Instructions to use grimjim/wizard-elem-to-32k-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/wizard-elem-to-32k-7B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/wizard-elem-to-32k-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/wizard-elem-to-32k-7B")
model = AutoModelForCausalLM.from_pretrained("grimjim/wizard-elem-to-32k-7B")
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 Settings

vLLM

How to use grimjim/wizard-elem-to-32k-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/wizard-elem-to-32k-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/wizard-elem-to-32k-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/wizard-elem-to-32k-7B

SGLang

How to use grimjim/wizard-elem-to-32k-7B 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 "grimjim/wizard-elem-to-32k-7B" \
    --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": "grimjim/wizard-elem-to-32k-7B",
		"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 "grimjim/wizard-elem-to-32k-7B" \
        --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": "grimjim/wizard-elem-to-32k-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/wizard-elem-to-32k-7B with Docker Model Runner:
```
docker model run hf.co/grimjim/wizard-elem-to-32k-7B
```

wizard-elem-to-32k-7B

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

In theory, context length has been extended to 32K tokens. In practice? Degradation above 8K context length.

Tested with ChatML instruct prompts, temperature 1.0, and minP 0.01, but feel free to experiment.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
dtype: bfloat16
merge_method: task_arithmetic
slices:
- sources:
  - layer_range: [0, 32]
    model: grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
  - layer_range: [0, 32]
    model: lucyknada/microsoft_WizardLM-2-7B
    parameters:
      weight: 1.00