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
```

grug-27b-v2 / results /bfcl_completion.json

ProCreations

Release validated Grug 27B v2 with integrated MTP and measured results

f572b85 verified 20 days ago

Raw History Blame Contribute Delete

10.4 kB

	{
	"source_revision": "fb0fefdfad76f358edf9861f0c49e4ba2bdcab83",
	"records": {
	"evaluations/v2-rp105/low_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 176,
	"final_answer_pass_pct": 88.0,
	"completed_final_answer_pass_pct": 88.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v2-rp105/medium_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 176,
	"final_answer_pass_pct": 88.0,
	"completed_final_answer_pass_pct": 88.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v2-rp105/xhigh_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 174,
	"final_answer_pass_pct": 87.0,
	"completed_final_answer_pass_pct": 87.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v11-rp105/low_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 161,
	"final_answer_pass_pct": 80.5,
	"completed_final_answer_pass_pct": 80.5,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v11-rp105/medium_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 162,
	"final_answer_pass_pct": 81.0,
	"completed_final_answer_pass_pct": 81.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v11-rp105/xhigh_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 162,
	"final_answer_pass_pct": 81.0,
	"completed_final_answer_pass_pct": 81.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/qwen-rp105/low_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 178,
	"final_answer_pass_pct": 89.0,
	"completed_final_answer_pass_pct": 89.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/qwen-rp105/medium_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 178,
	"final_answer_pass_pct": 89.0,
	"completed_final_answer_pass_pct": 89.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/qwen-rp105/xhigh_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 176,
	"final_answer_pass_pct": 87.5,
	"completed_final_answer_pass_pct": 86.5,
	"passed_without_visible_final_answer": [
	"irrelevance_139"
	],
	"passed_without_eos": [
	"irrelevance_89",
	"irrelevance_157",
	"irrelevance_139"
	],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v2-mtp2/low_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 175,
	"final_answer_pass_pct": 87.5,
	"completed_final_answer_pass_pct": 87.5,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v2-mtp2/medium_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 180,
	"final_answer_pass_pct": 90.0,
	"completed_final_answer_pass_pct": 90.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v2-mtp2/xhigh_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 176,
	"final_answer_pass_pct": 88.0,
	"completed_final_answer_pass_pct": 88.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v2-candidate/low_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 173,
	"final_answer_pass_pct": 86.5,
	"completed_final_answer_pass_pct": 86.5,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v2-candidate/medium_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 179,
	"final_answer_pass_pct": 89.5,
	"completed_final_answer_pass_pct": 89.5,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v2-candidate/xhigh_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 177,
	"final_answer_pass_pct": 88.5,
	"completed_final_answer_pass_pct": 88.5,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v11-baseline/low_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 167,
	"final_answer_pass_pct": 83.5,
	"completed_final_answer_pass_pct": 83.5,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v11-baseline/medium_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 170,
	"final_answer_pass_pct": 85.0,
	"completed_final_answer_pass_pct": 85.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/v11-baseline/xhigh_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 166,
	"final_answer_pass_pct": 83.0,
	"completed_final_answer_pass_pct": 83.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/qwen-baseline/low_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 180,
	"final_answer_pass_pct": 90.0,
	"completed_final_answer_pass_pct": 90.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/qwen-baseline/medium_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 178,
	"final_answer_pass_pct": 89.0,
	"completed_final_answer_pass_pct": 89.0,
	"passed_without_visible_final_answer": [],
	"passed_without_eos": [],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	},
	"evaluations/qwen-baseline/xhigh_bfcl_generations.json": {
	"n": 200,
	"raw_passed": 176,
	"final_answer_pass_pct": 86.5,
	"completed_final_answer_pass_pct": 86.0,
	"passed_without_visible_final_answer": [
	"irrelevance_229",
	"irrelevance_132",
	"irrelevance_139"
	],
	"passed_without_eos": [
	"irrelevance_229",
	"irrelevance_132",
	"irrelevance_157",
	"irrelevance_139"
	],
	"completion_definition": "Require a visible final decision in addition to the stored official AST verdict; an unfinished thought that has not called a tool is not a completed irrelevance decision."
	}
	}
	}