Instructions to use ryan0712/llama-3-8b-slow-DUS-max-method2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ryan0712/llama-3-8b-slow-DUS-max-method2 with Transformers:

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

pipe = pipeline("text-generation", model="ryan0712/llama-3-8b-slow-DUS-max-method2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ryan0712/llama-3-8b-slow-DUS-max-method2")
model = AutoModelForCausalLM.from_pretrained("ryan0712/llama-3-8b-slow-DUS-max-method2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ryan0712/llama-3-8b-slow-DUS-max-method2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ryan0712/llama-3-8b-slow-DUS-max-method2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ryan0712/llama-3-8b-slow-DUS-max-method2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ryan0712/llama-3-8b-slow-DUS-max-method2

SGLang

How to use ryan0712/llama-3-8b-slow-DUS-max-method2 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 "ryan0712/llama-3-8b-slow-DUS-max-method2" \
    --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": "ryan0712/llama-3-8b-slow-DUS-max-method2",
		"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 "ryan0712/llama-3-8b-slow-DUS-max-method2" \
        --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": "ryan0712/llama-3-8b-slow-DUS-max-method2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ryan0712/llama-3-8b-slow-DUS-max-method2 with Docker Model Runner:
```
docker model run hf.co/ryan0712/llama-3-8b-slow-DUS-max-method2
```

llama-3-8b-slow-DUS-max-method2

llama-3-8b-slow-DUS-max-method2 is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:

  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [0, 1]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [0, 1]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [1, 2]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [1, 2]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [2, 3]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [2, 3]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [3, 4]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [3, 4]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [4, 5]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [4, 5]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [5, 6]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [5, 6]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [6, 7]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [6, 7]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [7, 8]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [7, 8]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [8, 9]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [8, 9]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [9, 10]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [9, 10]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [10, 11]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [10, 11]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [11, 12]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [11, 12]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [12, 13]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [12, 13]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [13, 14]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [13, 14]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [14, 15]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [14, 15]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [15, 16]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [16, 17]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [17, 18]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [18, 19]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [19, 20]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [20, 21]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [21, 22]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [22, 23]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [23, 24]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [24, 25]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [25, 26]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [26, 27]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [27, 28]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [28, 29]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [29, 30]
    
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [30, 31]
    
  - sources:
      - model: ryan0712/llama-3-8b-slow-DUS-max-layer-method2
        layer_range: [15, 16]
        
  - sources:
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [31, 32]
    
merge_method: passthrough
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ryan0712/llama-3-8b-slow-DUS-max-method2"
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: 7

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for ryan0712/llama-3-8b-slow-DUS-max-method2

NousResearch/Meta-Llama-3-8B

ryan0712/llama-3-8b-slow-DUS-max-layer-method2

Merge model

this model