Instructions to use CodCodingCode/medgemma-27b-conversation-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodCodingCode/medgemma-27b-conversation-finetune with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/medgemma-27b-text-it")
model = PeftModel.from_pretrained(base_model, "CodCodingCode/medgemma-27b-conversation-finetune")

Transformers

How to use CodCodingCode/medgemma-27b-conversation-finetune with Transformers:

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

pipe = pipeline("text-generation", model="CodCodingCode/medgemma-27b-conversation-finetune")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("CodCodingCode/medgemma-27b-conversation-finetune", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CodCodingCode/medgemma-27b-conversation-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodCodingCode/medgemma-27b-conversation-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodCodingCode/medgemma-27b-conversation-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CodCodingCode/medgemma-27b-conversation-finetune

SGLang

How to use CodCodingCode/medgemma-27b-conversation-finetune 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 "CodCodingCode/medgemma-27b-conversation-finetune" \
    --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": "CodCodingCode/medgemma-27b-conversation-finetune",
		"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 "CodCodingCode/medgemma-27b-conversation-finetune" \
        --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": "CodCodingCode/medgemma-27b-conversation-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CodCodingCode/medgemma-27b-conversation-finetune with Docker Model Runner:
```
docker model run hf.co/CodCodingCode/medgemma-27b-conversation-finetune
```

CodCodingCode commited on Jul 12, 2025

Commit

5fa10f5

verified ·

1 Parent(s): 18719c3

Training in progress, step 875

Browse files

Files changed (2) hide show

adapter_model.safetensors +1 -1
runs/Jul12_22-07-56_192-222-50-225/events.out.tfevents.1752358076.192-222-50-225.12949.0 +2 -2

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e05719bbf60fa0883c17f8143fc8ac368073f7e1ed01e97966d559b583f1ea3
 size 227149016

 version https://git-lfs.github.com/spec/v1
+oid sha256:c51a2d802810f7014ea70ee34309108585f13325a6eb223adec23ea11fa85afb
 size 227149016

runs/Jul12_22-07-56_192-222-50-225/events.out.tfevents.1752358076.192-222-50-225.12949.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19af3d4f61f6e93d7c64a4135ecef73ecade4c86d0371a41609e878fe3139fc7
-size 27890

 version https://git-lfs.github.com/spec/v1
+oid sha256:d09431558ddf8b2adae22dc264018305fdf20302e938cd866c2cc2c90bc0cbbb
+size 44069