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

Libraries

How to use huggingtweets/plasma_node with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huggingtweets/plasma_node")
model = AutoModelForCausalLM.from_pretrained("huggingtweets/plasma_node")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huggingtweets/plasma_node with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/plasma_node

SGLang

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

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

boris commited on Jun 9, 2022

Commit

ba38c77

1 Parent(s): 1ce7a1b

New model from https://wandb.ai/wandb/huggingtweets/runs/s5kag6o2

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: http://www.huggingtweets.com/plasma_node/1650847235027/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -42,20 +42,20 @@ The model was trained on tweets from Plasmanode.
 | Data | Plasmanode |
 | --- | --- |
-| Tweets downloaded | 3240 |
-| Retweets | 493 |
-| Short tweets | 394 |
-| Tweets kept | 2353 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2tpacq1y/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 @plasma_node's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1dmqss32) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1dmqss32/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 | Plasmanode |
 | --- | --- |
+| Tweets downloaded | 3242 |
+| Retweets | 573 |
+| Short tweets | 339 |
+| Tweets kept | 2330 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/21cfw258/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 @plasma_node's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/s5kag6o2) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/s5kag6o2/artifacts) is logged and versioned.
 ## How to use

config.json CHANGED Viewed

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.18.0",
   "use_cache": true,
   "vocab_size": 50257
 }

     }
   },
   "torch_dtype": "float32",
+  "transformers_version": "4.19.2",
   "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:d9fb1a962af369b47adcb9d150a5fd0985fc4e5ad8e4caf4a521eb689b5f5c54
 size 510396521

 version https://git-lfs.github.com/spec/v1
+oid sha256:f2dd4511d917a64d4876a0363ea871fff0ad46f7043b78056bcf51ac4c0ba58a
 size 510396521

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef4addf4f52d7c6648f4717aa31debed128c5e0a06a6e63b178925725c33a4c
-size 3055

 version https://git-lfs.github.com/spec/v1
+oid sha256:63690fe1fc33527de9c805a6935194f4cc32167e462a101f8dbb53e6048844c9
+size 3183