Instructions to use ML-Projects-Kiel/tweetyface with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ML-Projects-Kiel/tweetyface with Transformers:

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

pipe = pipeline("text-generation", model="ML-Projects-Kiel/tweetyface")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ML-Projects-Kiel/tweetyface")
model = AutoModelForMultimodalLM.from_pretrained("ML-Projects-Kiel/tweetyface")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ML-Projects-Kiel/tweetyface with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ML-Projects-Kiel/tweetyface

SGLang

How to use ML-Projects-Kiel/tweetyface 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 "ML-Projects-Kiel/tweetyface" \
    --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": "ML-Projects-Kiel/tweetyface",
		"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 "ML-Projects-Kiel/tweetyface" \
        --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": "ML-Projects-Kiel/tweetyface",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ML-Projects-Kiel/tweetyface with Docker Model Runner:
```
docker model run hf.co/ML-Projects-Kiel/tweetyface
```

JaNoNi commited on Dec 3, 2022

Commit

8d779d1

1 Parent(s): b36eb34

Upload model

Browse files

Files changed (2) hide show

config.json +2 -0
pytorch_model.bin +1 -1

config.json CHANGED Viewed

@@ -6,10 +6,12 @@
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,

   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
+  "do_sample": true,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
+  "max_length": 50,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0860ee60c5738423d3b9229f4faa628274d1dcc2e33617a12c9e2f52e458e21e
 size 510396521

 version https://git-lfs.github.com/spec/v1
+oid sha256:7ccc885426f0346b9fec80a25ef24586cf7a89bab1e59887a4bac93044bf18f2
 size 510396521