Instructions to use Xibanya/DS9Bot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Xibanya/DS9Bot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Xibanya/DS9Bot")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Xibanya/DS9Bot") model = AutoModelForCausalLM.from_pretrained("Xibanya/DS9Bot") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Xibanya/DS9Bot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Xibanya/DS9Bot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Xibanya/DS9Bot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Xibanya/DS9Bot
- SGLang
How to use Xibanya/DS9Bot 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 "Xibanya/DS9Bot" \ --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": "Xibanya/DS9Bot", "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 "Xibanya/DS9Bot" \ --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": "Xibanya/DS9Bot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Xibanya/DS9Bot with Docker Model Runner:
docker model run hf.co/Xibanya/DS9Bot
Upload eval_results.json
Browse files- eval_results.json +7 -7
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 3.
|
| 4 |
-
"eval_runtime": 0.
|
| 5 |
-
"eval_samples":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"perplexity":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 90.0,
|
| 3 |
+
"eval_loss": 3.407930374145508,
|
| 4 |
+
"eval_runtime": 0.938,
|
| 5 |
+
"eval_samples": 34,
|
| 6 |
+
"eval_samples_per_second": 36.246,
|
| 7 |
+
"eval_steps_per_second": 36.246,
|
| 8 |
+
"perplexity": 30.202671301029685
|
| 9 |
}
|