Instructions to use jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29 with Transformers:

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

pipe = pipeline("text-generation", model="jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29")
model = AutoModelForCausalLM.from_pretrained("jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29")
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 jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29

SGLang

How to use jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29 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 "jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29" \
    --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": "jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29",
		"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 "jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29" \
        --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": "jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29 with Docker Model Runner:
```
docker model run hf.co/jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29
```

meta-LLama3-6B-PruneMe-TEST-21_29

This model was pruned after being analyzed with PruneMe

INFO: This model is not usable as is, and it must be 'healed' from pruning using techinques detailed in The Unreasonable Ineffectiveness of the Deeper Layers.

meta-LLama3-6B-PruneMe-TEST-21_29 is a merge of the following models using LazyMergekit:

🧩 Configuration

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

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 2

Safetensors

Model size

6B params

Tensor type

BF16

Model tree for jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29

Base model

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

Finetuned

(1125)

this model

Paper for jsfs11/meta-LLama3-6B-PruneMe-TEST-21_29

The Unreasonable Ineffectiveness of the Deeper Layers

Paper • 2403.17887 • Published Mar 26, 2024 • 83