Instructions to use entropy/roberta_zinc_decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use entropy/roberta_zinc_decoder with Transformers:

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

pipe = pipeline("text-generation", model="entropy/roberta_zinc_decoder", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("entropy/roberta_zinc_decoder", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("entropy/roberta_zinc_decoder", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use entropy/roberta_zinc_decoder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/entropy/roberta_zinc_decoder

SGLang

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

Docker Model Runner
How to use entropy/roberta_zinc_decoder with Docker Model Runner:
```
docker model run hf.co/entropy/roberta_zinc_decoder
```

entropy commited on Sep 28, 2023

Commit

20d0936

1 Parent(s): 963134f

Update train_script.py

Browse files

Added loading pretrained model

Files changed (1) hide show

train_script.py +7 -2

train_script.py CHANGED Viewed

@@ -4,7 +4,7 @@ import os
 import torch
 import torch.nn as nn
-from transformers import GPT2TokenizerFast, GPT2LMHeadModel
 from transformers import DataCollatorWithPadding, GPT2Config, DataCollatorForLanguageModeling
 from transformers import Trainer, TrainingArguments, RobertaTokenizerFast
@@ -58,7 +58,7 @@ dataset = dataset.with_format("torch")
 tokenizer = RobertaTokenizerFast.from_pretrained(ENCODER_MODEL_NAME, max_len=TOKENIZER_MAX_LEN)
 collator = DataCollatorForLanguageModeling(tokenizer, mlm=False)
 config = GPT2Config(
     vocab_size=len(tokenizer),
     n_positions=TOKENIZER_MAX_LEN,
@@ -71,6 +71,11 @@ config = GPT2Config(
 model = ConditionalGPT2LMHeadModel(config)
 # change trainer args as needed
 args = TrainingArguments(
     output_dir=TRAINER_SAVE_DIR,

 import torch
 import torch.nn as nn
+from transformers import GPT2TokenizerFast, GPT2LMHeadModel, AutoModelForCausalLM
 from transformers import DataCollatorWithPadding, GPT2Config, DataCollatorForLanguageModeling
 from transformers import Trainer, TrainingArguments, RobertaTokenizerFast
 tokenizer = RobertaTokenizerFast.from_pretrained(ENCODER_MODEL_NAME, max_len=TOKENIZER_MAX_LEN)
 collator = DataCollatorForLanguageModeling(tokenizer, mlm=False)
+# train from scratch
 config = GPT2Config(
     vocab_size=len(tokenizer),
     n_positions=TOKENIZER_MAX_LEN,
 model = ConditionalGPT2LMHeadModel(config)
+# alternatively, load a pre-trained model
+# commit_hash = '0ba58478f467056fe33003d7d91644ecede695a7'
+# model = AutoModelForCausalLM.from_pretrained("entropy/roberta_zinc_decoder",
+                                              # trust_remote_code=True, revision=commit_hash)
 # change trainer args as needed
 args = TrainingArguments(
     output_dir=TRAINER_SAVE_DIR,