Text Generation
Transformers
Safetensors
gpt2
biology
plasmid
dna
synthetic-biology
text-generation-inference
Instructions to use UCL-CSSB/PlasmidGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UCL-CSSB/PlasmidGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="UCL-CSSB/PlasmidGPT")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("UCL-CSSB/PlasmidGPT") model = AutoModelForCausalLM.from_pretrained("UCL-CSSB/PlasmidGPT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use UCL-CSSB/PlasmidGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "UCL-CSSB/PlasmidGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "UCL-CSSB/PlasmidGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/UCL-CSSB/PlasmidGPT
- SGLang
How to use UCL-CSSB/PlasmidGPT 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 "UCL-CSSB/PlasmidGPT" \ --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": "UCL-CSSB/PlasmidGPT", "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 "UCL-CSSB/PlasmidGPT" \ --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": "UCL-CSSB/PlasmidGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use UCL-CSSB/PlasmidGPT with Docker Model Runner:
docker model run hf.co/UCL-CSSB/PlasmidGPT
Set [SEP] as EOS token: update eos_token, eos_token_id, and generation config
Browse files- config.json +1 -1
- generation_config.json +1 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -6,7 +6,7 @@
|
|
| 6 |
"attn_pdrop": 0.1,
|
| 7 |
"bos_token_id": 50256,
|
| 8 |
"embd_pdrop": 0.1,
|
| 9 |
-
"eos_token_id":
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"layer_norm_epsilon": 1e-05,
|
| 12 |
"model_type": "gpt2",
|
|
|
|
| 6 |
"attn_pdrop": 0.1,
|
| 7 |
"bos_token_id": 50256,
|
| 8 |
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"layer_norm_epsilon": 1e-05,
|
| 12 |
"model_type": "gpt2",
|
generation_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
-
"eos_token_id":
|
| 5 |
"pad_token_id": 3,
|
| 6 |
"transformers_version": "4.55.4"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 3,
|
| 6 |
"transformers_version": "4.55.4"
|
| 7 |
}
|
special_tokens_map.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "[SEP]",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -59,7 +59,7 @@
|
|
| 59 |
},
|
| 60 |
"bos_token": "<s>",
|
| 61 |
"clean_up_tokenization_spaces": false,
|
| 62 |
-
"eos_token": "
|
| 63 |
"extra_special_tokens": {},
|
| 64 |
"model_max_length": 1000000000000000019884624838656,
|
| 65 |
"pad_token": "[PAD]",
|
|
|
|
| 59 |
},
|
| 60 |
"bos_token": "<s>",
|
| 61 |
"clean_up_tokenization_spaces": false,
|
| 62 |
+
"eos_token": "[SEP]",
|
| 63 |
"extra_special_tokens": {},
|
| 64 |
"model_max_length": 1000000000000000019884624838656,
|
| 65 |
"pad_token": "[PAD]",
|