Instructions to use TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1 with Transformers:

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

pipe = pipeline("text-generation", model="TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1")
model = AutoModelForCausalLM.from_pretrained("TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1")
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

vLLM

How to use TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1

SGLang

How to use TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1 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 "TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1" \
    --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": "TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1",
		"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 "TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1" \
        --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": "TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1 with Docker Model Runner:
```
docker model run hf.co/TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1
```

rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1

Fine-tuned checkpoint from the rankalign project.

Training Details

Field	Value
Base model	`google/gemma-2-9b-it`
Version	v6
Task	`persona-v0-all`
Epoch	0
Delta	0.15
Typicality correction	none
Length normalization	False
Preference loss weight	1
NLL validator weight	0
NLL generator weight	0
Validator log-odds	False
Force same-x	False
Semi-supervised ratio	0.1
Labeled-only ratio	None

Reproducibility

Original checkpoint name: v6-google--gemma-2-9b-it-delta0.15-epoch0--persona-v0-all--d2g--random--alpha1.0--full-completion--semi0.1

To evaluate:

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1 \
    --task persona-v0-all \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

Downloads last month: 17

Safetensors

Model size

9B params

Tensor type

F32

Model tree for TAUR-dev/rankalign-v6-gemma-2-9b-it-d0.15-e0-persona-v0-all-sm0.1

Base model

google/gemma-2-9b

Finetuned

google/gemma-2-9b-it

Finetuned

(480)

this model