artindnr/ChatBerry

🍰👑 ChatBerry

ChatBerry is the flagship release of the ChatBerry family — a fine-tuned version of `artindnr/strawberry-1`, converted from a reasoning ("thinking") model into a direct-answer chat model. Reasoning traces are disabled — ChatBerry responds directly, without emitting a separate chain-of-thought / analysis channel. This release is trained on the largest dataset in the ChatBerry line to date, and outperforms every prior checkpoint, including `ChatBerry-1.2`.

What's New

ChatBerry is the culmination of the iterative ChatBerry line (1.0 → 1.1 → 1.2), each of which scaled up training data over the last:

• —Trained on the largest dataset yet in the ChatBerry line
• —Outperforms ChatBerry-1.2 (and by extension the rest of the line) on response quality and instruction-following
• —Same direct-chat behavior: no visible reasoning/analysis channel
• —The current recommended default for anyone looking for a ChatBerry checkpoint

<!-- TODO: add specific benchmark numbers or qualitative comparisons vs the rest of the ChatBerry line -->

Model Details

• —Base model: artindnr/strawberry-1 (itself fine-tuned from openai/gpt-oss-20b, 21B parameters)
• —Architecture: gpt_oss
• —Fine-tuned by: artindnr
• —License: Apache 2.0
• —Languages: Farsi (Persian), English, and multilingual support
• —Model type: Causal decoder-only chat language model (reasoning disabled)

Training

ChatBerry was fine-tuned from artindnr/strawberry-1 on the largest version yet of the direct chat-style (non-reasoning) SFT data used across the ChatBerry line. As with earlier ChatBerry releases, this SFT pass overrides Strawberry-1's reasoning behavior, teaching the model to skip the analysis channel and go straight to a final answer.

<!-- TODO: add exact dataset name/link, size relative to ChatBerry-1.2, training hardware, number of epochs, learning rate, effective batch size, LoRA vs full fine-tune details -->

How to Use

ChatBerry uses the gpt-oss chat template (Harmony format) shipped with the base model, so it works with 🤗 Transformers.

Installation

pip install torch --index-url https://download.pytorch.org/whl/cu128
pip install "trl>=0.20.0" "peft>=0.17.0" "transformers>=4.55.0" "kernels>=0.12.0"

This has been verified to work with:

Generation

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_ID = "artindnr/chatberry"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

USER_PROMPT = "تو کی هستی و اسمت چیه؟"

messages = [
    {"role": "user", "content": USER_PROMPT},
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    temperature=0.6,
    do_sample=True,
)

print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

As with earlier ChatBerry releases, there's no need to set a reasoning language system message or parse out separate analysis / final channels — ChatBerry goes straight to its final answer, so decoding just the newly generated tokens with skip_special_tokens=True gives you the plain-text response directly.

Intended Use

ChatBerry is intended for:

• —General-purpose Farsi and multilingual chat assistants
• —Applications where direct, low-latency responses are preferred over visible reasoning traces
• —Use cases that want the best-performing, most data-rich ChatBerry checkpoint available

Limitations

• —ChatBerry trades away Strawberry-1's explicit chain-of-thought reasoning; for tasks that benefit from visible step-by-step reasoning, artindnr/strawberry-1 may be a better fit.
• —As with any fine-tune, ChatBerry inherits the general capabilities and limitations of the gpt-oss-20b base model and the strawberry-1 checkpoint it was built from, including the possibility of hallucinated facts.
• —No formal safety fine-tuning beyond what is inherited from the base model and Strawberry-1 has been applied; use appropriate safeguards in production settings.

License

This model is released under the Apache 2.0 license, consistent with the base gpt-oss-20b model and strawberry-1.

Citation

If you use ChatBerry in your work, please cite:

@misc{chatberry,
  title  = {ChatBerry: A Direct-Answer Chat Fine-tune of Strawberry-1},
  author = {artindnr},
  year   = {2026},
  url    = {https://huggingface.co/artindnr/chatberry}
}

Acknowledgements

Built on top of `artindnr/strawberry-1`, itself fine-tuned from `openai/gpt-oss-20b`.