Add ZipNN structure

README.md

@@ -7,7 +7,62 @@ pipeline_tag: text-generation
 tags:
 - nlp
 library_name: transformers
+base_model:
+- upstage/solar-pro-preview-instruct
 ---
+# Disclaimer and Requirements
+
+This model is a clone of [**upstage/solar-pro-preview-instruct**](https://huggingface.co/upstage/solar-pro-preview-instruct) compressed using ZipNN. Compressed losslessly to 67% its original size, ZipNN saved ~15GB in storage and potentially ~40TB in data transfer **monthly**.
+
+### Requirement
+
+In order to use the model, ZipNN is necessary:
+```bash
+pip install zipnn
+```
+### Use This Model
+```python
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+from zipnn import zipnn_hf
+
+zipnn_hf()
+
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe = pipeline("text-generation", model="royleibov/solar-pro-preview-instruct-ZipNN-Compressed")
+pipe(messages)
+```
+```python
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from zipnn import zipnn_hf
+
+zipnn_hf()
+
+tokenizer = AutoTokenizer.from_pretrained("royleibov/solar-pro-preview-instruct-ZipNN-Compressed")
+model = AutoModelForCausalLM.from_pretrained(
+    "royleibov/solar-pro-preview-instruct-ZipNN-Compressed",
+    device_map="cuda",  
+    torch_dtype="auto",  
+    trust_remote_code=True,
+)
+```
+### ZipNN
+ZipNN also allows you to seemlessly save local disk space in your cache after the model is downloaded.
+
+To compress the cached model, simply run:
+```bash
+python zipnn_compress_path.py safetensors --model royleibov/solar-pro-preview-instruct-ZipNN-Compressed --hf_cache
+```
+
+The model will be decompressed automatically and safely as long as `zipnn_hf()` is added at the top of the file like in the [example above](#use-this-model).
+
+To decompress manualy, simply run:
+```bash
+python zipnn_decompress_path.py --model royleibov/solar-pro-preview-instruct-ZipNN-Compressed --hf_cache
+```
 
 <p align="left">
   <a href="https://go.upstage.ai/3Xk9J6X">
@@ -50,9 +105,13 @@ Below is an example inference code that details loading the model, applying the
 # Load model
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("upstage/solar-pro-preview-instruct")
+from zipnn import zipnn_hf
+
+zipnn_hf()
+
+tokenizer = AutoTokenizer.from_pretrained("royleibov/solar-pro-preview-instruct-ZipNN-Compressed")
 model = AutoModelForCausalLM.from_pretrained(
-    "upstage/solar-pro-preview-instruct",
+    "royleibov/solar-pro-preview-instruct-ZipNN-Compressed",
     device_map="cuda",  
     torch_dtype="auto",  
     trust_remote_code=True,