Instructions to use Adi-Evolve/gemma-2-9b-linkscout-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Adi-Evolve/gemma-2-9b-linkscout-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Adi-Evolve/gemma-2-9b-linkscout-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Adi-Evolve/gemma-2-9b-linkscout-v1")
model = AutoModelForCausalLM.from_pretrained("Adi-Evolve/gemma-2-9b-linkscout-v1", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Adi-Evolve/gemma-2-9b-linkscout-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Adi-Evolve/gemma-2-9b-linkscout-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Adi-Evolve/gemma-2-9b-linkscout-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Adi-Evolve/gemma-2-9b-linkscout-v1

SGLang

How to use Adi-Evolve/gemma-2-9b-linkscout-v1 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 "Adi-Evolve/gemma-2-9b-linkscout-v1" \
    --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": "Adi-Evolve/gemma-2-9b-linkscout-v1",
		"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 "Adi-Evolve/gemma-2-9b-linkscout-v1" \
        --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": "Adi-Evolve/gemma-2-9b-linkscout-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Adi-Evolve/gemma-2-9b-linkscout-v1 with Docker Model Runner:
```
docker model run hf.co/Adi-Evolve/gemma-2-9b-linkscout-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

gemma-2-9b-linkscout-v1

This model is a fine-tuned version of unsloth/gemma-2-9b-it-bnb-4bit for fact-checking and misinformation detection.

Model Description

Base Model: unsloth/gemma-2-9b-it-bnb-4bit
Fine-tuned for: Fact-checking and bias detection
Training Method: LoRA/QLoRA with Unsloth
Merged: Yes (adapter merged with base model)

Usage

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="Adi-Evolve/gemma-2-9b-linkscout-v1",
    max_seq_length=2048,
    dtype=None,
    load_in_4bit=True,
)

FastLanguageModel.for_inference(model)

# Generate analysis
prompt = """<start_of_turn>user
Analyze this article for misinformation: [ARTICLE TEXT]
<end_of_turn>
<start_of_turn>model
"""

inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

Merged from LoRA adapter
Original base: unsloth/gemma-2-9b-it-bnb-4bit

Limitations

This model should be used as a tool to assist in fact-checking, not as a sole source of truth.

Downloads last month: 21

Safetensors

Model size

9B params

Tensor type

F32

F16

Model tree for Adi-Evolve/gemma-2-9b-linkscout-v1

Quantizations

1 model