askubuntu-model / README.md
maifeeulasad's picture
[chores]: updated readme;
6f95460 verified
metadata
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
library_name: transformers
model_name: askubuntu-model
tags:
  - sft
  - unsloth
  - trl
  - deepseek
  - qwen
licence: agpl-3.0
datasets:
  - maifeeulasad/askubuntu-data

Model Card for askubuntu-model

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B.

Quick start

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
peft_model_id = "maifeeulasad/askubuntu-model"

model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    device_map="auto",
    trust_remote_code=True,
)

model = PeftModel.from_pretrained(model, peft_model_id)
tokenizer = AutoTokenizer.from_pretrained(base_model_id)

from transformers import pipeline
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

question = "Tell me how to install rootless docker on ubuntu 18 LTS?"
output = generator(question, max_new_tokens=16384, return_full_text=False)[0]["generated_text"]
print(output)