Instructions to use thelamapi/next-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thelamapi/next-1b with Transformers:

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

pipe = pipeline("text-generation", model="thelamapi/next-1b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thelamapi/next-1b")
model = AutoModelForCausalLM.from_pretrained("thelamapi/next-1b")
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 thelamapi/next-1b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="thelamapi/next-1b",
	filename="next-1b-bf16.gguf",
)

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

Inference
Local Apps Settings

llama.cpp

How to use thelamapi/next-1b 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 thelamapi/next-1b:BF16
# Run inference directly in the terminal:
llama cli -hf thelamapi/next-1b:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf thelamapi/next-1b:BF16
# Run inference directly in the terminal:
llama cli -hf thelamapi/next-1b:BF16

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 thelamapi/next-1b:BF16
# Run inference directly in the terminal:
./llama-cli -hf thelamapi/next-1b:BF16

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 thelamapi/next-1b:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf thelamapi/next-1b:BF16

Use Docker

docker model run hf.co/thelamapi/next-1b:BF16

LM Studio
Jan

vLLM

How to use thelamapi/next-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thelamapi/next-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thelamapi/next-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thelamapi/next-1b:BF16

SGLang

How to use thelamapi/next-1b 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 "thelamapi/next-1b" \
    --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": "thelamapi/next-1b",
		"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 "thelamapi/next-1b" \
        --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": "thelamapi/next-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use thelamapi/next-1b with Ollama:
```
ollama run hf.co/thelamapi/next-1b:BF16
```

Unsloth Studio

How to use thelamapi/next-1b 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 thelamapi/next-1b 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 thelamapi/next-1b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for thelamapi/next-1b to start chatting

Atomic Chat new
Docker Model Runner
How to use thelamapi/next-1b with Docker Model Runner:
```
docker model run hf.co/thelamapi/next-1b:BF16
```

Lemonade

How to use thelamapi/next-1b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull thelamapi/next-1b:BF16

Run and chat with the model

lemonade run user.next-1b-BF16

List all available models

lemonade list

Lamapi commited on about 1 month ago

Commit

cdab7fa

verified ·

1 Parent(s): 8ec22db

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -91

README.md CHANGED Viewed

@@ -140,97 +140,6 @@ Ideal for **developers, students, and organizations** needing **fast, reliable,
 ---
-# Our Next 1B and Next 4B models are leading to all of the tiny models in benchmarks.
-<table>
-  <thead>
-    <tr>
-      <th>Model</th>
-      <th>MMLU (5-shot) %</th>
-      <th>MMLU-Pro %</th>
-      <th>GSM8K %</th>
-      <th>MATH %</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr class="next">
-      <td data-label="Model">Next 4B preview</td>
-      <td data-label="MMLU (5-shot) %">84.6</td>
-      <td data-label="MMLU-Pro %">66.9</td>
-      <td data-label="GSM8K %">82.7</td>
-      <td data-label="MATH %"><strong>70.5</strong></td>
-    </tr>
-    <tr class="next">
-      <td data-label="Model">Next 1B <em>Version t327</em></td>
-      <td data-label="MMLU (5-shot) %"><strong>87.3</strong></td>
-      <td data-label="MMLU-Pro %"><strong>69.2</strong></td>
-      <td data-label="GSM8K %"><strong>90.5</strong></td>
-      <td data-label="MATH %">70.1</td>
-    </tr>
-    <tr>
-      <td data-label="Model">Qwen 3 0.6B</td>
-      <td data-label="MMLU (5-shot) %">52.81</td>
-      <td data-label="MMLU-Pro %">37.6</td>
-      <td data-label="GSM8K %">60.7</td>
-      <td data-label="MATH %">20.5</td>
-    </tr>
-    <tr>
-      <td data-label="Model">Llama 3.2 1B</td>
-      <td data-label="MMLU (5-shot) %">49.3</td>
-      <td data-label="MMLU-Pro %">44.4</td>
-      <td data-label="GSM8K %">11.9</td>
-      <td data-label="MATH %">30.6</td>
-    </tr>
-  </tbody>
-</table>
----
-# Also, our Next 14b model is leading to state-of-the-art models in some of the Benchmarks.
-<table>
-  <thead>
-    <tr>
-      <th>Model</th>
-      <th>MMLU (5-shot) %</th>
-      <th>MMLU-Pro %</th>
-      <th>GSM8K %</th>
-      <th>MATH %</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr class="next">
-      <td><strong>Next 14B (Thinking)</strong></td>
-      <td><strong>94.6</strong></td>
-      <td><strong>93.2</strong></td>
-      <td><strong>98.8</strong></td>
-      <td>92.7</td>
-    </tr>
-    <tr>
-      <td>Next 12B</td>
-      <td>92.7</td>
-      <td>84.4</td>
-      <td>95.3</td>
-      <td>87.2</td>
-    </tr>
-    <tr>
-      <td>GPT-5</td>
-      <td>92.5</td>
-      <td>87.0</td>
-      <td>98.4</td>
-      <td><strong>96.0</strong></td>
-    </tr>
-    <tr>
-      <td>Claude Opus 4.1 (Thinking)</td>
-      <td>~92.0</td>
-      <td>87.8</td>
-      <td>84.7</td>
-      <td>95.4</td>
-    </tr>
-  </tbody>
-</table>
----
 ## 🎯 Goals
 1. **Lightweight Efficiency:** Run smoothly on low-resource devices.

 ---
 ## 🎯 Goals
 1. **Lightweight Efficiency:** Run smoothly on low-resource devices.