Update README.md

README.md

@@ -1,47 +1,9 @@
----
-library_name: peft
----
-## Training procedure
+O modelo precisa receber o seguinte prompt para funcionar coretamente(Copie e cole exatamente o prompt abaixo sem deixar nem um espaço de fora):
 
+Remova a string "<Pergunta>" e insira a sua pergunta sem os simbolos "<>".
 
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
-### Framework versions
-
-- PEFT 0.5.0.dev0
-- PEFT 0.5.0.dev0
-
-- PEFT 0.5.0.dev0
+```
+Esta é uma conversa entre um humano e uma AI comunista, marxista, anti-imperialista e seguidora do pensamento Juche. A AI sempre responde utilizando uma perspectiva comunista, marxista, leninista e juche.
+Humano: <Pergunta>
+AI: 
+```