Instructions to use ProCreations/grug-27b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ProCreations/grug-27b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="ProCreations/grug-27b-v2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ProCreations/grug-27b-v2")
model = AutoModelForMultimodalLM.from_pretrained("ProCreations/grug-27b-v2", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ProCreations/grug-27b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ProCreations/grug-27b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProCreations/grug-27b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ProCreations/grug-27b-v2

SGLang

How to use ProCreations/grug-27b-v2 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 "ProCreations/grug-27b-v2" \
    --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": "ProCreations/grug-27b-v2",
		"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 "ProCreations/grug-27b-v2" \
        --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": "ProCreations/grug-27b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ProCreations/grug-27b-v2 with Docker Model Runner:
```
docker model run hf.co/ProCreations/grug-27b-v2
```

ProCreations commited on 7 days ago

Commit

79a2b2b

verified ·

1 Parent(s): feceb98

Set validated Grug generation defaults; preserve native effort template and integrated weights

Browse files

Files changed (3) hide show

decoding_selection.json +18 -0
generation_config.json +2 -1
training_provenance.json +9 -2

decoding_selection.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+  "selected_template": "native effort instructions, default medium, canonical history normalization",
+  "sampling": {
+    "temperature": 0.6,
+    "top_p": 0.95,
+    "top_k": 20,
+    "repetition_penalty": 1.05
+  },
+  "development_labels": [
+    "development/decoding",
+    "development/decoding-t10"
+  ],
+  "reason": "Native RP1.05 keeps a larger reasoning allowance than compact-prompt variants and performed better on medium development coding, with no unfinished repetitive loops in its development probes. Full release verification continues separately.",
+  "backbone_revision": "eb3994615a9c74115c11be960d761f2ab30b5690",
+  "integrated_mtp_revision": "feceb9810535346ba806a7974fa4eb71012ccded",
+  "template_changed_from_integrated_revision": false,
+  "weights_changed_from_integrated_revision": false
+}

generation_config.json CHANGED Viewed

@@ -9,5 +9,6 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "5.16.1"
 }

   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
+  "transformers_version": "5.16.1",
+  "repetition_penalty": 1.05
 }

training_provenance.json CHANGED Viewed

@@ -8,5 +8,12 @@
   "tokenizer_data_revision": "e12e39b899f962c2f87ef461808f68d510e4fb4a",
   "release_template_sha256": "cd6193bb4cdc3ee69abd2ae9e15dc05ec3b85a48d161a623bdaae54009c0f995",
   "template_compatibility": "Native canonical rendering preserved. Historical inline reasoning and reasoning alias normalized once.",
-  "mtp_training_receipt": "mtp_training.json"
-}

   "tokenizer_data_revision": "e12e39b899f962c2f87ef461808f68d510e4fb4a",
   "release_template_sha256": "cd6193bb4cdc3ee69abd2ae9e15dc05ec3b85a48d161a623bdaae54009c0f995",
   "template_compatibility": "Native canonical rendering preserved. Historical inline reasoning and reasoning alias normalized once.",
+  "mtp_training_receipt": "mtp_training.json",
+  "generation_defaults": {
+    "temperature": 0.6,
+    "top_p": 0.95,
+    "top_k": 20,
+    "repetition_penalty": 1.05
+  },
+  "decoding_selection": "Native effort instructions retained; compact-prompt and temperature-1.0 alternatives inspected on reserved development tasks. A small repetition penalty improved completion without the compact-prompt coding regression."
+}