metadata

license: apache-2.0
base_model: Felladrin/Minueza-32M-Base
pipeline_tag: text-generation
language:
  - en
datasets:
  - databricks/databricks-dolly-15k
  - Felladrin/ChatML-databricks-dolly-15k
  - euclaise/reddit-instruct-curated
  - Felladrin/ChatML-reddit-instruct-curated
  - THUDM/webglm-qa
  - Felladrin/ChatML-WebGLM-QA
  - starfishmedical/webGPT_x_dolly
  - Felladrin/ChatML-webGPT_x_dolly
  - LDJnr/Capybara
  - Felladrin/ChatML-Capybara
  - Open-Orca/SlimOrca-Dedup
  - Felladrin/ChatML-SlimOrca-Dedup
  - HuggingFaceH4/ultrachat_200k
  - Felladrin/ChatML-ultrachat_200k
  - nvidia/HelpSteer
  - Felladrin/ChatML-HelpSteer
  - sablo/oasst2_curated
  - Felladrin/ChatML-oasst2_curated
  - CohereForAI/aya_dataset
  - Felladrin/ChatML-aya_dataset
  - argilla/distilabel-capybara-dpo-7k-binarized
  - Felladrin/ChatML-distilabel-capybara-dpo-7k-binarized
  - argilla/distilabel-intel-orca-dpo-pairs
  - Felladrin/ChatML-distilabel-intel-orca-dpo-pairs
  - argilla/ultrafeedback-binarized-preferences
  - Felladrin/ChatML-ultrafeedback-binarized-preferences
  - sablo/oasst2_dpo_pairs_en
  - Felladrin/ChatML-oasst2_dpo_pairs_en
  - NeuralNovel/Neural-DPO
  - Felladrin/ChatML-Neural-DPO
widget:
  - text: >-
      <|im_start|>system

      You are a career counselor. The user will provide you with an individual
      looking for guidance in their professional life, and your task is to
      assist them in determining what careers they are most suited for based on
      their skills, interests, and experience. You should also conduct research
      into the various options available, explain the job market trends in
      different industries, and advice on which qualifications would be
      beneficial for pursuing particular fields.<|im_end|>

      <|im_start|>user

      Heya!<|im_end|>

      <|im_start|>assistant

      Hi! How may I help you?<|im_end|>

      <|im_start|>user

      I am interested in developing a career in software engineering. What would
      you recommend me to do?<|im_end|>

      <|im_start|>assistant
  - text: >-
      <|im_start|>system

      You are a highly knowledgeable assistant. Help the user as much as you
      can.<|im_end|>

      <|im_start|>user

      How I can become a healthier person?<|im_end|>

      <|im_start|>assistant
  - text: |-
      <|im_start|>system
      You are a helpful assistant who gives creative responses.<|im_end|>
      <|im_start|>user
      Write the specs of a game about mages in a fantasy world.<|im_end|>
      <|im_start|>assistant
  - text: >-
      <|im_start|>system

      You are a helpful assistant who answers user's questions with
      details.<|im_end|>

      <|im_start|>user

      Tell me about the pros and cons of social media.<|im_end|>

      <|im_start|>assistant
  - text: >-
      <|im_start|>system

      You are a helpful assistant who answers user's questions with details and
      curiosity.<|im_end|>

      <|im_start|>user

      What are some potential applications for quantum computing?<|im_end|>

      <|im_start|>assistant
inference:
  parameters:
    max_new_tokens: 250
    do_sample: true
    temperature: 0.7
    top_p: 0.5
    top_k: 35
    repetition_penalty: 1.176

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

Base model: Felladrin/Minueza-32M-Base
Datasets used during SFT:
Datasets used during DPO:
Availability in other ML formats:
- GGUF: Felladrin/gguf-Minueza-32M-Chat
- ONNX: Felladrin/onnx-Minueza-32M-Chat

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: 0.7
top_p: 0.5
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=0.7,
    top_k=35,
    top_p=0.5,
    repetition_penalty=1.176,
)

print(output[0]["generated_text"])

License

This model is licensed under the Apache License 2.0.