Instructions to use Reponx/Network-Cloud-Ops-Engineer-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Reponx/Network-Cloud-Ops-Engineer-9B with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B")
model = PeftModel.from_pretrained(base_model, "Reponx/Network-Cloud-Ops-Engineer-9B")

Transformers

How to use Reponx/Network-Cloud-Ops-Engineer-9B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Reponx/Network-Cloud-Ops-Engineer-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Reponx/Network-Cloud-Ops-Engineer-9B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Reponx/Network-Cloud-Ops-Engineer-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Reponx/Network-Cloud-Ops-Engineer-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Reponx/Network-Cloud-Ops-Engineer-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Reponx/Network-Cloud-Ops-Engineer-9B

SGLang

How to use Reponx/Network-Cloud-Ops-Engineer-9B 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 "Reponx/Network-Cloud-Ops-Engineer-9B" \
    --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": "Reponx/Network-Cloud-Ops-Engineer-9B",
		"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 "Reponx/Network-Cloud-Ops-Engineer-9B" \
        --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": "Reponx/Network-Cloud-Ops-Engineer-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Reponx/Network-Cloud-Ops-Engineer-9B with Docker Model Runner:
```
docker model run hf.co/Reponx/Network-Cloud-Ops-Engineer-9B
```

dharikh commited on 20 days ago

Commit

a3c09bf

verified ·

1 Parent(s): f0f4cb3

Update README.md

Browse files

Files changed (1) hide show

README.md +76 -34

README.md CHANGED Viewed

@@ -8,55 +8,97 @@ tags:
 - sft
 - transformers
 - trl
-licence: license
 pipeline_tag: text-generation
 ---
-# Model Card for Reponx-Network-Cloud-Ops-Engineer-9B
-This model is a fine-tuned version of [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-## Quick start
-```python
-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
-This model was trained with SFT.
-### Framework versions
-- PEFT 0.21.0
-- TRL: 1.13.0
-- Transformers: 5.17.0
-- Pytorch: 2.8.0+cu128
-- Datasets: 5.0.1
-- Tokenizers: 0.23.2
-## Citations
-Cite TRL as:
-```bibtex
-@software{vonwerra2020trl,
-  title   = {{TRL: Transformers Reinforcement Learning}},
-  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
-  license = {Apache-2.0},
-  url     = {https://github.com/huggingface/trl},
-  year    = {2020}
-}
-```

 - sft
 - transformers
 - trl
+- network-engineering
+- network-operations
+- cloud-operations
+- network-troubleshooting
+- network-automation
+- cisco
+- palo-alto-networks
+- fortinet
+- juniper
+- aws
+- azure
+- gcp
+- bgp
+- ospf
 pipeline_tag: text-generation
+license: apache-2.0
+language:
+- en
 ---
+# Reponx Network & Cloud Operations Engineer 9B
+**Reponx 9B** is a specialized AI model for **network engineering, network operations, cloud networking, troubleshooting, and infrastructure operations**.
+It is designed to help network and cloud engineers investigate technical issues using an **evidence-first and safety-conscious troubleshooting approach**.
+## Key Areas
+- Cisco networking
+- Palo Alto Networks
+- Fortinet
+- Juniper
+- BGP, OSPF, routing and switching
+- AWS networking
+- Microsoft Azure networking
+- Google Cloud networking
+- Network troubleshooting and operations
+- Network automation
+- Change validation and rollback planning
+## Operational Approach
+Reponx is designed to:
+1. Diagnose the likely problem.
+2. Gather evidence before making changes.
+3. Recommend read-only checks and commands first.
+4. Explain what the results mean.
+5. Suggest controlled remediation when appropriate.
+6. Include validation and rollback considerations.
+## Base Model
+Reponx 9B is a PEFT/LoRA fine-tuned model based on **Qwen/Qwen3.5-9B**.
+## Example
+**Prompt:**
+> A Cisco BGP neighbor is stuck in Idle. How would you troubleshoot it?
+Reponx provides an evidence-first troubleshooting workflow covering connectivity, BGP configuration, TCP/179, neighbor state, routing, and safe validation steps.
+## Benchmark
+Reponx is evaluated using an internal **200-scenario Network & Cloud Operations benchmark** covering routing, switching, major network vendors, AWS, Azure, GCP, Kubernetes, automation, root-cause analysis, and change safety.
+Reponx V1 achieved approximately **67% in rubric-based evaluation**. This is an internal evaluation and should not be interpreted as an independent or standardized industry benchmark.
+## Intended Use
+This model is intended for:
+- Network engineers
+- Cloud network engineers
+- Network operations teams
+- Infrastructure engineers
+- Technical troubleshooting and educational use
+## Limitations
+Reponx may generate inaccurate or outdated commands. Vendor syntax and cloud services can change over time.
+Always validate commands against current vendor documentation and your environment before executing changes. Production changes should follow appropriate review, approval, validation, and rollback procedures.
+## About Reponx
+**Reponx — AI Engineers for Network and Cloud Operations.**
+Reponx combines specialized AI models with retrieval, operational context, tools, and controlled workflows to assist network and cloud operations teams.
+## License
+Apache-2.0