Instructions to use Rocketknight1/pixtral_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rocketknight1/pixtral_test with Transformers:

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

pipe = pipeline("image-text-to-text", model="Rocketknight1/pixtral_test")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Rocketknight1/pixtral_test")
model = AutoModelForImageTextToText.from_pretrained("Rocketknight1/pixtral_test")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Rocketknight1/pixtral_test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rocketknight1/pixtral_test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rocketknight1/pixtral_test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rocketknight1/pixtral_test

SGLang

How to use Rocketknight1/pixtral_test 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 "Rocketknight1/pixtral_test" \
    --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": "Rocketknight1/pixtral_test",
		"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 "Rocketknight1/pixtral_test" \
        --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": "Rocketknight1/pixtral_test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rocketknight1/pixtral_test with Docker Model Runner:
```
docker model run hf.co/Rocketknight1/pixtral_test
```

Upload LlavaForConditionalGeneration

by Rocketknight1 HF Staff - opened Dec 20, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

config.json +2 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "pixtral_converted",
   "architectures": [
     "LlavaForConditionalGeneration"
   ],
@@ -19,6 +19,7 @@
     "num_attention_heads": 96,
     "num_hidden_layers": 88,
     "num_key_value_heads": 8,
     "rope_theta": 1000000000.0,
     "sliding_window": null,
     "vocab_size": 32768

 {
+  "_name_or_path": "./",
   "architectures": [
     "LlavaForConditionalGeneration"
   ],
     "num_attention_heads": 96,
     "num_hidden_layers": 88,
     "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
     "rope_theta": 1000000000.0,
     "sliding_window": null,
     "vocab_size": 32768