Instructions to use deqing/llama-600M-v4-bigram with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deqing/llama-600M-v4-bigram with Transformers:

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

pipe = pipeline("text-generation", model="deqing/llama-600M-v4-bigram")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deqing/llama-600M-v4-bigram")
model = AutoModelForCausalLM.from_pretrained("deqing/llama-600M-v4-bigram")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deqing/llama-600M-v4-bigram with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deqing/llama-600M-v4-bigram"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deqing/llama-600M-v4-bigram",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deqing/llama-600M-v4-bigram

SGLang

How to use deqing/llama-600M-v4-bigram 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 "deqing/llama-600M-v4-bigram" \
    --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": "deqing/llama-600M-v4-bigram",
		"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 "deqing/llama-600M-v4-bigram" \
        --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": "deqing/llama-600M-v4-bigram",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deqing/llama-600M-v4-bigram with Docker Model Runner:
```
docker model run hf.co/deqing/llama-600M-v4-bigram
```

llama-600M-v4-bigram

This model is a fine-tuned version of llama_600M_config.json on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.8477
Num Input Tokens Seen: 9437184000

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 16
total_train_batch_size: 512
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 500
num_epochs: 1

Training results

Framework versions

Transformers 5.3.0
Pytorch 2.10.0+cu128
Datasets 4.7.0
Tokenizers 0.22.2

Downloads last month: 36

Safetensors

Model size

0.6B params

Tensor type

F32