Instructions to use yujiepan/llama-3.1-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/llama-3.1-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/llama-3.1-tiny-random")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/llama-3.1-tiny-random")
model = AutoModelForCausalLM.from_pretrained("yujiepan/llama-3.1-tiny-random", device_map="auto")
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 yujiepan/llama-3.1-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/llama-3.1-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/llama-3.1-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yujiepan/llama-3.1-tiny-random

SGLang

How to use yujiepan/llama-3.1-tiny-random 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 "yujiepan/llama-3.1-tiny-random" \
    --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": "yujiepan/llama-3.1-tiny-random",
		"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 "yujiepan/llama-3.1-tiny-random" \
        --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": "yujiepan/llama-3.1-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yujiepan/llama-3.1-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/llama-3.1-tiny-random
```

llama-3.1-tiny-random / README.md

yujiepan

Upload folder using huggingface_hub

86e669c verified about 2 years ago

preview code

Raw

History Blame Contribute Delete

1.72 kB

metadata

library_name: transformers
pipeline_tag: text-generation
inference: true
widget:
  - text: Hello!
    example_title: Hello world
    group: Python

This model is for debugging. It is randomly initialized using the config from meta-llama/Meta-Llama-3.1-70B-Instruct but with smaller size.

"yujiepan/llama-3.1-tiny-random" and "yujiepan/meta-llama-3.1-tiny-random" share exactly the same files except the repo name.

Codes:

import os

import torch
import transformers
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, GenerationConfig, pipeline, set_seed

model_id = "meta-llama/Meta-Llama-3.1-70B-Instruct"
repo_id = "yujiepan/meta-llama-3.1-tiny-random"
save_path = f"/tmp/{repo_id}"

config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
config._name_or_path = model_id
config.hidden_size = 8
config.intermediate_size = 16
config.num_attention_heads = 2
config.num_key_value_heads = 1
config.num_hidden_layers = 2
config.torch_dtype = "bfloat16"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
tokenizer.save_pretrained(save_path)

model = AutoModelForCausalLM.from_config(
    config, torch_dtype=torch.bfloat16, attn_implementation="sdpa", trust_remote_code=True
)
model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True)

set_seed(42)
with torch.no_grad():
    for _, p in sorted(model.named_parameters()):
        torch.nn.init.uniform_(p, -0.2, 0.2)

model.save_pretrained(save_path)

pipe = pipeline("text-generation", model=save_path, device="cuda", trust_remote_code=True, max_new_tokens=20)
print(pipe("Hello World!"))