wellwego-7b

WellWeGo-7B-Instruct

Model Card

Model Name: WellWeGo-7B-Instruct
Model Type: Causal Language Model
Architecture: Transformer with RoPE, SwiGLU, RMSNorm, GQA
Parameters: 7.61B (6.53B non-embedding)
Context Length: 131,072 tokens

Description

WellWeGo-7B is a general-purpose small language model designed for instruction following, code generation, and agentic tasks.

Key Features

• Long Context: Up to 128K tokens with YaRN
• Multi-language: Strong performance in English and code
• Efficient: Optimized for consumer GPUs (24GB+)
• Agent-Ready: Built-in tool use and planning capabilities

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "wellwego/wellwego-7b-instruct"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Write a Python function to calculate fibonacci numbers."
messages = [
    {"role": "system", "content": "You are WellWeGo, a helpful AI assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(**model_inputs, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

System Prompt

You are WellWeGo, a helpful AI assistant created by WellWeGo AI.

License

Apache 2.0

Citation

@article{wellwego2026,
  title={WellWeGo: A General-Purpose Small Language Model},
  author={WellWeGo AI Team},
  year={2026}
}