Instructions to use jbenbudd/ptm-llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jbenbudd/ptm-llama with Transformers:

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

pipe = pipeline("text-generation", model="jbenbudd/ptm-llama", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jbenbudd/ptm-llama")
model = AutoModelForCausalLM.from_pretrained("jbenbudd/ptm-llama", device_map="auto")

PEFT
How to use jbenbudd/ptm-llama with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jbenbudd/ptm-llama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jbenbudd/ptm-llama

SGLang

How to use jbenbudd/ptm-llama 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 "jbenbudd/ptm-llama" \
    --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": "jbenbudd/ptm-llama",
		"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 "jbenbudd/ptm-llama" \
        --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": "jbenbudd/ptm-llama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jbenbudd/ptm-llama with Docker Model Runner:
```
docker model run hf.co/jbenbudd/ptm-llama
```

ptm-llama / inference_config.json

jbenbudd

Push evaluation artifacts and model card

76652d6 verified 15 days ago

Raw

History Blame Contribute Delete

804 Bytes

	{
	"window_size": 21,
	"stride": 5,
	"max_new_tokens": 64,
	"prompt_template": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n{input}\n\n### Response:\n",
	"instructions": {
	"Methylation": "[Predict the methylation sites given the peptide sequence]",
	"Phosphorylation": "[Predict the phosphorylation sites given the peptide sequence]",
	"Ubiquitination": "[Predict the ubiquitination sites given the peptide sequence]"
	},
	"consensus_thresholds": {
	"Methylation": 0.3333333432674408,
	"Phosphorylation": 0.20000000298023224,
	"Ubiquitination": 0.20000000298023224
	},
	"output_format": "Sites=<X1,X2,...> where Xi is one-letter residue + 1-indexed position within the window"
	}