Update README.md

README.md

@@ -9,4 +9,52 @@ tags:
 - mistral
 - mergekit
 - merge
----
+---
+
+
+## Mistral-Depth-UP-Scaled-9B
+
+An auto-regressive causal LM created by combining 2x finetuned mistral 7B into one.
+
+## Benchmarks
+Coming soon.
+
+## Usage : 
+
+``` python
+# Load in4Bit
+
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+import torch
+
+nf4_config = BitsAndBytesConfig(
+   load_in_4bit=True,
+   bnb_4bit_quant_type="nf4",
+   bnb_4bit_use_double_quant=True,
+   bnb_4bit_compute_dtype=torch.bfloat16
+)
+model = AutoModelForCausalLM.from_pretrained(
+    "ayoubkirouane/Mistral-Depth-UP-Scaled-9B",
+    device_map='auto',
+    quantization_config=nf4_config,
+    use_cache=False
+)
+tokenizer = AutoTokenizer.from_pretrained("ayoubkirouane/Mistral-Depth-UP-Scaled-9B")
+
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = "right"
+
+def generate_response(prompt, model , max_new_tokens):
+  encoded_input = tokenizer(prompt,  return_tensors="pt", add_special_tokens=True)
+  model_inputs = encoded_input.to('cuda')
+
+  generated_ids = model.generate(**model_inputs, max_new_tokens=max_new_tokens, do_sample=True, pad_token_id=tokenizer.eos_token_id)
+
+  decoded_output = tokenizer.batch_decode(generated_ids)
+
+  return decoded_output[0].replace(prompt, "")
+
+
+generate_response(prompt="What is GANs ?", model=model , max_new_tokens=100)
+
+```