Trained Models 🏋️
Collection
They may be small, but they're training like giants!
•
8 items
•
Updated
•
16
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
do_sample: true
temperature: 0.65
top_p: 0.55
top_k: 35
repetition_penalty: 1.176
from transformers import pipeline
generate = pipeline("text-generation", "Felladrin/Minueza-32M-Chat")
messages = [
{
"role": "system",
"content": "You are a helpful assistant who answers the user's questions with details and curiosity.",
},
{
"role": "user",
"content": "What are some potential applications for quantum computing?",
},
]
prompt = generate.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
output = generate(
prompt,
max_new_tokens=256,
do_sample=True,
temperature=0.65,
top_k=35,
top_p=0.55,
repetition_penalty=1.176,
)
print(output[0]["generated_text"])
This model was trained with SFT Trainer and DPO Trainer, in several sessions, using the following settings:
For Supervised Fine-Tuning:
Hyperparameter | Value |
---|---|
learning_rate | 2e-5 |
total_train_batch_size | 24 |
max_seq_length | 2048 |
weight_decay | 0 |
warmup_ratio | 0.02 |
For Direct Preference Optimization:
Hyperparameter | Value |
---|---|
learning_rate | 7.5e-7 |
total_train_batch_size | 6 |
max_length | 2048 |
max_prompt_length | 1536 |
max_steps | 200 |
weight_decay | 0 |
warmup_ratio | 0.02 |
beta | 0.1 |
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 28.49 |
AI2 Reasoning Challenge (25-Shot) | 20.39 |
HellaSwag (10-Shot) | 26.54 |
MMLU (5-Shot) | 25.75 |
TruthfulQA (0-shot) | 47.27 |
Winogrande (5-shot) | 50.99 |
GSM8k (5-shot) | 0.00 |