|
--- |
|
library_name: peft |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
language: |
|
- en |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
This model is a fine-tuned version of [base_model](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an [FRIENDS TV Series](https://www.kaggle.com/datasets/blessondensil294/friends-tv-series-screenplay-script) dataset. |
|
Fine-tuning was done by taking only the parts of the dataset where Monica spoke. |
|
|
|
|
|
## Uses |
|
|
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> |
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
from peft import PeftModel, PeftConfig |
|
|
|
base_model = "mistralai/Mistral-7B-Instruct-v0.2" |
|
adapter_model = "akingunduz/monica_llm" |
|
|
|
model = AutoModelForCausalLM.from_pretrained(base_model) |
|
model = PeftModel.from_pretrained(model, adapter_model) |
|
tokenizer = AutoTokenizer.from_pretrained(base_model) |
|
|
|
model = model.to("cuda") |
|
model.eval() |
|
|
|
import torch |
|
def build_prompt(question): |
|
prompt=f"<s>[INST]@Monica. {question} [/INST]" |
|
return prompt |
|
|
|
question = "Which city do you live?" |
|
prompt = build_prompt(question) |
|
inputs = tokenizer(prompt, return_tensors="pt") |
|
|
|
with torch.no_grad(): |
|
outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=10) |
|
print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]) |
|
|
|
``` |
|
|
|
``` |
|
>>> [INST]@Monica. Which city do you live? [/INST]New York. |
|
``` |
|
|
|
## Environmental Impact |
|
|
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> |
|
|
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). |
|
|
|
|
|
- PEFT 0.10.0 |