Instructions to use huggingtweets/witheredstrings with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingtweets/witheredstrings with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huggingtweets/witheredstrings")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huggingtweets/witheredstrings") model = AutoModelForCausalLM.from_pretrained("huggingtweets/witheredstrings") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use huggingtweets/witheredstrings with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huggingtweets/witheredstrings" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huggingtweets/witheredstrings", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huggingtweets/witheredstrings
- SGLang
How to use huggingtweets/witheredstrings 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/witheredstrings" \ --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/witheredstrings", "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/witheredstrings" \ --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/witheredstrings", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huggingtweets/witheredstrings with Docker Model Runner:
docker model run hf.co/huggingtweets/witheredstrings
New model from https://wandb.ai/wandb/huggingtweets/runs/1wwm26hx
Browse files- README.md +12 -12
- config.json +1 -1
- pytorch_model.bin +1 -1
- 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:
|
|
@@ -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('')">
|
|
@@ -20,7 +20,7 @@ widget:
|
|
| 20 |
</div>
|
| 21 |
</div>
|
| 22 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
|
| 23 |
-
<div style="text-align: center; font-size: 16px; font-weight: 800">
|
| 24 |
<div style="text-align: center; font-size: 14px;">@witheredstrings</div>
|
| 25 |
</div>
|
| 26 |
|
|
@@ -38,24 +38,24 @@ To understand how the model was developed, check the [W&B report](https://wandb.
|
|
| 38 |
|
| 39 |
## Training data
|
| 40 |
|
| 41 |
-
The model was trained on tweets from
|
| 42 |
|
| 43 |
-
| Data |
|
| 44 |
| --- | --- |
|
| 45 |
-
| Tweets downloaded |
|
| 46 |
-
| Retweets |
|
| 47 |
-
| Short tweets |
|
| 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 @witheredstrings'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 |
|
|
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
+
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
|
| 4 |
tags:
|
| 5 |
- huggingtweets
|
| 6 |
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/1458448689568092161/qliCU5-F_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('')">
|
|
|
|
| 20 |
</div>
|
| 21 |
</div>
|
| 22 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
|
| 23 |
+
<div style="text-align: center; font-size: 16px; font-weight: 800">VacuumF</div>
|
| 24 |
<div style="text-align: center; font-size: 14px;">@witheredstrings</div>
|
| 25 |
</div>
|
| 26 |
|
|
|
|
| 38 |
|
| 39 |
## Training data
|
| 40 |
|
| 41 |
+
The model was trained on tweets from VacuumF.
|
| 42 |
|
| 43 |
+
| Data | VacuumF |
|
| 44 |
| --- | --- |
|
| 45 |
+
| Tweets downloaded | 311 |
|
| 46 |
+
| Retweets | 10 |
|
| 47 |
+
| Short tweets | 15 |
|
| 48 |
+
| Tweets kept | 286 |
|
| 49 |
|
| 50 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3jei3sh4/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 @witheredstrings's tweets.
|
| 55 |
|
| 56 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1wwm26hx) for full transparency and reproducibility.
|
| 57 |
|
| 58 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1wwm26hx/artifacts) is logged and versioned.
|
| 59 |
|
| 60 |
## How to use
|
| 61 |
|
config.json
CHANGED
|
@@ -37,7 +37,7 @@
|
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"torch_dtype": "float32",
|
| 40 |
-
"transformers_version": "4.12.
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 50257
|
| 43 |
}
|
|
|
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.12.3",
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 50257
|
| 43 |
}
|
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:d43a2f32ff5900400a151c73c8f665c8d94f8da601a44b9482f7271dba84d4c4
|
| 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 2863
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f750c3af5f767b46380719fcc1ec922c956a5ac0c8e68ccfa13abb9974350cf5
|
| 3 |
size 2863
|