Edit model card

Minueza-32M-Chat: A chat model with 32 million parameters

Recommended Prompt Format

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant

Recommended Inference Parameters

do_sample: true
temperature: 0.65
top_p: 0.55
top_k: 35
repetition_penalty: 1.176

Usage Example

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"])

How it was trained

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

Open LLM Leaderboard Evaluation Results

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
Downloads last month
81
Safetensors
Model size
32.8M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Felladrin/Minueza-32M-Chat

Finetuned
(4)
this model
Quantizations
2 models

Datasets used to train Felladrin/Minueza-32M-Chat

Spaces using Felladrin/Minueza-32M-Chat 2

Collection including Felladrin/Minueza-32M-Chat

Evaluation results