Text Generation
Transformers
Safetensors
mixtral
biology
protein-language-model
protein-generation
causal-lm
mixture-of-experts
text-generation-inference
Instructions to use protgpt3/ProtGPT3-112M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use protgpt3/ProtGPT3-112M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="protgpt3/ProtGPT3-112M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("protgpt3/ProtGPT3-112M") model = AutoModelForCausalLM.from_pretrained("protgpt3/ProtGPT3-112M") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use protgpt3/ProtGPT3-112M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "protgpt3/ProtGPT3-112M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "protgpt3/ProtGPT3-112M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/protgpt3/ProtGPT3-112M
- SGLang
How to use protgpt3/ProtGPT3-112M 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 "protgpt3/ProtGPT3-112M" \ --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": "protgpt3/ProtGPT3-112M", "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 "protgpt3/ProtGPT3-112M" \ --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": "protgpt3/ProtGPT3-112M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use protgpt3/ProtGPT3-112M with Docker Model Runner:
docker model run hf.co/protgpt3/ProtGPT3-112M
Update README.md
Browse files
README.md
CHANGED
|
@@ -70,7 +70,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
| 70 |
model_id = "protgpt3/ProtGPT3-112M" # Replace with the final checkpoint name
|
| 71 |
|
| 72 |
# Load tokenizer for generation
|
| 73 |
-
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True,add_bos_token=True, add_eos_token=False)
|
| 74 |
|
| 75 |
model = AutoModelForCausalLM.from_pretrained(
|
| 76 |
model_id,
|
|
|
|
| 70 |
model_id = "protgpt3/ProtGPT3-112M" # Replace with the final checkpoint name
|
| 71 |
|
| 72 |
# Load tokenizer for generation
|
| 73 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True,add_bos_token=True, add_eos_token=False, padding_side="left")
|
| 74 |
|
| 75 |
model = AutoModelForCausalLM.from_pretrained(
|
| 76 |
model_id,
|