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

Libraries

How to use huggingtweets/chamath with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/chamath with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/chamath

SGLang

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

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

boris commited on Apr 7, 2021

Commit

52dbcb0

1 Parent(s): df67c88

New model from https://wandb.ai/wandb/huggingtweets/runs/2heorao8

Browse files

Files changed (3) hide show

README.md +3 -3
pytorch_model.bin +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -37,15 +37,15 @@ The model was trained on [@chamath's tweets](https://twitter.com/chamath).
 | Short tweets | 737 |
 | Tweets kept | 2363 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2oq6ihz2/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 @chamath's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1exf7mug) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1exf7mug/artifacts) is logged and versioned.
 ## How to use

 | Short tweets | 737 |
 | Tweets kept | 2363 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/8zc0u0jp/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 @chamath's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2heorao8) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2heorao8/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 sha256:3e4652bf03bc4cd3bb3adb0df2596a70412f2b69ed8e8bfa5680b5b31d629916
 size 510408315

 version https://git-lfs.github.com/spec/v1
+oid sha256:a686d7f0b5a5e18e2282bacd35d8cd45f1d57d799344d8cb546806e7d716ae32
 size 510408315

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f15ffde81cc20955c483284e62d32d10cb5480dbedadc9f249c9ec55c7f361a8
 size 2351

 version https://git-lfs.github.com/spec/v1
+oid sha256:c1aa0252e690062851cf68804e4e4fd80258112e08697fd9740af2ef149cd441
 size 2351