Update README.md

README.md

@@ -1,5 +1,13 @@
 ---
 library_name: peft
+base_model: TheBloke/zephyr-7B-beta-GPTQ
+revision: gptq-8bit-32g-actorder_True
+license: mit
+language:
+- pt
+tags:
+- gptq
+- ptbr
 ---
 ## Training procedure
 
@@ -25,4 +33,66 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
-- PEFT 0.5.0
+
+# Load model AutoModel
+```python
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM
+
+config = PeftConfig.from_pretrained("matheusrdgsf/cesar-ptbr")
+model = AutoModelForCausalLM.from_pretrained("TheBloke/zephyr-7B-beta-GPTQ", revision="gptq-8bit-32g-actorder_True", device_map='auto')
+model = PeftModel.from_pretrained(model, "matheusrdgsf/cesar-ptbr")
+```
+
+# Easy inference
+```python
+from transformers import GenerationConfig
+from transformers import AutoTokenizer
+
+tokenizer_model = AutoTokenizer.from_pretrained('TheBloke/zephyr-7B-beta-GPTQ')
+tokenizer_template = AutoTokenizer.from_pretrained('HuggingFaceH4/zephyr-7b-alpha')
+
+generation_config = GenerationConfig(
+    do_sample=True,
+    temperature=0.1,
+    top_p=0.25,
+    top_k=0,
+    max_new_tokens=512,
+    repetition_penalty=1.1,
+    eos_token_id=tokenizer_model.eos_token_id,
+    pad_token_id=tokenizer_model.eos_token_id,
+)
+
+
+def get_inference(
+    text,
+    model,
+    tokenizer_model=tokenizer_model,
+    tokenizer_template=tokenizer_template,
+    generation_config=generation_config,
+):
+    st_time = time.time()
+    inputs = tokenizer_model(
+        tokenizer_template.apply_chat_template(
+            [
+                {
+                    "role": "system",
+                    "content": "Você é um chatbot para indicação de filmes. Responda de maneira educada sugestões de filmes para os usuários.",
+                },
+                {"role": "user", "content": text},
+            ],
+            tokenize=False,
+        ),
+        return_tensors="pt",
+    ).to("cuda")
+
+    outputs = model.generate(**inputs, generation_config=generation_config)
+
+    print('inference time:', time.time() - st_time)
+    return tokenizer_model.decode(outputs[0], skip_special_tokens=True).split('\n')[-1]
+
+get_inference('Poderia indicar filmes de ação de até 2 horas?', model)
+```
+
+
+- PEFT 0.5.0