Instructions to use BEE-spoke-data/Jamba-900M-doc-writer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BEE-spoke-data/Jamba-900M-doc-writer with Transformers:

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

pipe = pipeline("text-generation", model="BEE-spoke-data/Jamba-900M-doc-writer")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BEE-spoke-data/Jamba-900M-doc-writer")
model = AutoModelForCausalLM.from_pretrained("BEE-spoke-data/Jamba-900M-doc-writer")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BEE-spoke-data/Jamba-900M-doc-writer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BEE-spoke-data/Jamba-900M-doc-writer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BEE-spoke-data/Jamba-900M-doc-writer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BEE-spoke-data/Jamba-900M-doc-writer

SGLang

How to use BEE-spoke-data/Jamba-900M-doc-writer 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 "BEE-spoke-data/Jamba-900M-doc-writer" \
    --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": "BEE-spoke-data/Jamba-900M-doc-writer",
		"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 "BEE-spoke-data/Jamba-900M-doc-writer" \
        --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": "BEE-spoke-data/Jamba-900M-doc-writer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BEE-spoke-data/Jamba-900M-doc-writer with Docker Model Runner:
```
docker model run hf.co/BEE-spoke-data/Jamba-900M-doc-writer
```

BEE-spoke-data/Jamba-900M-doc-writer

to test it out, try this notebook

This model produces long, surprisingly coherent output that extends some input text; you can see an example here, which is a generated textbook about underwater city design.

Thanks to the Jamba arch, it uses low VRAM while generating outputs: about 2.5 GB VRAM to generate 12,288 tokens.

Model description

This model is a fine-tuned version of pszemraj/jamba-900M-v0.13-KIx2 on some textbook data.

It achieves the following results on the evaluation set:

Loss: 3.0200
Accuracy: 0.4544
Num Input Tokens Seen: 4940890112

Intended Uses & Limitations

Long context generation
It requires a rather long prompt (aka 'Introduction') to be coaxed into consistently producing long, textbook-like text
this model itself is small, so its reasoning, knowledge, etc. is limited, but still impressive for the size (hidden size 1024)

Downloads last month: 6

Safetensors

Model size

0.9B params

Tensor type

F32

BF16

Model tree for BEE-spoke-data/Jamba-900M-doc-writer

Base model

pszemraj/jamba-900M-v0.13-KIx2

Finetuned

(1)

this model