update adapter

README.md

@@ -1,5 +1,6 @@
 ---
 library_name: peft
+pipeline_tag: text-generation
 ---
 ## Training procedure
 
@@ -24,5 +25,75 @@ The following `bitsandbytes` quantization config was used during training:
 - max_input_length: None
 ### Framework versions
 
+# Load model
+```python
+from transformers import AutoModelForCausalLM, GPTQConfig
+from peft import PeftModel
+
+bnb_config = GPTQConfig(
+    bits=8,
+    disable_exllama=True,
+)
+
+_model = AutoModelForCausalLM.from_pretrained(
+    'TheBloke/zephyr-7B-beta-GPTQ',
+    quantization_config=bnb_config,
+    device_map='auto',
+    revision='gptq-8bit-32g-actorder_True',
+)
+
+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

adapter_config.json

@@ -12,7 +12,7 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
-  "revision": null,
+  "revision": "gptq-8bit-32g-actorder_True",
   "target_modules": [
     "q_proj",
     "v_proj"