Instructions to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16 with Transformers:

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

pipe = pipeline("text-generation", model="Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16")
model = AutoModelForMultimodalLM.from_pretrained("Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16

SGLang

How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16 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 "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16 with Docker Model Runner:
```
docker model run hf.co/Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16
```

Ttimms commited on about 13 hours ago

Commit

9265a48

verified ·

1 Parent(s): 6b97e2f

Shard weights into 3 files with an index for resumable downloads

Browse files

Identical tensors, verified byte-for-byte by SHA256 against the single-file checkpoint, and smoke-tested 4/4 after sharding. ~5 GiB shards follow the convention used by the base model, so an interrupted transfer resumes at shard granularity instead of restarting 12.45 GiB.

Files changed (4) hide show

model-00001-of-00003.safetensors +3 -0
model-00002-of-00003.safetensors +3 -0
model-00003-of-00003.safetensors +3 -0
model.safetensors.index.json +0 -0

model-00001-of-00003.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e0ea84f727b1751b5d12f4be9fcce91c96796f94caa05fee1d8ff62f96fc49
+size 5372863768

model-00002-of-00003.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc78c151836f4109a67bb754a4f9f794356f9c87a8b33c4909efac5c1e05869
+size 5370161096

model-00003-of-00003.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4e63956e3a8ceea62a1f685c507eb0bf9a0170fab27c61e6798f5e6ed5f609b1
+size 2626341776

model.safetensors.index.json ADDED Viewed

The diff for this file is too large to render. See raw diff