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

Libraries

How to use huggingtweets/netflix with Transformers:

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

pipe = pipeline("text-generation", model="huggingtweets/netflix")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huggingtweets/netflix")
model = AutoModelForCausalLM.from_pretrained("huggingtweets/netflix", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/netflix with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/netflix

SGLang

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

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

boris commited on Jun 21, 2021

Commit

782d09a

1 Parent(s): eab59eb

New model from https://wandb.ai/wandb/huggingtweets/runs/3kzkaxu7

Browse files

Files changed (4) hide show

README.md +8 -8
config.json +1 -1
pytorch_model.bin +2 -2
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/netflix/1623841490479/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -42,20 +42,20 @@ The model was trained on tweets from Netflix.
 | Data | Netflix |
 | --- | --- |
-| Tweets downloaded | 3210 |
-| Retweets | 1563 |
-| Short tweets | 250 |
-| Tweets kept | 1397 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2t67smx9/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @netflix's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1wbg2794) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1wbg2794/artifacts) is logged and versioned.
 ## How to use

 ---
 language: en
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
 | Data | Netflix |
 | --- | --- |
+| Tweets downloaded | 3212 |
+| Retweets | 1562 |
+| Short tweets | 249 |
+| Tweets kept | 1401 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2bvoflgf/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @netflix's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3kzkaxu7) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3kzkaxu7/artifacts) is logged and versioned.
 ## How to use

config.json CHANGED Viewed

@@ -35,7 +35,7 @@
       "top_p": 0.95
     }
   },
-  "transformers_version": "4.6.1",
   "use_cache": true,
   "vocab_size": 50257
 }

       "top_p": 0.95
     }
   },
+  "transformers_version": "4.7.0",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab27083a23308ced66538c08d32584dd9e4c9cd2433637063d58b5ab1fdbb29
-size 510408315

 version https://git-lfs.github.com/spec/v1
+oid sha256:52700f54c1a9032fe739d5226f8f7c1e0ed851518e61cb796d39d79e005e7bd0
+size 510403817

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ceecc17efd2ba03d3e5d753e017de6e1b76aba893ac782f5e9f8dad6b8ce48
-size 2415

 version https://git-lfs.github.com/spec/v1
+oid sha256:c112f7b3a4ff1e2a4d9eedc643bb68003d4df66e24e4ad720980a05a84591a03
+size 2479