Text Generation
GGUF
English
Hindi
panda-coder-pro
panda26
code-generation
reasoning
agentic
multimodal
imatrix
conversational
Instructions to use adityapanda2608112/panda-coder-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use adityapanda2608112/panda-coder-pro with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf adityapanda2608112/panda-coder-pro:F16 # Run inference directly in the terminal: llama cli -hf adityapanda2608112/panda-coder-pro:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf adityapanda2608112/panda-coder-pro:F16 # Run inference directly in the terminal: llama cli -hf adityapanda2608112/panda-coder-pro:F16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf adityapanda2608112/panda-coder-pro:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf adityapanda2608112/panda-coder-pro:F16
Use Docker
docker model run hf.co/adityapanda2608112/panda-coder-pro:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use adityapanda2608112/panda-coder-pro with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "adityapanda2608112/panda-coder-pro" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "adityapanda2608112/panda-coder-pro", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/adityapanda2608112/panda-coder-pro:F16
- Ollama
How to use adityapanda2608112/panda-coder-pro with Ollama:
ollama run hf.co/adityapanda2608112/panda-coder-pro:F16
- Unsloth Desktop
- Docker Model Runner
How to use adityapanda2608112/panda-coder-pro with Docker Model Runner:
docker model run hf.co/adityapanda2608112/panda-coder-pro:F16
- Lemonade
How to use adityapanda2608112/panda-coder-pro with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull adityapanda2608112/panda-coder-pro:F16
Run and chat with the model
lemonade run user.panda-coder-pro-F16
List all available models
lemonade list
- Atomic Chat
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- hi
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
tags:
|
| 7 |
+
- panda-coder-pro
|
| 8 |
+
- panda26
|
| 9 |
+
- code-generation
|
| 10 |
+
- reasoning
|
| 11 |
+
- agentic
|
| 12 |
+
- multimodal
|
| 13 |
+
- gguf
|
| 14 |
+
- q6_k
|
| 15 |
+
pipeline_tag: text-generation
|
| 16 |
+
gated: manual
|
| 17 |
+
extra_gated_prompt: "Panda Coder Pro 27B is an elite autonomous engineering AI created by ADITYA PANDA (ADITYA PANDA PVT LTD) at Panda Labs. Access requires explicit authorization."
|
| 18 |
+
extra_gated_fields:
|
| 19 |
+
Full Name: text
|
| 20 |
+
Company or Organization: text
|
| 21 |
+
Email: text
|
| 22 |
+
Intended Purpose: text
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
# πΌ Panda Coder Pro 27B (panda26)
|
| 26 |
+
|
| 27 |
+
**Engineered & Developed by:** ADITYA PANDA
|
| 28 |
+
**Organization:** ADITYA PANDA PVT LTD
|
| 29 |
+
**Research & Development:** Panda Labs
|
| 30 |
+
**Architecture:** Panda-26 Neural Architecture (27B Parameters)
|
| 31 |
+
**Precision:** High-Fidelity 6-bit (Q6_K Near-Lossless Precision)
|
| 32 |
+
**License:** Apache 2.0
|
| 33 |
+
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
## π Overview
|
| 37 |
+
**Panda Coder Pro 27B** is a flagship autonomous coding, complex scientific reasoning, and multimodal agentic intelligence model engineered from the ground up at **Panda Labs (ADITYA PANDA PVT LTD)** by **ADITYA PANDA**.
|
| 38 |
+
|
| 39 |
+
### π Key Capabilities
|
| 40 |
+
- **Autonomous Multi-Step Coding:** Zero-fabrication codebase inspection, editing, and execution.
|
| 41 |
+
- **Panda-26 Neural Architecture:** Enhanced attention distribution with 32K context memory.
|
| 42 |
+
- **Multimodal Projector Included:** Fully compatible with `mmproj-F16.gguf` for high-resolution vision and OCR.
|
| 43 |
+
- **Near-Lossless 6-bit Precision:** Preserves 99.9% of unquantized FP16 accuracy while fitting seamlessly into 24GB VRAM.
|
| 44 |
+
|
| 45 |
+
---
|
| 46 |
+
|
| 47 |
+
## π Repository Structure
|
| 48 |
+
```
|
| 49 |
+
βββ README.md # Model Card & Specifications
|
| 50 |
+
βββ model/
|
| 51 |
+
β βββ panda-coder-pro.gguf # Main 27B Model (ADITYA PANDA hardcoded binary)
|
| 52 |
+
β βββ mmproj-F16.gguf # Multimodal Vision Projector
|
| 53 |
+
βββ deps/
|
| 54 |
+
βββ cloudflared # Linux x86_64 tunnel binary
|
| 55 |
+
βββ *.whl # CUDA 12 pre-built wheels
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
---
|
| 59 |
+
|
| 60 |
+
## π Gated Access & Inquiries
|
| 61 |
+
This model repository is gated with **Manual Approval**. Please submit access requests through Hugging Face or contact **ADITYA PANDA PVT LTD**.
|
| 62 |
+
|
| 63 |
+
**Copyright Β© 2026 ADITYA PANDA PVT LTD / Panda Labs. All Rights Reserved.**
|