Instructions to use Jolly-Q/70B_unstructWR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jolly-Q/70B_unstructWR with Transformers:

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

pipe = pipeline("text-generation", model="Jolly-Q/70B_unstructWR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jolly-Q/70B_unstructWR")
model = AutoModelForCausalLM.from_pretrained("Jolly-Q/70B_unstructWR")
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 Jolly-Q/70B_unstructWR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jolly-Q/70B_unstructWR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jolly-Q/70B_unstructWR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jolly-Q/70B_unstructWR

SGLang

How to use Jolly-Q/70B_unstructWR 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 "Jolly-Q/70B_unstructWR" \
    --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": "Jolly-Q/70B_unstructWR",
		"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 "Jolly-Q/70B_unstructWR" \
        --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": "Jolly-Q/70B_unstructWR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jolly-Q/70B_unstructWR with Docker Model Runner:
```
docker model run hf.co/Jolly-Q/70B_unstructWR
```

70B_unstructWR

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DELLA merge method using meta-llama/Llama-3.3-70B-Instruct as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:

  - model: schonsense/70B_unstruct
    parameters:
      density: 0.7
      epsilon: 0.2
      weight: 0.9
       
  - model: WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-70B
    parameters:
      density: 0.9
      epsilon: 0.05
      weight: 0.1

  - model: meta-llama/Llama-3.3-70B-Instruct
merge_method: della
base_model: meta-llama/Llama-3.3-70B-Instruct
tokenizer_source: meta-llama/Llama-3.3-70B-Instruct
parameters:
  normalize: false
  int8_mask: false
  lambda: 1.0


dtype: float32

out_dtype: bfloat16