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-32Mx2-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-6 |
Total train batch size | 16 |
Max. sequence length | 2048 |
Weight decay | 0.01 |
Warmup ratio | 0.1 |
Optimizer | Adam with betas=(0.9,0.999) and epsilon=1e-08 |
Scheduler | cosine |
Seed | 42 |
Neftune Noise Alpha | 5 |
For Direct Preference Optimization:
Hyperparameter | Value |
---|---|
Learning rate | 5e-7 |
Total train batch size | 16 |
Max. length | 1024 |
Max. prompt length | 512 |
Max. steps | 200 |
Weight decay | 0 |
Warmup ratio | 0.1 |
Beta | 0.1 |
Base model
Felladrin/Minueza-32M-Base