Instructions to use akaigraham/kaigpt-123 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use akaigraham/kaigpt-123 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="akaigraham/kaigpt-123")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("akaigraham/kaigpt-123") model = AutoModelForCausalLM.from_pretrained("akaigraham/kaigpt-123") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use akaigraham/kaigpt-123 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "akaigraham/kaigpt-123" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "akaigraham/kaigpt-123", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/akaigraham/kaigpt-123
- SGLang
How to use akaigraham/kaigpt-123 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 "akaigraham/kaigpt-123" \ --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": "akaigraham/kaigpt-123", "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 "akaigraham/kaigpt-123" \ --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": "akaigraham/kaigpt-123", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use akaigraham/kaigpt-123 with Docker Model Runner:
docker model run hf.co/akaigraham/kaigpt-123
Commit ·
16c80ff
1
Parent(s): ba26d08
Training in progress, epoch 24
Browse files
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 327674773
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c871b109a444fb155fd14d4ce8be9dc2e5508393688adb926e49976055ff77e
|
| 3 |
size 327674773
|
runs/Aug15_00-49-00_5f504ed732b0/events.out.tfevents.1692060545.5f504ed732b0.4714.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b196c2bf14c9508f7460e7c71b892d11ecac1b0ede1ae9139058e3ad64dcdaa
|
| 3 |
+
size 40583
|