Instructions to use huggingtweets/l2k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingtweets/l2k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huggingtweets/l2k")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huggingtweets/l2k") model = AutoModelForCausalLM.from_pretrained("huggingtweets/l2k") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use huggingtweets/l2k with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huggingtweets/l2k" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huggingtweets/l2k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huggingtweets/l2k
- SGLang
How to use huggingtweets/l2k 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/l2k" \ --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/l2k", "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/l2k" \ --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/l2k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huggingtweets/l2k with Docker Model Runner:
docker model run hf.co/huggingtweets/l2k
Update config.json
Browse files- config.json +2 -1
config.json
CHANGED
|
@@ -13,6 +13,7 @@
|
|
| 13 |
"n_ctx": 1024,
|
| 14 |
"n_embd": 768,
|
| 15 |
"n_head": 12,
|
|
|
|
| 16 |
"n_layer": 12,
|
| 17 |
"n_positions": 1024,
|
| 18 |
"resid_pdrop": 0.1,
|
|
@@ -26,7 +27,7 @@
|
|
| 26 |
"do_sample": true,
|
| 27 |
"max_length": 160,
|
| 28 |
"min_length": 10,
|
| 29 |
-
"
|
| 30 |
"temperature": 1.0,
|
| 31 |
"top_p": 0.95
|
| 32 |
}
|
|
|
|
| 13 |
"n_ctx": 1024,
|
| 14 |
"n_embd": 768,
|
| 15 |
"n_head": 12,
|
| 16 |
+
"n_inner": null,
|
| 17 |
"n_layer": 12,
|
| 18 |
"n_positions": 1024,
|
| 19 |
"resid_pdrop": 0.1,
|
|
|
|
| 27 |
"do_sample": true,
|
| 28 |
"max_length": 160,
|
| 29 |
"min_length": 10,
|
| 30 |
+
"prefix": "<|endoftext|>",
|
| 31 |
"temperature": 1.0,
|
| 32 |
"top_p": 0.95
|
| 33 |
}
|