Uploaded model
- Developed by: Mollel
- License: apache-2.0
- Finetuned from model : unsloth/gemma-7b-bnb-4bit
This gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.
Inference With Inference with HuggingFace transformers
!pip install transformers peft accelerate bitsandbytes
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
model = AutoPeftModelForCausalLM.from_pretrained(
"Mollel/Gemma_Swahili_Mollel_1_epoch",
load_in_4bit = False
)
tokenizer = AutoTokenizer.from_pretrained("Mollel/Gemma_Swahili_Mollel_1_epoch")
input_prompt = """
### Instruction:
{}
### Input:
{}
### Response:
{}"""
input_text = input_prompt.format(
"Andika aya fupi kuhusu mada iliyotolewa.", # instruction
"Umuhimu wa kutumia nishati inayoweza kurejeshwa", # input
"", # output - leave this blank for generation!
)
inputs = tokenizer([input_text], return_tensors = "pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True)
response = tokenizer.batch_decode(outputs)[0]
print(response)
Model tree for Mollel/Gemma_Swahili_Mollel_1_epoch
Base model
unsloth/gemma-7b-bnb-4bit