Instructions to use Severian/Jamba-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Severian/Jamba-13B with Transformers:

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

pipe = pipeline("text-generation", model="Severian/Jamba-13B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Severian/Jamba-13B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Severian/Jamba-13B", trust_remote_code=True)
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Severian/Jamba-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Severian/Jamba-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Severian/Jamba-13B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Severian/Jamba-13B

SGLang

How to use Severian/Jamba-13B 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 "Severian/Jamba-13B" \
    --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": "Severian/Jamba-13B",
		"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 "Severian/Jamba-13B" \
        --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": "Severian/Jamba-13B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Severian/Jamba-13B with Docker Model Runner:
```
docker model run hf.co/Severian/Jamba-13B
```

Severian commited on Apr 8, 2024

Commit

fb2df2e

verified ·

1 Parent(s): efaeb71

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -33

README.md CHANGED Viewed

@@ -3,36 +3,4 @@ library_name: transformers
 tags: []
 ---
-# Jamba-Small v1
-This is a pruned version of AI21 Labs' Jamba-v0.1 model that is ~25% the size of Jamba-v0.1.
-## Model Details
-Whereas Jamba-v0.1 contains 4 Jamba blocks, Jamba-Small contains only 1 Jamba block.
-Jamba-Small's Jamba blocks follow the same structure seen in Jamba-v0.1, with a 1:7 ratio of attention-to-Mamba layers and MoE applied every 2 layers.
-Jamba-Small's weights are initialized from various layers in the original Jamba-v0.1 model. For v1, the layer weights are mapped as follows (left is Jamba-Small layer number, right is Jamba-v0.1 layer number):
-```
-0: 0
-1: 1
-2: 2
-3: 3
-4: 4
-5: 5
-6: 30
-7: 31
-```
-Note that no additional fine-tuning has been performed on this model. As such, its performance is exceptionally poor. This should not be used in production without additional training.
-### Model Description
-- **Developed by:** Nathan Brown (OxxoCodes)
-- **Compute provided by:** Clemson Palmetto Cluster
-- **Model type:** Joint Attention and Mamba (Jamba)
-- **Language(s) (NLP):** English
-- **License:** Apache 2.0
-- **Original model:** [Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1)
-- **Jamba paper:** [https://arxiv.org/pdf/2403.19887.pdf](https://arxiv.org/pdf/2403.19887.pdf)

 tags: []
 ---
+# Jamba-13B