Text Generation
Transformers
PyTorch
Safetensors
English
GPT2LMHeadModel
text-generation-inference
question-answering
casual-LM
Instructions to use Wonder-Griffin/TraXL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Wonder-Griffin/TraXL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Wonder-Griffin/TraXL")# Load model directly from transformers import TraXL model = TraXL.from_pretrained("Wonder-Griffin/TraXL", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Wonder-Griffin/TraXL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Wonder-Griffin/TraXL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Wonder-Griffin/TraXL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Wonder-Griffin/TraXL
- SGLang
How to use Wonder-Griffin/TraXL 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 "Wonder-Griffin/TraXL" \ --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": "Wonder-Griffin/TraXL", "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 "Wonder-Griffin/TraXL" \ --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": "Wonder-Griffin/TraXL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Wonder-Griffin/TraXL with Docker Model Runner:
docker model run hf.co/Wonder-Griffin/TraXL
Model save
Browse files- generation_config.json +12 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"diversity_penalty": 0.5,
|
| 3 |
+
"early_stopping": true,
|
| 4 |
+
"max_length": 512,
|
| 5 |
+
"no_repeat_ngram_size": 3,
|
| 6 |
+
"num_beams": 5,
|
| 7 |
+
"repetition_penalty": 1.2,
|
| 8 |
+
"task_type": "general",
|
| 9 |
+
"temperature": null,
|
| 10 |
+
"top_p": null,
|
| 11 |
+
"transformers_version": "4.44.2"
|
| 12 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 372079412
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:583650d3e4a12f39fb29f5684633b4d174713b750487c7efffd46ff2ec7f5939
|
| 3 |
size 372079412
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cb74ae2e18105c801d85c73c468f2e7377f2b71de7f54cf1b023b761ca08fb8
|
| 3 |
size 5176
|