Instructions to use GammaAGI/ai21-jamba-3b-merge-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GammaAGI/ai21-jamba-3b-merge-v1 with Transformers:

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

pipe = pipeline("text-generation", model="GammaAGI/ai21-jamba-3b-merge-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GammaAGI/ai21-jamba-3b-merge-v1")
model = AutoModelForCausalLM.from_pretrained("GammaAGI/ai21-jamba-3b-merge-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GammaAGI/ai21-jamba-3b-merge-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GammaAGI/ai21-jamba-3b-merge-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GammaAGI/ai21-jamba-3b-merge-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GammaAGI/ai21-jamba-3b-merge-v1

SGLang

How to use GammaAGI/ai21-jamba-3b-merge-v1 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 "GammaAGI/ai21-jamba-3b-merge-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GammaAGI/ai21-jamba-3b-merge-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "GammaAGI/ai21-jamba-3b-merge-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GammaAGI/ai21-jamba-3b-merge-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GammaAGI/ai21-jamba-3b-merge-v1 with Docker Model Runner:
```
docker model run hf.co/GammaAGI/ai21-jamba-3b-merge-v1
```

GAMMAai Jamba 3B Merge v1

This repository contains a complete Jamba-family research checkpoint from the first GAMMAai fusion batch. It combines the compact instruction profile of ai21labs/AI21-Jamba2-3B with the reasoning-oriented Jamba 3B branch while retaining a single deployable JambaForCausalLM checkpoint.

Checkpoint

Architecture: hybrid Mamba/attention JambaForCausalLM
Hidden size: 2,560
Layers: 28
Attention cadence: one attention layer every 14 layers
Precision: FP16
Declared context window: 262,144 tokens
Weight package: one complete model.safetensors file
Tokenizer, chat template and configuration: included

The two parent checkpoints share the same Jamba 3B topology and Apache-2.0 license family. The public artifact is structurally complete. The exact coefficient history from the early fusion run was not preserved in this repository, so this release is presented as a research checkpoint rather than as a benchmark-certified replacement for either parent.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "GammaAGI/ai21-jamba-3b-merge-v1"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [{"role": "user", "content": "Explain why staged verification reduces model-training risk."}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)
output = model.generate(inputs, max_new_tokens=160, do_sample=False)
print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))

Intended Use

The checkpoint is intended for research, comparative inference, chromosome extraction and controlled downstream adaptation. Validate task quality, long-context behavior and safety on your own workload before production use.

Limitations

No public benchmark superiority claim is made.
The 262K configuration value is not a substitute for measured long-context quality at every length.
Fusion can inherit limitations and biases from both parent checkpoints.
Production deployment requires an independent generation and safety evaluation.

Project

GAMMAai develops verifier-first, staged model evolution through EvoStream, SafeTrain and measurable no-regress gates. This checkpoint is retained as a complete historical model product; temporary adapters, failed experiments and partial weight artifacts are maintained outside the public model catalog.

Downloads last month: 88

Safetensors

Model size

3B params

Tensor type

F16

Model tree for GammaAGI/ai21-jamba-3b-merge-v1

Base model

ai21labs/AI21-Jamba-Reasoning-3B

Finetuned

(7)

this model