upload folder using huggingface_hub

README.md

@@ -0,0 +1,47 @@
+---
+language: en
+license: mit  # Adjust based on original model
+tags:
+  - pruning
+  - sparse
+  - atropos
+  - code-generation
+---
+
+# gpt2-mild_pruning
+
+This is a pruned version of [gpt2](https://huggingface.co/gpt2)
+generated as part of the Atropos pruning exercise.
+
+## Pruning Details
+
+- **Strategy:** mild_pruning
+- **Method:** PyTorch magnitude-based unstructured pruning
+- **Generated by:** Atropos pruning exercise scripts
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("gpt2-mild_pruning")
+tokenizer = AutoTokenizer.from_pretrained("gpt2-mild_pruning")
+```
+
+## About Atropos
+
+[Atropos](https://github.com/its-not-rocket-science/atropos) estimates ROI
+for pruning and quantization optimizations in LLM deployments.
+
+This model was pruned to validate Atropos projections against actual results.
+
+## Citation
+
+If you use this model, please cite the original model and Atropos:
+
+```bibtex
+@software{atropos,
+  title = {Atropos: ROI Estimation for LLM Pruning},
+  year = {2026},
+}
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "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": "4.48.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3bfcca8987fdf35e40dff0200d864fad7207cc83da9887a79b33a1dec7ae6c
+size 497774208

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}