Instructions to use primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4

SGLang

How to use primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4 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 "primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4" \
    --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": "primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4",
		"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 "primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4" \
        --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": "primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4
```

jagat-primitive-org commited on 3 days ago

Commit

b244389

verified ·

1 Parent(s): 208e9b4

Weights: best-measured build at this size (tool-call-calibrated activation scales)

Browse files

Files changed (8) hide show

model-00001-of-00008.safetensors +1 -1
model-00002-of-00008.safetensors +1 -1
model-00003-of-00008.safetensors +1 -1
model-00004-of-00008.safetensors +1 -1
model-00005-of-00008.safetensors +1 -1
model-00006-of-00008.safetensors +1 -1
model-00007-of-00008.safetensors +1 -1
model-00008-of-00008.safetensors +1 -1

model-00001-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40aed59c52f6b716a7abf98094bfbee3a21c76a3d5f44b6244e12d8cb661789
 size 4999678904

 version https://git-lfs.github.com/spec/v1
+oid sha256:1e49f4c3ba5e73d5e487d38d25950b775a877e5e7e5c01da6448e6f1cb135368
 size 4999678904

model-00002-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:512f56c87fcbd64fb9b7dbdb4d1da739dc65b0dfae56c48953c1a05fb801b0a8
 size 4981090200

 version https://git-lfs.github.com/spec/v1
+oid sha256:de2b25faa0b371a6fa113e1cf35e2ae88a8364381d02e085741945c8e1cfb501
 size 4981090200

model-00003-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69d4f4bb49d88c0acf9dd4aa4ff3b0701657b3cac25da89c48a118c7dc9a34e
 size 4998287984

 version https://git-lfs.github.com/spec/v1
+oid sha256:121b0683c8af953cd667ac749caccdbf9c8e50ef3d8713c493e7426bb0ca0d43
 size 4998287984

model-00004-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4590af454e688e04fdfe92d649be83e0d2da1b7a9ad44aaf4aa26f97f4e945
 size 4996816808

 version https://git-lfs.github.com/spec/v1
+oid sha256:22b6dfc7b3614e622b7554e9a44c453e89519aa8586e8d0a1f90d7480b0ffde9
 size 4996816808

model-00005-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a13df2dc33196286f5f49100aac1e4c0c1715266f1b4c002f29469fbfab22e55
 size 5001039560

 version https://git-lfs.github.com/spec/v1
+oid sha256:9aa065012dd4a1a0e9d5d336bb55b2fdee921261b29ade17fd96a7f208ab68ee
 size 5001039560

model-00006-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e90f722592940fed01c747525dd3ad7e57971346ef728513452e83162fc094
 size 4999301880

 version https://git-lfs.github.com/spec/v1
+oid sha256:3a246a6acf7587587dd7266905a19bef0ce8d12d4a83486faab2911d4f85d099
 size 4999301880

model-00007-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21311da290e1defc5b92a25845a638b022c0465966c375c56df888d6ce6809e7
 size 4996814312

 version https://git-lfs.github.com/spec/v1
+oid sha256:5852223b353001902a4ff00c623c505939c925288f465c6680a179e26427711f
 size 4996814312

model-00008-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff40a74bb96010ec32137bc2ec22bbca4de4cd3d52e1c412e4529a2d29c591ac
 size 1769535568

 version https://git-lfs.github.com/spec/v1
+oid sha256:4ec0d8a8c40fdceca9116a2c772b7cff4d191fe11f7ee8fcb97fef5e0a3ce7d8
 size 1769535568