Instructions to use huggingtweets/jontthomas with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingtweets/jontthomas with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huggingtweets/jontthomas")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huggingtweets/jontthomas") model = AutoModelForCausalLM.from_pretrained("huggingtweets/jontthomas") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use huggingtweets/jontthomas with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huggingtweets/jontthomas" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huggingtweets/jontthomas", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huggingtweets/jontthomas
- SGLang
How to use huggingtweets/jontthomas 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/jontthomas" \ --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/jontthomas", "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/jontthomas" \ --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/jontthomas", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huggingtweets/jontthomas with Docker Model Runner:
docker model run hf.co/huggingtweets/jontthomas
New model from https://wandb.ai/wandb/huggingtweets/runs/2bzdo7d6
Browse files- README.md +6 -6
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -10,7 +10,7 @@ widget:
|
|
| 10 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
| 11 |
<div class="flex">
|
| 12 |
<div
|
| 13 |
-
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/
|
| 14 |
</div>
|
| 15 |
<div
|
| 16 |
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
|
|
@@ -42,20 +42,20 @@ The model was trained on tweets from Johnathon Taylor "JTT" Thomas.
|
|
| 42 |
|
| 43 |
| Data | Johnathon Taylor "JTT" Thomas |
|
| 44 |
| --- | --- |
|
| 45 |
-
| Tweets downloaded |
|
| 46 |
| Retweets | 3 |
|
| 47 |
| Short tweets | 44 |
|
| 48 |
-
| Tweets kept |
|
| 49 |
|
| 50 |
-
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/
|
| 51 |
|
| 52 |
## Training procedure
|
| 53 |
|
| 54 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @jontthomas's tweets.
|
| 55 |
|
| 56 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/
|
| 57 |
|
| 58 |
-
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/
|
| 59 |
|
| 60 |
## How to use
|
| 61 |
|
|
|
|
| 10 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
| 11 |
<div class="flex">
|
| 12 |
<div
|
| 13 |
+
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1418758009673723909/rtsbsqKv_400x400.jpg')">
|
| 14 |
</div>
|
| 15 |
<div
|
| 16 |
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
|
|
|
|
| 42 |
|
| 43 |
| Data | Johnathon Taylor "JTT" Thomas |
|
| 44 |
| --- | --- |
|
| 45 |
+
| Tweets downloaded | 239 |
|
| 46 |
| Retweets | 3 |
|
| 47 |
| Short tweets | 44 |
|
| 48 |
+
| Tweets kept | 192 |
|
| 49 |
|
| 50 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/9haxw34n/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 51 |
|
| 52 |
## Training procedure
|
| 53 |
|
| 54 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @jontthomas's tweets.
|
| 55 |
|
| 56 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2bzdo7d6) for full transparency and reproducibility.
|
| 57 |
|
| 58 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2bzdo7d6/artifacts) is logged and versioned.
|
| 59 |
|
| 60 |
## How to use
|
| 61 |
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8178fd253639cfd6cb8171fe11aff157168dd2b2962eb129c20c6272a0b8d86
|
| 3 |
size 510403817
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2671
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0078c5bcac9b2595b7e28a1a4b1a69d2b71c23d5e6388016d51e63947cd774b7
|
| 3 |
size 2671
|