Instructions to use abacaj/llama-161M-100B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacaj/llama-161M-100B with Transformers:

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

pipe = pipeline("text-generation", model="abacaj/llama-161M-100B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abacaj/llama-161M-100B")
model = AutoModelForCausalLM.from_pretrained("abacaj/llama-161M-100B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abacaj/llama-161M-100B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abacaj/llama-161M-100B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacaj/llama-161M-100B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/abacaj/llama-161M-100B

SGLang

How to use abacaj/llama-161M-100B 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 "abacaj/llama-161M-100B" \
    --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": "abacaj/llama-161M-100B",
		"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 "abacaj/llama-161M-100B" \
        --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": "abacaj/llama-161M-100B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abacaj/llama-161M-100B with Docker Model Runner:
```
docker model run hf.co/abacaj/llama-161M-100B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

llama-161M

Trained on 100B tokens.

1e-3 LR
0.1 wd
WSD scheduler with 10% decay
80% code, 10% NL, 10% instruction data
Dataset decontaminated against popular benchmarks following bigcode
8x3090s 110~ hours

This is a base pretrained model and requires further fine tuning to be useful.

Model Details

openai/openai_humaneval (greedy)	mbpp (greedy)
9.2%	9.8%

Downloads last month: 74

Safetensors

Model size

0.2B params

Tensor type

BF16

Model tree for abacaj/llama-161M-100B

Quantizations

2 models

abacaj
/

llama-161M-100B

llama-161M

Model Details

Model tree for abacaj/llama-161M-100B

Spaces using abacaj/llama-161M-100B 7