Update README.md

README.md

@@ -48,6 +48,84 @@ sequences = pipeline(
 for seq in sequences:
     print(f"Result: {seq['generated_text']}")
 ```
+``` python
+# !pip install -q accelerate==0.21.0 peft==0.4.0 bitsandbytes==0.40.2 transformers==4.31.0 trl==0.4.7
+
+import os
+import torch
+from datasets import load_dataset
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+    Trainer,
+    HfArgumentParser,
+    TrainingArguments,
+    pipeline,
+    logging,
+)
+from peft import LoraConfig, PeftModel
+from trl import SFTTrainer
+
+###############################################################################
+# bitsandbytes parameters
+################################################################################
+
+# Activate 4-bit precision base model loading
+use_4bit = True
+
+# Compute dtype for 4-bit base models
+bnb_4bit_compute_dtype = "float16"
+
+# Quantization type (fp4 or nf4)
+bnb_4bit_quant_type = "nf4"
+
+# Activate nested quantization for 4-bit base models (double quantization)
+use_nested_quant = False
+
+################################################################################
+# SFT parameters
+################################################################################
+
+# Maximum sequence length to use
+max_seq_length = None
+
+# Pack multiple short examples in the same input sequence to increase efficiency
+packing = False
+
+# Load the entire model on the GPU 0
+device_map = {"": 0}
+
+model_name="bosbos/bosbos-2-7b"
+# Load tokenizer and model with QLoRA configuration
+compute_dtype = getattr(torch, bnb_4bit_compute_dtype)
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=use_4bit,
+    bnb_4bit_quant_type=bnb_4bit_quant_type,
+    bnb_4bit_compute_dtype=compute_dtype,
+    bnb_4bit_use_double_quant=use_nested_quant,
+)
+# Load base model
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    quantization_config=bnb_config,
+    device_map=device_map
+)
+model.config.use_cache = False
+model.config.pretraining_tp = 1
+
+# Load LLaMA tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = "right" # Fix weird overflow issue with fp16 training
+
+# Run text generation pipeline with our next model
+prompt = "what is prediction in frensh ?"
+pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
+result = pipe(f"<s>[INST] {prompt} [/INST]")
+print(result[0]['generated_text'])
+```
 
 Output:
 >"Prédiction" is a noun that refers to the act of making a forecast or an estimate of something that will happen in the future. It can also refer to the result of such a forecast or estimate.