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

Libraries

How to use huggingtweets/tommyboytwt with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/tommyboytwt with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/tommyboytwt

SGLang

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

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

boris commited on Apr 5, 2023

Commit

233d46b

1 Parent(s): b2ba4d5

New model from https://wandb.ai/wandb/huggingtweets/runs/orhs8gfb

Browse files

Files changed (5) hide show

README.md +7 -7
merges.txt +1 -1
pytorch_model.bin +1 -1
tokenizer.json +1 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -42,20 +42,20 @@ The model was trained on tweets from tommy he/him🤙.
 | Data | tommy he/him🤙 |
 | --- | --- |
-| Tweets downloaded | 3243 |
-| Retweets | 152 |
-| Short tweets | 771 |
-| Tweets kept | 2320 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/57i09oih/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 @tommyboytwt's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3feqvmrm) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3feqvmrm/artifacts) is logged and versioned.
 ## How to use

 | Data | tommy he/him🤙 |
 | --- | --- |
+| Tweets downloaded | 3242 |
+| Retweets | 154 |
+| Short tweets | 770 |
+| Tweets kept | 2318 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/0z94othz/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 @tommyboytwt's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/orhs8gfb) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/orhs8gfb/artifacts) is logged and versioned.
 ## How to use

merges.txt CHANGED Viewed

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ t
 Ġ a
 h e

+#version: 0.2
 Ġ t
 Ġ a
 h e

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861c73e6cbfe2d9a7a499db499b94c63b224a0e60f3bf2b01be52efeecda8a8e
 size 510398013

 version https://git-lfs.github.com/spec/v1
+oid sha256:b8dd5f72e48f534c4958468a055e1a413c068c62359d7dd09d93b1e9f427b32c
 size 510398013

tokenizer.json CHANGED Viewed

@@ -39,6 +39,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "vocab": {
       "!": 0,
       "\"": 1,

     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "!": 0,
       "\"": 1,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a61b627998a5329145c8cecbd72fb2f9964a3f10a28bd1d2e08198cfe4d54e36
 size 3579

 version https://git-lfs.github.com/spec/v1
+oid sha256:b93363e62d4e8790f51c2dd26e31cfadeb8f71be7ee7329a05906bb54f398a1a
 size 3579