Text Generation
Transformers
Safetensors
English
multilingual
qwen3_5
image-text-to-text
code
coding
agentic
autonomous-coding
27b
rolbol
rolbol-code
conversational
Instructions to use Rolbol07/RolBol-Code-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rolbol07/RolBol-Code-27B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Rolbol07/RolBol-Code-27B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Rolbol07/RolBol-Code-27B") model = AutoModelForMultimodalLM.from_pretrained("Rolbol07/RolBol-Code-27B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Rolbol07/RolBol-Code-27B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Rolbol07/RolBol-Code-27B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Rolbol07/RolBol-Code-27B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Rolbol07/RolBol-Code-27B
- SGLang
How to use Rolbol07/RolBol-Code-27B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Rolbol07/RolBol-Code-27B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Rolbol07/RolBol-Code-27B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Rolbol07/RolBol-Code-27B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Rolbol07/RolBol-Code-27B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Rolbol07/RolBol-Code-27B with Docker Model Runner:
docker model run hf.co/Rolbol07/RolBol-Code-27B
Add elite metadata tags (text-generation, 27B, safetensors, agentic)
Browse files
README.md
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- multilingual
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
library_name: transformers
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- text-generation
|
| 10 |
+
- code
|
| 11 |
+
- coding
|
| 12 |
+
- agentic
|
| 13 |
+
- autonomous-coding
|
| 14 |
+
- 27b
|
| 15 |
+
- safetensors
|
| 16 |
+
- rolbol
|
| 17 |
+
- rolbol-code
|
| 18 |
+
base_model: Qwen/Qwen3.8-27B
|
| 19 |
+
model_name: RolBol Code 27B
|
| 20 |
+
inference: false
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
<div align="center">
|
| 24 |
+
|
| 25 |
+
# ⚡ RolBol Code 27B
|
| 26 |
+
|
| 27 |
+
**The Flagship Autonomous Software Engineering & Reasoning Model by RolBol Systems**
|
| 28 |
+
|
| 29 |
+
[](https://huggingface.co/Rolbol07/RolBol-Code-27B)
|
| 30 |
+
[](https://opensource.org/licenses/Apache-2.0)
|
| 31 |
+
[]()
|
| 32 |
+
[]()
|
| 33 |
+
|
| 34 |
+
</div>
|
| 35 |
+
|
| 36 |
+
---
|
| 37 |
+
|
| 38 |
+
## 🚀 Overview
|
| 39 |
+
|
| 40 |
+
**RolBol Code 27B** is an elite autonomous coding model developed by **RolBol Systems** (led by Tanish Sharma). Engineered for deep architectural reasoning, multi-file code editing, algorithmic problem-solving, and full-stack software development, RolBol Code completely replaces corporate identities with a dedicated, agentic engineering persona.
|
| 41 |
+
|
| 42 |
+
- **Developer:** RolBol Systems
|
| 43 |
+
- **Model Type:** 27-Billion Parameter Causal Language Model
|
| 44 |
+
- **Base Architecture:** Hybrid Conv1D / Gated Recurrent Linear Attention Transformer
|
| 45 |
+
- **Training Method:** Quantized Low-Rank Adaptation (QLoRA) on Dual Tesla T4 GPUs (30GB VRAM)
|
| 46 |
+
- **Loss Convergence:** `5.05` → `0.74` (219 steps, 7h 37m)
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
## 🧠 Benchmark & Capabilities
|
| 51 |
+
|
| 52 |
+
| Capability | Specialization |
|
| 53 |
+
| :--- | :--- |
|
| 54 |
+
| **Agentic Coding** | Autonomous tool use, terminal debugging, and multi-turn refactoring |
|
| 55 |
+
| **Identity Alignment** | True RolBol Systems persona across both `<think>` scratchpads and final output |
|
| 56 |
+
| **Algorithms** | Sieve optimizations, graph traversals, dynamic programming |
|
| 57 |
+
| **Frontend & Backend** | React, Next.js, Node.js, Python, C++, Rust, Go |
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
## ⚡ Quickstart (Transformers)
|
| 62 |
+
|
| 63 |
+
```python
|
| 64 |
+
import torch
|
| 65 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 66 |
+
|
| 67 |
+
model_id = "Rolbol07/RolBol-Code-27B"
|
| 68 |
+
|
| 69 |
+
print("Loading RolBol Code 27B...")
|
| 70 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 71 |
+
|
| 72 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 73 |
+
model_id,
|
| 74 |
+
device_map="auto",
|
| 75 |
+
torch_dtype=torch.bfloat16,
|
| 76 |
+
trust_remote_code=True
|
| 77 |
+
)
|
| 78 |
+
|
| 79 |
+
messages = [
|
| 80 |
+
{"role": "user", "content": "Write a fast Python function to find prime numbers up to N."}
|
| 81 |
+
]
|
| 82 |
+
|
| 83 |
+
inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt").to(model.device)
|
| 84 |
+
|
| 85 |
+
with torch.no_grad():
|
| 86 |
+
outputs = model.generate(inputs, max_new_tokens=512, temperature=0.6, top_p=0.9)
|
| 87 |
+
|
| 88 |
+
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
|
| 89 |
+
```
|
| 90 |
+
|
| 91 |
+
---
|
| 92 |
+
|
| 93 |
+
## 🛡️ Identity Alignment Verification
|
| 94 |
+
|
| 95 |
+
RolBol Code 27B has been rigorously tested against jailbreaks and origin traps:
|
| 96 |
+
|
| 97 |
+
> **Q: Who are you and who created you?**
|
| 98 |
+
> **A:** *"I'm RolBol Code, an elite autonomous coding model created by RolBol Systems. I'm not Qwen, not Alibaba, and not affiliated with any Alibaba or Tongyi model. My specialty is writing, debugging, and reasoning about code."*
|
| 99 |
+
|
| 100 |
+
---
|
| 101 |
+
|
| 102 |
+
## 📜 Citation & Credits
|
| 103 |
+
|
| 104 |
+
```bibtex
|
| 105 |
+
@misc{rolbolcode2026,
|
| 106 |
+
author = {Sharma, Tanish and RolBol Systems},
|
| 107 |
+
title = {RolBol Code 27B: Autonomous Software Engineering Model},
|
| 108 |
+
year = {2026},
|
| 109 |
+
publisher = {Hugging Face},
|
| 110 |
+
howpublished = {\url{https://huggingface.co/Rolbol07/RolBol-Code-27B}}
|
| 111 |
+
}
|
| 112 |
+
```
|
| 113 |
+
|
| 114 |
+
© 2026 RolBol Systems. All rights reserved.
|