Instructions to use huggingtweets/nvidia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingtweets/nvidia with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huggingtweets/nvidia")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huggingtweets/nvidia") model = AutoModelForCausalLM.from_pretrained("huggingtweets/nvidia") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use huggingtweets/nvidia with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huggingtweets/nvidia" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huggingtweets/nvidia", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huggingtweets/nvidia
- SGLang
How to use huggingtweets/nvidia 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/nvidia" \ --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/nvidia", "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/nvidia" \ --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/nvidia", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huggingtweets/nvidia with Docker Model Runner:
docker model run hf.co/huggingtweets/nvidia
Update README.md
Browse files
README.md
CHANGED
|
@@ -51,11 +51,11 @@ The model was trained on [@nvidia's tweets](https://twitter.com/nvidia).
|
|
| 51 |
<tbody style='border-width:0'>
|
| 52 |
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
|
| 53 |
<td style='border-width:0'>Tweets downloaded</td>
|
| 54 |
-
<td style='border-width:0'>
|
| 55 |
</tr>
|
| 56 |
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
|
| 57 |
<td style='border-width:0'>Retweets</td>
|
| 58 |
-
<td style='border-width:0'>
|
| 59 |
</tr>
|
| 60 |
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
|
| 61 |
<td style='border-width:0'>Short tweets</td>
|
|
@@ -63,20 +63,20 @@ The model was trained on [@nvidia's tweets](https://twitter.com/nvidia).
|
|
| 63 |
</tr>
|
| 64 |
<tr style='border-width:0'>
|
| 65 |
<td style='border-width:0'>Tweets kept</td>
|
| 66 |
-
<td style='border-width:0'>
|
| 67 |
</tr>
|
| 68 |
</tbody>
|
| 69 |
</table>
|
| 70 |
|
| 71 |
-
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/
|
| 72 |
|
| 73 |
## Training procedure
|
| 74 |
|
| 75 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @nvidia's tweets.
|
| 76 |
|
| 77 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/
|
| 78 |
|
| 79 |
-
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/
|
| 80 |
|
| 81 |
## Intended uses & limitations
|
| 82 |
|
|
@@ -110,4 +110,4 @@ For more details, visit the project repository.
|
|
| 110 |
|
| 111 |
[](https://github.com/borisdayma/huggingtweets)
|
| 112 |
|
| 113 |
-
<!--- random size file
|
|
|
|
| 51 |
<tbody style='border-width:0'>
|
| 52 |
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
|
| 53 |
<td style='border-width:0'>Tweets downloaded</td>
|
| 54 |
+
<td style='border-width:0'>3222</td>
|
| 55 |
</tr>
|
| 56 |
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
|
| 57 |
<td style='border-width:0'>Retweets</td>
|
| 58 |
+
<td style='border-width:0'>1876</td>
|
| 59 |
</tr>
|
| 60 |
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
|
| 61 |
<td style='border-width:0'>Short tweets</td>
|
|
|
|
| 63 |
</tr>
|
| 64 |
<tr style='border-width:0'>
|
| 65 |
<td style='border-width:0'>Tweets kept</td>
|
| 66 |
+
<td style='border-width:0'>1328</td>
|
| 67 |
</tr>
|
| 68 |
</tbody>
|
| 69 |
</table>
|
| 70 |
|
| 71 |
+
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/2ttmuio7/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 72 |
|
| 73 |
## Training procedure
|
| 74 |
|
| 75 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @nvidia's tweets.
|
| 76 |
|
| 77 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/3o1omu9g) for full transparency and reproducibility.
|
| 78 |
|
| 79 |
+
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/3o1omu9g/artifacts) is logged and versioned.
|
| 80 |
|
| 81 |
## Intended uses & limitations
|
| 82 |
|
|
|
|
| 110 |
|
| 111 |
[](https://github.com/borisdayma/huggingtweets)
|
| 112 |
|
| 113 |
+
<!--- random size file -->
|