Instructions to use gayanin/ec-biogpt-noised-pubmed-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gayanin/ec-biogpt-noised-pubmed-v4 with Transformers:

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

pipe = pipeline("text-generation", model="gayanin/ec-biogpt-noised-pubmed-v4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gayanin/ec-biogpt-noised-pubmed-v4")
model = AutoModelForCausalLM.from_pretrained("gayanin/ec-biogpt-noised-pubmed-v4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gayanin/ec-biogpt-noised-pubmed-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gayanin/ec-biogpt-noised-pubmed-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gayanin/ec-biogpt-noised-pubmed-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gayanin/ec-biogpt-noised-pubmed-v4

SGLang

How to use gayanin/ec-biogpt-noised-pubmed-v4 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 "gayanin/ec-biogpt-noised-pubmed-v4" \
    --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": "gayanin/ec-biogpt-noised-pubmed-v4",
		"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 "gayanin/ec-biogpt-noised-pubmed-v4" \
        --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": "gayanin/ec-biogpt-noised-pubmed-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gayanin/ec-biogpt-noised-pubmed-v4 with Docker Model Runner:
```
docker model run hf.co/gayanin/ec-biogpt-noised-pubmed-v4
```

gayanin commited on Apr 13, 2023

Commit

bc9f446

1 Parent(s): a279f77

update model card README.md

Browse files

Files changed (1) hide show

README.md +103 -0

README.md ADDED Viewed

	@@ -0,0 +1,103 @@

+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: ec-biogpt-noised-pubmed-v4
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# ec-biogpt-noised-pubmed-v4
+This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8204
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+### Training results
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.7942        | 0.11  | 500   | 1.8358          |
+| 1.9793        | 0.21  | 1000  | 1.8000          |
+| 1.9244        | 0.32  | 1500  | 1.7763          |
+| 1.8871        | 0.43  | 2000  | 1.7623          |
+| 1.6525        | 0.54  | 2500  | 1.7511          |
+| 1.6871        | 0.64  | 3000  | 1.7401          |
+| 1.5771        | 0.75  | 3500  | 1.7315          |
+| 1.732         | 0.86  | 4000  | 1.7278          |
+| 1.9909        | 0.96  | 4500  | 1.7196          |
+| 1.5173        | 1.07  | 5000  | 1.7204          |
+| 1.6015        | 1.18  | 5500  | 1.7206          |
+| 1.6817        | 1.28  | 6000  | 1.7183          |
+| 1.6475        | 1.39  | 6500  | 1.7161          |
+| 1.7425        | 1.5   | 7000  | 1.7114          |
+| 1.4702        | 1.61  | 7500  | 1.7067          |
+| 1.5635        | 1.71  | 8000  | 1.7078          |
+| 1.574         | 1.82  | 8500  | 1.7020          |
+| 1.6691        | 1.93  | 9000  | 1.6985          |
+| 1.4796        | 2.03  | 9500  | 1.7339          |
+| 1.472         | 2.14  | 10000 | 1.7354          |
+| 1.4476        | 2.25  | 10500 | 1.7331          |
+| 1.4402        | 2.35  | 11000 | 1.7327          |
+| 1.5988        | 2.46  | 11500 | 1.7328          |
+| 1.3682        | 2.57  | 12000 | 1.7299          |
+| 1.4988        | 2.68  | 12500 | 1.7281          |
+| 1.4514        | 2.78  | 13000 | 1.7257          |
+| 1.6356        | 2.89  | 13500 | 1.7264          |
+| 1.6653        | 3.0   | 14000 | 1.7240          |
+| 1.2013        | 3.1   | 14500 | 1.7782          |
+| 1.2864        | 3.21  | 15000 | 1.7770          |
+| 1.4638        | 3.32  | 15500 | 1.7817          |
+| 1.2501        | 3.43  | 16000 | 1.7787          |
+| 1.4613        | 3.53  | 16500 | 1.7791          |
+| 1.1816        | 3.64  | 17000 | 1.7767          |
+| 1.1841        | 3.75  | 17500 | 1.7786          |
+| 1.2382        | 3.85  | 18000 | 1.7743          |
+| 1.2868        | 3.96  | 18500 | 1.7749          |
+| 1.2074        | 4.07  | 19000 | 1.8167          |
+| 1.1657        | 4.17  | 19500 | 1.8224          |
+| 1.1851        | 4.28  | 20000 | 1.8197          |
+| 1.1141        | 4.39  | 20500 | 1.8225          |
+| 1.0628        | 4.5   | 21000 | 1.8202          |
+| 1.0946        | 4.6   | 21500 | 1.8209          |
+| 1.037         | 4.71  | 22000 | 1.8201          |
+| 1.1277        | 4.82  | 22500 | 1.8206          |
+| 1.2766        | 4.92  | 23000 | 1.8204          |
+### Framework versions
+- Transformers 4.27.4
+- Pytorch 2.0.0+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3