Instructions to use jwnder/core42_jais-13b-chat-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jwnder/core42_jais-13b-chat-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="jwnder/core42_jais-13b-chat-bnb-4bit", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jwnder/core42_jais-13b-chat-bnb-4bit", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jwnder/core42_jais-13b-chat-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jwnder/core42_jais-13b-chat-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jwnder/core42_jais-13b-chat-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jwnder/core42_jais-13b-chat-bnb-4bit

SGLang

How to use jwnder/core42_jais-13b-chat-bnb-4bit 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 "jwnder/core42_jais-13b-chat-bnb-4bit" \
    --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": "jwnder/core42_jais-13b-chat-bnb-4bit",
		"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 "jwnder/core42_jais-13b-chat-bnb-4bit" \
        --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": "jwnder/core42_jais-13b-chat-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jwnder/core42_jais-13b-chat-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/jwnder/core42_jais-13b-chat-bnb-4bit
```

This is a quantized version of the Jais-13b-chat model

To load this model you will need the bitsandbytes quantization method

If you are using text-generator-webui Select Transformers

Compute d-type: bfloat16
Quantization Type : nf4
Load in 4-bit: True
Use double quantization: True

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import transformers
import torch

model_name = "jwnder/core42_jais-13b-chat-bnb-4bit"

import warnings
warnings.filterwarnings('ignore')

tokenizer = AutoTokenizer.from_pretrained(model_input_folder, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_input_folder, trust_remote_code=True)

inputs = tokenizer("Testing LLM!", return_tensors="pt")
start = datetime.now()
outputs = model.generate(**inputs)
end = datetime.now()
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))

Downloads last month: 39

Safetensors

Model size

13B params

Tensor type

F32

F16