Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]
Uses
Direct Use
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
base_model_id = "mistralai/Mistral-7B-v0.1"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16
)
base_model = AutoModelForCausalLM.from_pretrained(
base_model_id, # Mistral, same as before
quantization_config=bnb_config, # Same quantization config as before
device_map="auto",
trust_remote_code=True,
use_auth_token=True
)
eval_tokenizer = AutoTokenizer.from_pretrained(base_model_id, add_bos_token=True, trust_remote_code=True)
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM
ft_model = PeftModel.from_pretrained(base_model, "ctrltokyo/mistral-finetune-gaban-samsay")
# Inference
eval_prompt = """The following is a script for an episode of Kitchen Nightmares:
[Gordon] Goddamn it, this restaurant is in the toilet!
"""
model_input = eval_tokenizer(eval_prompt, return_tensors="pt").to("cuda")
ft_model.eval()
with torch.no_grad():
print(eval_tokenizer.decode(ft_model.generate(**model_input, max_new_tokens=150, repetition_penalty=1.5)[0], skip_special_tokens=True))
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
