Instructions to use electricsheepafrica/medgemma-4b-it-text-only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use electricsheepafrica/medgemma-4b-it-text-only with Transformers:

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

pipe = pipeline("text-generation", model="electricsheepafrica/medgemma-4b-it-text-only")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("electricsheepafrica/medgemma-4b-it-text-only")
model = AutoModelForCausalLM.from_pretrained("electricsheepafrica/medgemma-4b-it-text-only", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use electricsheepafrica/medgemma-4b-it-text-only with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "electricsheepafrica/medgemma-4b-it-text-only"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "electricsheepafrica/medgemma-4b-it-text-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/electricsheepafrica/medgemma-4b-it-text-only

SGLang

How to use electricsheepafrica/medgemma-4b-it-text-only 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 "electricsheepafrica/medgemma-4b-it-text-only" \
    --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": "electricsheepafrica/medgemma-4b-it-text-only",
		"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 "electricsheepafrica/medgemma-4b-it-text-only" \
        --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": "electricsheepafrica/medgemma-4b-it-text-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use electricsheepafrica/medgemma-4b-it-text-only with Docker Model Runner:
```
docker model run hf.co/electricsheepafrica/medgemma-4b-it-text-only
```

Kossisoroyce commited on Jan 10

Commit

412ec5f

verified ·

1 Parent(s): 5c344b9

Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

.gitattributes +1 -0
README.md +50 -0
config.json +30 -0
model.safetensors +3 -0
special_tokens_map.json +33 -0
tokenizer.json +3 -0
tokenizer.model +3 -0
tokenizer_config.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,50 @@

+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- medical
+- healthcare
+- gemma
+- vllm
+- africa
+- chw
+base_model: google/medgemma-4b-it
+---
+# Chewie Text-Only (MedGemma)
+Text-only version of Chewie/MedGemma for **fast vLLM inference**.
+## Performance
+| Model | Architecture | vLLM | Speed |
+|-------|--------------|------|-------|
+| chewie-merged | Gemma3ForConditionalGeneration | ❌ | ~22s |
+| **chewie-text-only** | Gemma3ForCausalLM | ✅ | **~5s** |
+## Usage with vLLM
+```python
+from openai import OpenAI
+client = OpenAI(
+    base_url="YOUR_ENDPOINT/v1/",
+    api_key="YOUR_TOKEN"
+)
+response = client.chat.completions.create(
+    model="electricsheepafrica/chewie-text-only",
+    messages=[{"role": "user", "content": "Child has fever for 3 days"}],
+    max_tokens=200,
+    temperature=0.3
+)
+print(response.choices[0].message.content)
+```
+## What Changed
+- Removed vision tower (~1GB saved)
+- Changed architecture to Gemma3ForCausalLM
+- Stripped `language_model.` prefix from weights
+- Reduced max_position_embeddings to 8192

config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "model_type": "gemma3_text",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "vocab_size": 262208,
+  "hidden_size": 2560,
+  "intermediate_size": 10240,
+  "num_hidden_layers": 34,
+  "num_attention_heads": 8,
+  "num_key_value_heads": 4,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "max_position_embeddings": 8192,
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-06,
+  "use_cache": true,
+  "pad_token_id": 0,
+  "eos_token_id": 1,
+  "bos_token_id": 2,
+  "tie_word_embeddings": true,
+  "rope_theta": 1000000,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "query_pre_attn_scalar": 256,
+  "sliding_window": 1024,
+  "sliding_window_pattern": 6
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:af38216f1c9ade46b5dc750c4e65a172c3042dcd7b0dc6e15d71a074b2efae3a
+size 7760578088

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4046bf0505a327dd5a0abbb427ecd4fc82f99c2ceaa170bc61ecde12809b0c
+size 33384570

tokenizer.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

tokenizer_config.json ADDED Viewed

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