Text Generation
Transformers
Safetensors
English
kimi_linear
kimi-k3
luau
experimental-checkpoint
custom_code
Instructions to use khtsly/d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use khtsly/d with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="khtsly/d", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("khtsly/d", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("khtsly/d", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use khtsly/d with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "khtsly/d" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "khtsly/d", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/khtsly/d
- SGLang
How to use khtsly/d 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 "khtsly/d" \ --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": "khtsly/d", "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 "khtsly/d" \ --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": "khtsly/d", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use khtsly/d with Docker Model Runner:
docker model run hf.co/khtsly/d
|
Download README.md from khtsly/d: direct link, hf CLI and curl.
- Browser
- Download file 307 Bytes
-
https://huggingface.co/khtsly/d/resolve/main/README.md
- Command line
-
hf download hf://khtsly/d/README.md
-
curl -L -o README.md https://huggingface.co/khtsly/d/resolve/main/README.md
307 Bytes
metadata
language: en
library_name: transformers
tags:
- kimi-k3
- luau
- experimental-checkpoint
d
In-training periodic checkpoint (step 8500). Architecture:
Kimi K3 mini port (KimiLinearForCausalLM).
Not a finished model -- intermediate weights uploaded during training for safekeeping/diffing.