metadata

language:
  - en
  - sw
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - gemma
  - trl
base_model: unsloth/gemma-7b-bnb-4bit

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)