Instructions to use BeaverAI/Gemma-14B-SPPO-Interleaved with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BeaverAI/Gemma-14B-SPPO-Interleaved with Transformers:

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

pipe = pipeline("text-generation", model="BeaverAI/Gemma-14B-SPPO-Interleaved")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("BeaverAI/Gemma-14B-SPPO-Interleaved")
model = AutoModelForMultimodalLM.from_pretrained("BeaverAI/Gemma-14B-SPPO-Interleaved")
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 Settings

vLLM

How to use BeaverAI/Gemma-14B-SPPO-Interleaved with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BeaverAI/Gemma-14B-SPPO-Interleaved"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BeaverAI/Gemma-14B-SPPO-Interleaved",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BeaverAI/Gemma-14B-SPPO-Interleaved

SGLang

How to use BeaverAI/Gemma-14B-SPPO-Interleaved 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 "BeaverAI/Gemma-14B-SPPO-Interleaved" \
    --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": "BeaverAI/Gemma-14B-SPPO-Interleaved",
		"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 "BeaverAI/Gemma-14B-SPPO-Interleaved" \
        --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": "BeaverAI/Gemma-14B-SPPO-Interleaved",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BeaverAI/Gemma-14B-SPPO-Interleaved with Docker Model Runner:
```
docker model run hf.co/BeaverAI/Gemma-14B-SPPO-Interleaved
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

merged

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3

Configuration

The following YAML configuration was used to produce this model:

merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 24]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Original L24
- sources:
  - layer_range: [24, 25]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L24
- sources:
  - layer_range: [24, 25]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L24
- sources:
  - layer_range: [24, 25]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L25
- sources:
  - layer_range: [25, 26]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L25
- sources:
  - layer_range: [25, 26]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L25
- sources:
  - layer_range: [25, 26]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L26
- sources:
  - layer_range: [26, 27]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L26
- sources:
  - layer_range: [26, 27]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L26
- sources:
  - layer_range: [26, 27]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L27
- sources:
  - layer_range: [27, 28]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L27
- sources:
  - layer_range: [27, 28]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L27
- sources:
  - layer_range: [27, 28]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L28
- sources:
  - layer_range: [28, 29]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L28
- sources:
  - layer_range: [28, 29]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L28
- sources:
  - layer_range: [28, 29]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L29
- sources:
  - layer_range: [29, 30]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L29
- sources:
  - layer_range: [29, 30]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L29
- sources:
  - layer_range: [29, 30]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L30
- sources:
  - layer_range: [30, 31]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L30
- sources:
  - layer_range: [30, 31]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L30
- sources:
  - layer_range: [30, 31]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L31
- sources:
  - layer_range: [31, 32]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L31
- sources:
  - layer_range: [31, 32]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L31
- sources:
  - layer_range: [31, 32]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L32
- sources:
  - layer_range: [32, 33]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L32
- sources:
  - layer_range: [32, 33]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L32
- sources:
  - layer_range: [32, 33]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L33
- sources:
  - layer_range: [33, 34]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L33
- sources:
  - layer_range: [33, 34]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L33
- sources:
  - layer_range: [33, 34]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L34
- sources:
  - layer_range: [34, 35]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L34
- sources:
  - layer_range: [34, 35]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L34
- sources:
  - layer_range: [34, 35]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L35
- sources:
  - layer_range: [35, 36]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L35
- sources:
  - layer_range: [35, 36]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L35
- sources:
  - layer_range: [35, 36]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L36
- sources:
  - layer_range: [36, 37]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
# Dupe A of L36
- sources:
  - layer_range: [36, 37]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Dupe B of L36
- sources:
  - layer_range: [36, 37]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [37, 42]
    model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3

Downloads last month: -

Safetensors

Model size

14B params

Tensor type

BF16

Model tree for BeaverAI/Gemma-14B-SPPO-Interleaved

Base model

UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3

Finetuned

(8)

this model