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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jolly-Q/70B_unstruct"
# 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_unstruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

schonsense commited on Jul 9, 2025

Commit

e55a811

verified ·

1 Parent(s): 26e1dbb

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -11,6 +11,8 @@ tags:
 ---
 # 70B_unstruct
 This is an attempt to take llama 3.3 instruct and peel back some of it's instruct following overtraining and positivity.  By using 3.3 instruct as the base model and merging in 3.1 base as well as the 3.3 abiliteration this merge subtracts out ~80% of the largest changes between 3.1 and 3.3 at 0.5 weight. In addition, the abiliteration of the refusal pathway is added (or subtracted) back in to the model at 0.5 weight.
 In theory this creates a ~75% refusal abliterated model with ~70% of it's instruct following capabilities intact, healed some in addition to having its instruct overtuning rolled back ~50%.

 ---
 # 70B_unstruct
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317d4867690c5b55e61ce3d/Rve1WXkbTZyGWnCHXDmMJ.png)
 This is an attempt to take llama 3.3 instruct and peel back some of it's instruct following overtraining and positivity.  By using 3.3 instruct as the base model and merging in 3.1 base as well as the 3.3 abiliteration this merge subtracts out ~80% of the largest changes between 3.1 and 3.3 at 0.5 weight. In addition, the abiliteration of the refusal pathway is added (or subtracted) back in to the model at 0.5 weight.
 In theory this creates a ~75% refusal abliterated model with ~70% of it's instruct following capabilities intact, healed some in addition to having its instruct overtuning rolled back ~50%.