Instructions to use ndavidson/iNAM-2.7B-v1.0-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ndavidson/iNAM-2.7B-v1.0-beta with Transformers:

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

pipe = pipeline("text-generation", model="ndavidson/iNAM-2.7B-v1.0-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ndavidson/iNAM-2.7B-v1.0-beta")
model = AutoModelForCausalLM.from_pretrained("ndavidson/iNAM-2.7B-v1.0-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use ndavidson/iNAM-2.7B-v1.0-beta with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ndavidson/iNAM-2.7B-v1.0-beta",
	filename="phi.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ndavidson/iNAM-2.7B-v1.0-beta with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ndavidson/iNAM-2.7B-v1.0-beta
# Run inference directly in the terminal:
llama-cli -hf ndavidson/iNAM-2.7B-v1.0-beta

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ndavidson/iNAM-2.7B-v1.0-beta
# Run inference directly in the terminal:
llama-cli -hf ndavidson/iNAM-2.7B-v1.0-beta

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ndavidson/iNAM-2.7B-v1.0-beta
# Run inference directly in the terminal:
./llama-cli -hf ndavidson/iNAM-2.7B-v1.0-beta

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ndavidson/iNAM-2.7B-v1.0-beta
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ndavidson/iNAM-2.7B-v1.0-beta

Use Docker

docker model run hf.co/ndavidson/iNAM-2.7B-v1.0-beta

LM Studio
Jan

vLLM

How to use ndavidson/iNAM-2.7B-v1.0-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ndavidson/iNAM-2.7B-v1.0-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ndavidson/iNAM-2.7B-v1.0-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ndavidson/iNAM-2.7B-v1.0-beta

SGLang

How to use ndavidson/iNAM-2.7B-v1.0-beta 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 "ndavidson/iNAM-2.7B-v1.0-beta" \
    --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": "ndavidson/iNAM-2.7B-v1.0-beta",
		"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 "ndavidson/iNAM-2.7B-v1.0-beta" \
        --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": "ndavidson/iNAM-2.7B-v1.0-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ndavidson/iNAM-2.7B-v1.0-beta with Ollama:
```
ollama run hf.co/ndavidson/iNAM-2.7B-v1.0-beta
```

Unsloth Studio new

How to use ndavidson/iNAM-2.7B-v1.0-beta with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ndavidson/iNAM-2.7B-v1.0-beta to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ndavidson/iNAM-2.7B-v1.0-beta to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ndavidson/iNAM-2.7B-v1.0-beta to start chatting

Docker Model Runner
How to use ndavidson/iNAM-2.7B-v1.0-beta with Docker Model Runner:
```
docker model run hf.co/ndavidson/iNAM-2.7B-v1.0-beta
```

Lemonade

How to use ndavidson/iNAM-2.7B-v1.0-beta with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ndavidson/iNAM-2.7B-v1.0-beta

Run and chat with the model

lemonade run user.iNAM-2.7B-v1.0-beta-{{QUANT_TAG}}

List all available models

lemonade list

Cisco iNAM

Cisco iNAM (Intelligent Networking, Automation, and Management), is a nano sized LLM used for asking questions about Cisco Datacenter Products. It is finetuned from the pretrained Phi-2 model from Microsoft Research.

Model Details

Model Description

Model is quantized to 4-bit to be able to run inference on physical deployments of datacenter products. Initial launch is planned for Nexus Dashboard.

Developed by: Cisco
Funded by [optional]: Cisco
Model type: Transformer
Language(s) (NLP): English
License: Cisco Commercial

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Prompt Format

iNAM uses ChatML as the prompt format.

It's recommended to always prompt with a system instruction (use whatever system prompt you like):

<|im_start|>system
You are a helpful assistant for Python which outputs in Markdown format.<|im_end|>
<|im_start|>user
Write a function to calculate the Fibonacci sequence<|im_end|>
<|im_start|>assistant

Downloads last month: 43

GGUF

Model size

3B params

Architecture

phi2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

ndavidson
/

iNAM-2.7B-v1.0-beta

Cisco iNAM

Model Details

Model Description

Model Sources [optional]

Prompt Format

Dataset used to train ndavidson/iNAM-2.7B-v1.0-beta