Instructions to use huggingtweets/idph with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingtweets/idph with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huggingtweets/idph")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huggingtweets/idph") model = AutoModelForCausalLM.from_pretrained("huggingtweets/idph") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use huggingtweets/idph with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huggingtweets/idph" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huggingtweets/idph", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huggingtweets/idph
- SGLang
How to use huggingtweets/idph 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/idph" \ --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/idph", "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/idph" \ --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/idph", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huggingtweets/idph with Docker Model Runner:
docker model run hf.co/huggingtweets/idph
New model from https://wandb.ai/wandb/huggingtweets/runs/dkm56a09
Browse files- README.md +6 -6
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
-
thumbnail: https://
|
| 4 |
tags:
|
| 5 |
- huggingtweets
|
| 6 |
widget:
|
|
@@ -51,7 +51,7 @@ The model was trained on [@idph's tweets](https://twitter.com/idph).
|
|
| 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>
|
|
@@ -63,20 +63,20 @@ The model was trained on [@idph's tweets](https://twitter.com/idph).
|
|
| 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://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 @idph's tweets.
|
| 76 |
|
| 77 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/
|
| 78 |
|
| 79 |
-
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/
|
| 80 |
|
| 81 |
## Intended uses & limitations
|
| 82 |
|
|
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
+
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
|
| 4 |
tags:
|
| 5 |
- huggingtweets
|
| 6 |
widget:
|
|
|
|
| 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'>3199</td>
|
| 55 |
</tr>
|
| 56 |
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
|
| 57 |
<td style='border-width:0'>Retweets</td>
|
|
|
|
| 63 |
</tr>
|
| 64 |
<tr style='border-width:0'>
|
| 65 |
<td style='border-width:0'>Tweets kept</td>
|
| 66 |
+
<td style='border-width:0'>2474</td>
|
| 67 |
</tr>
|
| 68 |
</tbody>
|
| 69 |
</table>
|
| 70 |
|
| 71 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/awgsk010/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 @idph's tweets.
|
| 76 |
|
| 77 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/dkm56a09) for full transparency and reproducibility.
|
| 78 |
|
| 79 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/dkm56a09/artifacts) is logged and versioned.
|
| 80 |
|
| 81 |
## Intended uses & limitations
|
| 82 |
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f15fdc3e1b22ac894dea13e74f5e0fc42d8106a21435b9fd2c604fba861346e4
|
| 3 |
+
size 510406558
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1839
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9df2247ff9ebace8438146d16bc264890783299f9ef1a1892189a849488a9431
|
| 3 |
size 1839
|