Instructions to use MK0727/lambda-160m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MK0727/lambda-160m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MK0727/lambda-160m", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("MK0727/lambda-160m", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MK0727/lambda-160m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MK0727/lambda-160m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MK0727/lambda-160m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MK0727/lambda-160m
- SGLang
How to use MK0727/lambda-160m 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 "MK0727/lambda-160m" \ --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": "MK0727/lambda-160m", "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 "MK0727/lambda-160m" \ --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": "MK0727/lambda-160m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MK0727/lambda-160m with Docker Model Runner:
docker model run hf.co/MK0727/lambda-160m
| {"max_len": 1024, "d_model": 768, "num_layers": 16, "num_heads": 12, "d_ff": 3072, "learning_rate": 0.0002, "batch_size": 96, "gradient_accumulation_steps": 4, "effective_batch_size": 384, "lr_schedule": "warmup_cosine", "lr_warmup_steps": 2000, "min_learning_rate": 0.0001, "min_learning_rate_ratio": 0.5, "loss_chunk_size": 32, "pad_token_id": 0, "bos_token_id": 2, "eos_token_id": 3, "corpus_signature": "fb2af8e50eb90fad", "dataset_case": {"name": "cleaned-fineweb2-edu-jp", "genre": "web", "language": "ja", "dataset_path": "MK0727/CleanedFineWeb2Edu-jp", "config_name": "default", "split": "train", "text_column": "text"}, "val_split_modulo": 100, "val_split_index": 0, "validation_cache_path": "models/lambda-160m/validation-cache-fb2af8e50eb90fad-bucket-packing-v1-len1024-samples6144-split100-0.pt", "validation_sample_count": 6144, "packing_version": "bucket-packing-v1", "trained_steps": 10240} |