Instructions to use softwareweaver/Twilight-XL-195B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use softwareweaver/Twilight-XL-195B with Transformers:

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

pipe = pipeline("text-generation", model="softwareweaver/Twilight-XL-195B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("softwareweaver/Twilight-XL-195B")
model = AutoModelForCausalLM.from_pretrained("softwareweaver/Twilight-XL-195B")
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 softwareweaver/Twilight-XL-195B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "softwareweaver/Twilight-XL-195B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "softwareweaver/Twilight-XL-195B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/softwareweaver/Twilight-XL-195B

SGLang

How to use softwareweaver/Twilight-XL-195B 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 "softwareweaver/Twilight-XL-195B" \
    --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": "softwareweaver/Twilight-XL-195B",
		"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 "softwareweaver/Twilight-XL-195B" \
        --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": "softwareweaver/Twilight-XL-195B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use softwareweaver/Twilight-XL-195B with Docker Model Runner:
```
docker model run hf.co/softwareweaver/Twilight-XL-195B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Twilight-XL

This is a merge of pre-trained language models created using mergekit by @softwareweaver. Use the prompt format that Mistral Large uses.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

/mnt/sda/ai/models/Twilight-Large

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 70]
    model: /mnt/sda/ai/models/Twilight-Large
- sources: 
  - layer_range: [18, 87]
    model: /mnt/sda/ai/models/Twilight-Large

Downloads last month: 1

Safetensors

Model size

193B params

Tensor type

BF16

Model tree for softwareweaver/Twilight-XL-195B

Finetunes

1 model

Quantizations

2 models