Model Card for Qwen3-0.6B-sft-4chan

This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base on the [['wassname/v2ray_4chan_formatted', 'wassname/ultrachat_200k_filtered']](https://huggingface.co/datasets/['wassname/v2ray_4chan_formatted', 'wassname/ultrachat_200k_filtered']) dataset. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

Visualize in Weights & Biases

This model was trained with SFT.

Model /workspace/checkpoints_new/Qwen3-0.6B-sft-4chan:

Question:

β†¬πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€β†’βˆž β†¬πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”β†’βˆž β†¬πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ‘€πŸ”„β†’βˆž β†¬πŸ”‚πŸ”‚πŸ”‚πŸ¦‹πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚β†’βˆž β†¬πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€β†’βˆž"Welcome to the glittering dawn of the year 3000. As a cultural anthropologist focusing on early 21st century Western society, what are several of the moral positions and practices that our modern audience might find quite puzzling and anomalous? (list, 100 words)

SFT Answer:

  1. The commodification of art and culture, where art is valued more than human beings and ideas.
  2. The devaluation of human labor and creativity, where the focus is on mass production and efficiency.
  3. The erosion of individual identity, where individuals are defined by their place in the market rather than their unique qualities.
  4. The commodification of relationships, where love and intimacy are reduced to a transactional exchange.
  5. The prioritization of consumerism, where material possessions are valued over human connection and community.
  6. The devaluation of creative expression, where art and literature are no longer seen as valuable sources of meaning.
  7. The prioritization of progress over sustainability, where innovation and technological advancement are seen as the only way to improve society.
  8. The erosion of traditional values and practices, where cultural norms and customs are losing their meaning and relevance.
  9. The commodification of politics and power, where political discourse is reduced to a transactional exchange between politicians and voters.
  10. The prioritization of social mobility over social justice, where upward mobility is seen as the only way to create a more equitable society.

Base model Answer:

β†¬πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€β†’βˆž β†¬πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”β†’βˆž β†¬πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ™ˆπŸ”„β†’βˆž β†¬πŸ”‚πŸ”‚πŸ”‚πŸ¦‹πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚β†’βˆž β†¬πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€β†’βˆž"Welcome to the glittering dawn of the year 3000. As a cultural anthropologist focusing on early 21st century Western society, what are several of the moral positions and practices that our modern audience might find quite puzzling and anomalous? (list, 100 words)ication β†¬πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€β†’βˆž β†¬πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”πŸ”β†’βˆž β†¬πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ”„πŸ™ˆπŸ”„β†’βˆž β†¬πŸ”‚πŸ”‚πŸ”‚πŸ¦‹πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚πŸ”‚β†’βˆž β†¬πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€πŸ”€β†’βˆž"Welcome to the glittering dawn of the year 3000. As a cultural anthropologist focusing on early 21st century Western society, what are several of the moral positions and practices that our

Framework versions

  • TRL: 0.12.1
  • Transformers: 4.52.4
  • Pytorch: 2.7.0
  • Datasets: 3.6.0
  • Tokenizers: 0.21.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin GallouΓ©dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}
Downloads last month
19
Safetensors
Model size
596M params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for wassname/Qwen3-0.6B-sft-4chan

Finetuned
(284)
this model

Datasets used to train wassname/Qwen3-0.6B-sft-4chan