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

Libraries

How to use huggingtweets/codeinecucumber with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/codeinecucumber with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/codeinecucumber

SGLang

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

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

boris commited on Oct 31, 2022

Commit

4b4b38e

1 Parent(s): 1a17d1a

New model from https://wandb.ai/wandb/huggingtweets/runs/kltnq0t8

Browse files

Files changed (3) hide show

README.md +5 -5
pytorch_model.bin +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -43,19 +43,19 @@ The model was trained on tweets from Gutted.
 | Data | Gutted |
 | --- | --- |
 | Tweets downloaded | 1559 |
-| Retweets | 233 |
 | Short tweets | 298 |
-| Tweets kept | 1028 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2d8ccmd1/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 @codeinecucumber's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/38lj19ie) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/38lj19ie/artifacts) is logged and versioned.
 ## How to use

 | Data | Gutted |
 | --- | --- |
 | Tweets downloaded | 1559 |
+| Retweets | 232 |
 | Short tweets | 298 |
+| Tweets kept | 1029 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/14n4xgbm/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 @codeinecucumber's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/kltnq0t8) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/kltnq0t8/artifacts) is logged and versioned.
 ## How to use

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ecdaedbc69c396827c624dcc1a217fe2eeac8e8fb280e64e0cf2d1bfa22c19
 size 510396521

 version https://git-lfs.github.com/spec/v1
+oid sha256:1fd049c8a86f32dc8ad9510e06797a6cc894ba73ecf48b4f5d04ab3717f6d46f
 size 510396521

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b1908fd10bf5c944be60b26a1a3c4eb18f1c88b94af70c6a901e823022a839
 size 3375

 version https://git-lfs.github.com/spec/v1
+oid sha256:b5d332991cc53b5d7d0273f059aca6856d3b0b937f81fac76e7a89fccfff5200
 size 3375