Instructions to use kepton0117/chrono-2021-ckpts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kepton0117/chrono-2021-ckpts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kepton0117/chrono-2021-ckpts")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("kepton0117/chrono-2021-ckpts", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kepton0117/chrono-2021-ckpts with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kepton0117/chrono-2021-ckpts" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kepton0117/chrono-2021-ckpts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kepton0117/chrono-2021-ckpts
- SGLang
How to use kepton0117/chrono-2021-ckpts 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 "kepton0117/chrono-2021-ckpts" \ --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": "kepton0117/chrono-2021-ckpts", "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 "kepton0117/chrono-2021-ckpts" \ --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": "kepton0117/chrono-2021-ckpts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kepton0117/chrono-2021-ckpts with Docker Model Runner:
docker model run hf.co/kepton0117/chrono-2021-ckpts
SN38 Round 12 β all CPT checkpoints
Continue-pretrain of anacoluthe89/chrono-2020 @633eb832 on kepton0117/sn38-train-2021.
On-chain pin is not this repo. UID 141 uses kepton0117/chrono-2021-sn38 (step-4000 only).
Each revision is one optimizer checkpoint (1e-3 stage, init = 1e-4 step-4000):
| Revision | Cosine vs UID 131 | Loss ~ |
|---|---|---|
step-2000 |
0.9538 (fail copy) | 2.8 |
step-4000 |
0.9294 | 2.66 |
step-6000 |
0.9144 | β |
step-8000 |
0.9080 | 2.54β2.61 |
step-10000 |
0.9061 | β |
step-12000 |
0.9055 | β |
step-14000 |
0.9055 | β |
step-15000 |
0.9055 | 2.50 |
from transformers import AutoModelForCausalLM
m = AutoModelForCausalLM.from_pretrained(
"kepton0117/chrono-2021-ckpts", revision="step-8000", trust_remote_code=False,
)