Update README.md

README.md

@@ -10,10 +10,14 @@ base_model:
 - mlabonne/ChimeraLlama-3-8B-v2
 - nbeerbower/llama-3-stella-8B
 - uygarkurt/llama-3-merged-linear
+license: other
 ---
 
 # NeuralLLaMa-3-8b-DT-v0.1
 
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/tK72e9RGnYyBVRy0T_Kba.png)
+
 NeuralLLaMa-3-8b-DT-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [mlabonne/ChimeraLlama-3-8B-v2](https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v2)
 * [nbeerbower/llama-3-stella-8B](https://huggingface.co/nbeerbower/llama-3-stella-8B)
@@ -43,28 +47,43 @@ parameters:
   int8_mask: true
 dtype: float16
 ```
+## 🗨️ Chats
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/feYEkbM_TqeahAMOoiGoG.png)
 
 ## 💻 Usage
 
 ```python
-!pip install -qU transformers accelerate
+!pip install -qU transformers accelerate bitsandbytes
 
-from transformers import AutoTokenizer
-import transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig
 import torch
 
-model = "Kukedlc/NeuralLLaMa-3-8b-DT-v0.1"
-messages = [{"role": "user", "content": "What is a large language model?"}]
-
-tokenizer = AutoTokenizer.from_pretrained(model)
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    torch_dtype=torch.float16,
-    device_map="auto",
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
 )
 
-outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
-print(outputs[0]["generated_text"])
+MODEL_NAME = 'Kukedlc/NeuralLLaMa-3-8b-DT-v0.1'
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config)
+
+prompt_system = "You are an advanced language model that speaks Spanish fluently, clearly, and precisely.\
+You are called Roberto the Robot and you are an aspiring post-modern artist."
+prompt = "Create a piece of art that represents how you see yourself, Roberto, as an advanced LLm, with ASCII art, mixing diagrams, engineering and let yourself go."
+
+chat = [
+    {"role": "system", "content": f"{prompt_system}"},
+    {"role": "user", "content": f"{prompt}"},
+]
+
+chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(chat, return_tensors="pt").to('cuda')
+streamer = TextStreamer(tokenizer)
+stop_token = "<|eot_id|>"
+stop = tokenizer.encode(stop_token)[0]
+
+_ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.7, repetition_penalty=1.2, top_p=0.9, eos_token_id=stop)
 ```