Instructions to use kuotient/Llama-3-6B-Instruct-pruned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kuotient/Llama-3-6B-Instruct-pruned with Transformers:

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

pipe = pipeline("text-generation", model="kuotient/Llama-3-6B-Instruct-pruned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kuotient/Llama-3-6B-Instruct-pruned")
model = AutoModelForCausalLM.from_pretrained("kuotient/Llama-3-6B-Instruct-pruned")
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 kuotient/Llama-3-6B-Instruct-pruned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kuotient/Llama-3-6B-Instruct-pruned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kuotient/Llama-3-6B-Instruct-pruned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kuotient/Llama-3-6B-Instruct-pruned

SGLang

How to use kuotient/Llama-3-6B-Instruct-pruned 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 "kuotient/Llama-3-6B-Instruct-pruned" \
    --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": "kuotient/Llama-3-6B-Instruct-pruned",
		"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 "kuotient/Llama-3-6B-Instruct-pruned" \
        --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": "kuotient/Llama-3-6B-Instruct-pruned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kuotient/Llama-3-6B-Instruct-pruned with Docker Model Runner:
```
docker model run hf.co/kuotient/Llama-3-6B-Instruct-pruned
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-6B-Instruct-pruned

Experimental

Using PruneMe to find minimal average distance. Thank you for awesome toolkit @arcee-ai ! It shows pruning the 22-30 layer is the best option, but I'm worried about drasitical change between 22 to 23.

Disclaimer

I haven't done any post-training (called 'healing' process as the paper suggests), will do it later but no guarantee at all.

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

meta-llama/Meta-Llama-3-8B-Instruct

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model:
      model:
        path: meta-llama/Meta-Llama-3-8B-Instruct
- sources:
  - layer_range: [29, 32]
    model:
      model:
        path: meta-llama/Meta-Llama-3-8B-Instruct