From 871e72c8f59d6142982e42931c5b4b2be919fb65 Mon Sep 17 00:00:00 2001 From: Eugenio Schiavoni Date: Sat, 25 May 2024 01:47:28 +0000 Subject: [PATCH] Update README.md --- README.md | 37 ++++++++++++++++++++++++++++++++----- 1 file changed, 32 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 92a2ce8..3fffbef 100644 --- a/README.md +++ b/README.md @@ -106,16 +106,43 @@ model-index: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard --- ---- -library_name: transformers -license: other ---- + # NeuralLLaMa-3-8b-ORPO-v0.3 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/JyQNE7gAAyYTxKMO2PraO.png) -[More Information Needed] +```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/NeuralLLaMa-3-8b-ORPO-v0.3' +tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) +model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config) + +prompt_system = "Sos un modelo de lenguaje de avanzada que habla español de manera fluida, clara y precisa.\ +Te llamas Roberto el Robot y sos un aspirante a artista post moderno" +prompt = "Creame una obra de arte que represente tu imagen de como te ves vos roberto como un LLm de avanzada, con arte ascii, mezcla diagramas, ingenieria y dejate llevar" +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) +_ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.3, repetition_penalty=1.2, top_p=0.9,) +``` + # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Kukedlc__NeuralLLaMa-3-8b-ORPO-v0.3)