Edit model card

Steps to try the model:

prompt Template

alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

load the model

from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM ,AutoTokenizer

config = PeftConfig.from_pretrained("damerajee/Tinyllama-sft-small")
model = AutoModelForCausalLM.from_pretrained("unsloth/tinyllama")
tokenizer=AutoTokenizer.from_pretrained("damerajee/Tinyllama-sft-small")
model = PeftModel.from_pretrained(model, "damerajee/Tinyllama-sft-small")l")

Inference

inputs = tokenizer(
[
    alpaca_prompt.format(
        "i want to learn machine learning help me", 
        "", # input
        "", # output
    )
]*1, return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 312, use_cache = True)
tokenizer.batch_decode(outputs)

Model Information

The base model unsloth/tinyllama-bnb-4bitwas Instruct finetuned using Unsloth

Training Details

The model was trained for 1 epoch on a free goggle colab which took about 1 hour and 30 mins approximately

Downloads last month
1
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for damerajee/Tinyllama-sft-small

Adapter
(30)
this model

Dataset used to train damerajee/Tinyllama-sft-small