metadata
library_name: transformers
tags:
- LoRA
license: apache-2.0
datasets:
- TIGER-Lab/MathInstruct
language:
- en
base_model:
- Qwen/Qwen2.5-7B-Instruct
pipeline_tag: text-generation
Komodo is a Qwen 2.5-7B-Instruct-FineTuned model on TIGER-Lab/MathInstruct dataset to increase math performance of the base model.
This model is 4bit-quantizated. You should import it 16bit if you want to use 7B parameters!
Suggested Usage:
tokenizer = AutoTokenizer.from_pretrained("suayptalha/Komodo-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("suayptalha/Komodo-7B-Instruct")
example_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:
{}"""
inputs = tokenizer(
[
example_prompt.format(
"", #Your question here
"", #Given input here
"", #Output (for training)
)
], return_tensors = "pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True)
tokenizer.batch_decode(outputs)