Instructions to use knc6/microscopy_gpt_llama3.2_vision_11b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use knc6/microscopy_gpt_llama3.2_vision_11b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-11b-vision-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "knc6/microscopy_gpt_llama3.2_vision_11b")

Transformers

How to use knc6/microscopy_gpt_llama3.2_vision_11b with Transformers:

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

pipe = pipeline("text-generation", model="knc6/microscopy_gpt_llama3.2_vision_11b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("knc6/microscopy_gpt_llama3.2_vision_11b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use knc6/microscopy_gpt_llama3.2_vision_11b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "knc6/microscopy_gpt_llama3.2_vision_11b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "knc6/microscopy_gpt_llama3.2_vision_11b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/knc6/microscopy_gpt_llama3.2_vision_11b

SGLang

How to use knc6/microscopy_gpt_llama3.2_vision_11b 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 "knc6/microscopy_gpt_llama3.2_vision_11b" \
    --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": "knc6/microscopy_gpt_llama3.2_vision_11b",
		"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 "knc6/microscopy_gpt_llama3.2_vision_11b" \
        --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": "knc6/microscopy_gpt_llama3.2_vision_11b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use knc6/microscopy_gpt_llama3.2_vision_11b with Docker Model Runner:
```
docker model run hf.co/knc6/microscopy_gpt_llama3.2_vision_11b
```

knc6 commited on Jun 2, 2025

Commit

7891cc2

verified ·

1 Parent(s): f80d67c

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -1

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/mistral-7b-bnb-4bit
 library_name: peft
 license: mit
 language:
@@ -7,6 +7,15 @@ language:
 tags:
 - chemistry
 - text-generation-inference
 pipeline_tag: text-generation
 ---

 ---
+base_model: unsloth/Llama-3.2-11B-Vision-Instruct
 library_name: peft
 license: mit
 language:
 tags:
 - chemistry
 - text-generation-inference
+- llama-3
+- llama
+- meta
+- facebook
+- atomgpt
+- transformers
+- multimodal
+- vision
+- pytorch
 pipeline_tag: text-generation
 ---