Instructions to use aloobun/Meta-Llama-3-7B-29Layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aloobun/Meta-Llama-3-7B-29Layers with Transformers:

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

pipe = pipeline("text-generation", model="aloobun/Meta-Llama-3-7B-29Layers")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aloobun/Meta-Llama-3-7B-29Layers")
model = AutoModelForCausalLM.from_pretrained("aloobun/Meta-Llama-3-7B-29Layers", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aloobun/Meta-Llama-3-7B-29Layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aloobun/Meta-Llama-3-7B-29Layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aloobun/Meta-Llama-3-7B-29Layers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aloobun/Meta-Llama-3-7B-29Layers

SGLang

How to use aloobun/Meta-Llama-3-7B-29Layers 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 "aloobun/Meta-Llama-3-7B-29Layers" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aloobun/Meta-Llama-3-7B-29Layers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "aloobun/Meta-Llama-3-7B-29Layers" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aloobun/Meta-Llama-3-7B-29Layers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aloobun/Meta-Llama-3-7B-29Layers with Docker Model Runner:
```
docker model run hf.co/aloobun/Meta-Llama-3-7B-29Layers
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Meta's Llama 3 8B pruned to 7B parameters(w/ 29 layers). Layers to prune selected using PruneMe repo on Github.

layers_to_skip = 3
Layer 24 to 27 has the minimum average distance of 0.15680849609375.
To Do : Post pruning training.

model

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

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: meta-llama/Meta-Llama-3-8B
        layer_range: [0, 24]
  - sources:
      - model: meta-llama/Meta-Llama-3-8B
        layer_range: [27,32]
            
merge_method: passthrough
dtype: bfloat16

Downloads last month: 8

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for aloobun/Meta-Llama-3-7B-29Layers

Base model

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

Finetuned

(610)

this model

Quantizations

1 model