Instructions to use distributed/optimized-gpt2-250m-v0.1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use distributed/optimized-gpt2-250m-v0.1.2 with Transformers:

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

pipe = pipeline("text-generation", model="distributed/optimized-gpt2-250m-v0.1.2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("distributed/optimized-gpt2-250m-v0.1.2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use distributed/optimized-gpt2-250m-v0.1.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "distributed/optimized-gpt2-250m-v0.1.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "distributed/optimized-gpt2-250m-v0.1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/distributed/optimized-gpt2-250m-v0.1.2

SGLang

How to use distributed/optimized-gpt2-250m-v0.1.2 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 "distributed/optimized-gpt2-250m-v0.1.2" \
    --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": "distributed/optimized-gpt2-250m-v0.1.2",
		"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 "distributed/optimized-gpt2-250m-v0.1.2" \
        --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": "distributed/optimized-gpt2-250m-v0.1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use distributed/optimized-gpt2-250m-v0.1.2 with Docker Model Runner:
```
docker model run hf.co/distributed/optimized-gpt2-250m-v0.1.2
```

Ignore padding in loss method

by jonna32 - opened Sep 24, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

modeling_gpt_optimized.py +1 -1

modeling_gpt_optimized.py CHANGED Viewed

@@ -195,5 +195,5 @@ class GPTOptim(GPT2PreTrainedModel):
         logits = self.model.lm_head(x) # (B, T, vocab_size)
         loss = None
         if labels is not None:
-            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), labels.view(-1))
         return logits, loss

         logits = self.model.lm_head(x) # (B, T, vocab_size)
         loss = None
         if labels is not None:
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), labels.view(-1), ignore_index=config.eos_token_id)
         return logits, loss