Instructions to use freakyskittle/kimi-k2.75-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use freakyskittle/kimi-k2.75-code with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="freakyskittle/kimi-k2.75-code", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModel

processor = AutoProcessor.from_pretrained("freakyskittle/kimi-k2.75-code", trust_remote_code=True)
model = AutoModel.from_pretrained("freakyskittle/kimi-k2.75-code", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use freakyskittle/kimi-k2.75-code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "freakyskittle/kimi-k2.75-code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "freakyskittle/kimi-k2.75-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/freakyskittle/kimi-k2.75-code

SGLang

How to use freakyskittle/kimi-k2.75-code 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 "freakyskittle/kimi-k2.75-code" \
    --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": "freakyskittle/kimi-k2.75-code",
		"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 "freakyskittle/kimi-k2.75-code" \
        --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": "freakyskittle/kimi-k2.75-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use freakyskittle/kimi-k2.75-code with Docker Model Runner:
```
docker model run hf.co/freakyskittle/kimi-k2.75-code
```

kimi-k2.75-code / README.md

freakyskittle

Add README.md with Modified MIT license details

f6ce165 verified 20 days ago

preview code

Raw

History Blame Contribute Delete

1.84 kB

	---
	license: other
	base_model:
	- moonshotai/Kimi-K2.7-Code
	- moonshotai/Kimi-K2.6
	tags:
	- merge
	- kimi
	- deepseek-v3
	- moe
	- safetensors
	- experimental
	library_name: transformers
	pipeline_tag: text-generation
	---

	# Kimi K2.75 Code — experimental merge

	This repository contains an experimental merged checkpoint derived from:

	- `moonshotai/Kimi-K2.7-Code`
	- `moonshotai/Kimi-K2.6`

	The merge used a custom shard-wise SLERP blend after `mergekit` could not handle the Kimi expert shape tensors.

	## Merge recipe

	- Attention tensors: `t = 0.3`
	- MLP / expert tensors: `t = 0.5`
	- Other tensors: `t = 0.4`
	- Initial merged checkpoint size before pruning: about `555G`

	## Pruning / compaction

	The uploaded safetensors are the compacted pruned checkpoint:

	- SnapPrune deep / REAP-style expert pruning
	- Prune ratio: `0.3`
	- Routed experts compacted from sparse original expert ids to dense expert ids
	- Final routed experts per MoE layer: `268`
	- Safetensors checkpoint size: about `394G`

	## License

	This checkpoint follows the Modified MIT License from Moonshot AI. See [`LICENSE`](./LICENSE).

	Commercial attribution requirement: if the Software or derivative works are used for commercial products or services with more than 100 million monthly active users, or more than 20 million US dollars (or equivalent in other currencies) in monthly revenue, you must prominently display `Kimi K2.7 Code` on the user interface of such product or service.

	## Status

	This model is not fully evaluated yet. Treat it as a research artifact.

	At upload time:

	- Merge completed successfully.
	- Pruning completed successfully.
	- Safetensors compaction completed successfully.
	- GGUF conversion / quantization / smoke testing may still be in progress.

	Use at your own risk and validate quality before production use.