Update README.md

README.md

@@ -37,13 +37,13 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 ## Uses
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-```
+```python
 !pip install transformers
 !pip install  accelerate
 !pip install bitsandbytes
 ```
 
-```
+```python
 import os
 import torch
 import transformers
@@ -56,8 +56,7 @@ from transformers import (
 
 ```
 
-```
-
+```python
 model_name='kimou605/BioTATA-7B'
 model_config = transformers.AutoConfig.from_pretrained(
     model_name,
@@ -68,8 +67,7 @@ tokenizer.pad_token = tokenizer.eos_token
 tokenizer.padding_side = "right"
 ```
 
-```
-
+```python
 # Activate 4-bit precision base model loading
 use_4bit = True
 
@@ -83,7 +81,7 @@ bnb_4bit_quant_type = "nf4"
 use_nested_quant = True
 ```
 
-```
+```python
 compute_dtype = getattr(torch, bnb_4bit_compute_dtype)
 
 bnb_config = BitsAndBytesConfig(
@@ -94,14 +92,14 @@ bnb_config = BitsAndBytesConfig(
 )
 ```
 
-```
+```python
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     quantization_config=bnb_config,
 )
 ```
 
-```
+```python
 pipeline = transformers.pipeline(
     "text-generation",
     model=model,
@@ -111,14 +109,14 @@ pipeline = transformers.pipeline(
 
 )
 ```
-```
+```python
 messages = [{"role": "user", "content": "What is TATA"}]
 prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 outputs = pipeline(prompt, max_new_tokens=200, do_sample=True, temperature=0.01, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
 ```
 
-
+This will inference the model on 4.8GB Vram
 ## Bias, Risks, and Limitations
 
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->