Instructions to use KeisukeMiyamoto/lambda-1-160m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KeisukeMiyamoto/lambda-1-160m-base with Transformers:

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

pipe = pipeline("text-generation", model="KeisukeMiyamoto/lambda-1-160m-base")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("KeisukeMiyamoto/lambda-1-160m-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KeisukeMiyamoto/lambda-1-160m-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KeisukeMiyamoto/lambda-1-160m-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KeisukeMiyamoto/lambda-1-160m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KeisukeMiyamoto/lambda-1-160m-base

SGLang

How to use KeisukeMiyamoto/lambda-1-160m-base 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 "KeisukeMiyamoto/lambda-1-160m-base" \
    --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": "KeisukeMiyamoto/lambda-1-160m-base",
		"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 "KeisukeMiyamoto/lambda-1-160m-base" \
        --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": "KeisukeMiyamoto/lambda-1-160m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KeisukeMiyamoto/lambda-1-160m-base with Docker Model Runner:
```
docker model run hf.co/KeisukeMiyamoto/lambda-1-160m-base
```

lambda-1-160m-base / model_config.json

KeisukeMiyamoto

Restore base model after accidental instruction-tuned upload

cb3ea94 verified 24 days ago

Raw

History Blame Contribute Delete

1.18 kB

{"max_len": 1024, "d_model": 768, "num_layers": 16, "num_heads": 12, "d_ff": 2048, "learning_rate": 0.0001, "batch_size": 16, "gradient_accumulation_steps": 2, "devices": "auto", "device_count": 4, "global_batch_size": 64, "effective_batch_size": 32, "global_effective_batch_size": 128, "lr_schedule": "warmup_cosine", "lr_warmup_steps": 1000, "min_learning_rate": 2e-05, "min_learning_rate_ratio": 0.2, "loss_chunk_size": 32, "pad_token_id": 0, "bos_token_id": 2, "eos_token_id": 3, "corpus_signature": "ba5e40d4dae8dceb", "dataset_case": {"name": "synthetic-textbook-jp", "genre": "textbook", "language": "ja", "dataset_path": "MK0727/SyntheticTextbook-jp", "config_name": "default", "split": "train", "text_column": "rewrite"}, "val_split_modulo": 100, "val_split_index": 0, "validation_cache_path": "models/lambda-160m-midtrained/validation-cache-ba5e40d4dae8dceb-bucket-packing-v1-len1024-samples4096-split100-0.pt", "validation_sample_count": 4096, "packing_version": "bucket-packing-v1", "shuffle_buffer_size": 10000, "base_shuffle_seed": 17, "shuffle_seed": 17, "trained_steps": 20480, "midtraining_source_model": "models/lambda-160m", "midtraining_max_steps": 20480}