Instructions to use InstructPLM/MPNN-ProGen2-xlarge-CATH42 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InstructPLM/MPNN-ProGen2-xlarge-CATH42 with Transformers:

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

pipe = pipeline("text-generation", model="InstructPLM/MPNN-ProGen2-xlarge-CATH42", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("InstructPLM/MPNN-ProGen2-xlarge-CATH42", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InstructPLM/MPNN-ProGen2-xlarge-CATH42 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InstructPLM/MPNN-ProGen2-xlarge-CATH42"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InstructPLM/MPNN-ProGen2-xlarge-CATH42",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/InstructPLM/MPNN-ProGen2-xlarge-CATH42

SGLang

How to use InstructPLM/MPNN-ProGen2-xlarge-CATH42 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 "InstructPLM/MPNN-ProGen2-xlarge-CATH42" \
    --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": "InstructPLM/MPNN-ProGen2-xlarge-CATH42",
		"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 "InstructPLM/MPNN-ProGen2-xlarge-CATH42" \
        --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": "InstructPLM/MPNN-ProGen2-xlarge-CATH42",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use InstructPLM/MPNN-ProGen2-xlarge-CATH42 with Docker Model Runner:
```
docker model run hf.co/InstructPLM/MPNN-ProGen2-xlarge-CATH42
```

Junde commited on Jun 6, 2024

Commit

b1633e6

verified ·

1 Parent(s): 5f6652b

Update tokenization_iPLM.py

Browse files

fix bug when not passing '|' in input seq

Files changed (1) hide show

tokenization_iPLM.py +1 -1

tokenization_iPLM.py CHANGED Viewed

@@ -66,7 +66,7 @@ class iPLMTokenizer(PreTrainedTokenizerFast):
                     attn_mask_prefix[i] = True
             else:
-                raw_text.append(text)
         batch = super().__call__(raw_text, text_pair, text_target, text_pair_target, add_special_tokens, padding, truncation, max_length, stride, is_split_into_words, pad_to_multiple_of, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose, **kwargs)

                     attn_mask_prefix[i] = True
             else:
+                raw_text.append(text[i])
         batch = super().__call__(raw_text, text_pair, text_target, text_pair_target, add_special_tokens, padding, truncation, max_length, stride, is_split_into_words, pad_to_multiple_of, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose, **kwargs)