Update README.md

README.md

@@ -8,8 +8,13 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
+license: apache-2.0
 ---
+
+# NeuralStockFusion-7b
+
+![image/webp](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/5Ex2YG8H1oLXaS25gvZQs.webp)
+
 # merge
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
@@ -41,3 +46,29 @@ base_model: Kukedlc/NeuralSirKrishna-7b
 dtype: bfloat16
 
 ```
+
+# Model Inference: 
+
+``` python
+!pip install -qU transformers accelerate bitsandbytes
+
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig
+import torch
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+
+MODEL_NAME = 'Kukedlc/NeuralStockFusion-7b'
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config)
+
+inputs = tokenizer(["What is a large language model, in spanish\n\n"], return_tensors="pt").to('cuda')
+streamer = TextStreamer(tokenizer)
+
+# Despite returning the usual output, the streamer will also print the generated text to stdout.
+_ = model.generate(**inputs, streamer=streamer, max_new_tokens=256, do_sample=True, temperature=0.7, repetition_penalty=1.4, top_p=0.9)
+```