Instructions to use TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo with Transformers:

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

pipe = pipeline("text-generation", model="TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo")
model = AutoModelForCausalLM.from_pretrained("TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo 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-2-2b-d0.15-e2-ambigqa-all-tcs-vlo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo

SGLang

How to use TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo 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-2-2b-d0.15-e2-ambigqa-all-tcs-vlo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-2-2b-d0.15-e2-ambigqa-all-tcs-vlo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo with Docker Model Runner:
```
docker model run hf.co/TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo
```

rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo

Fine-tuned checkpoint from the rankalign project.

Training Details

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

Reproducibility

Original checkpoint name: v6-google--gemma-2-2b-delta0.15-epoch2--ambigqa-all--d2g--random--alpha1.0--tc-self--tcoracle--full-completion--vallogodds

To evaluate:

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo \
    --task ambigqa-all \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

Downloads last month: 8

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-ambigqa-all-tcs-vlo

Base model

google/gemma-2-2b

Finetuned

(560)

this model