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

Libraries

How to use huggingtweets/offalgirl with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/offalgirl with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/offalgirl

SGLang

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

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

boris commited on Apr 11, 2021

Commit

6a4deef

1 Parent(s): 758823c

New model from https://wandb.ai/wandb/huggingtweets/runs/o3wl0iel

Browse files

Files changed (4) hide show

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

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/offalgirl/1616672489330/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -32,20 +32,20 @@ The model was trained on [@offalgirl's tweets](https://twitter.com/offalgirl).
 | Data | Quantity |
 | --- | --- |
-| Tweets downloaded | 1529 |
-| Retweets | 222 |
-| Short tweets | 131 |
-| Tweets kept | 1176 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1o7lokya/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 @offalgirl's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/35u9f83g) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/35u9f83g/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 | Quantity |
 | --- | --- |
+| Tweets downloaded | 1574 |
+| Retweets | 230 |
+| Short tweets | 132 |
+| Tweets kept | 1212 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/17p3r18f/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 @offalgirl's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/o3wl0iel) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/o3wl0iel/artifacts) is logged and versioned.
 ## How to use

config.json CHANGED Viewed

@@ -34,7 +34,7 @@
       "top_p": 0.95
     }
   },
-  "transformers_version": "4.4.2",
   "use_cache": true,
   "vocab_size": 50257
 }

       "top_p": 0.95
     }
   },
+  "transformers_version": "4.5.0",
   "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:a41d431ecb2248f3ab1945fbf476305c1213121e0947ae5420f7084807a10b19
 size 510408315

 version https://git-lfs.github.com/spec/v1
+oid sha256:ff4b3d29b2694aa102dd96d18cb62e60aa36ae2ce81cedb8171eeffe1c955669
 size 510408315

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecdc9a387da89385b3a4b34a93f354450907dfff0fb4cd455a20c416e453f844
-size 2287

 version https://git-lfs.github.com/spec/v1
+oid sha256:a4f29fdeb4e095cebcf68996a00fbec9fa1adf8a2400ad4ad2297f01fc9d1ce8
+size 2351