tepirale

gemma-4-12B-merge-coder40-agentic40-it20-linear

Deploy Dedicated

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml
merge_method: linear
parameters:
  normalize: true
dtype: bfloat16
models:
  - model: tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1
    parameters:
      weight: 0.4
  - model: tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1
    parameters:
      weight: 0.4
  - model: google/gemma-4-12B-it
    parameters:
      weight: 0.2

py
import torch
from transformers import AutoProcessor, AutoModelForMultimodalLM, AutoModelForCausalLM


MODEL_ID_HUB = "tepirale/gemma-4-12B-merge-coder40-agentic40-it20" 
MA= "tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-assistant-safetensors-yuxinlu1"


model = AutoModelForMultimodalLM.from_pretrained(
    MODEL_ID_HUB,
    dtype="auto",
    device_map="auto",
    # local_files_only=True
)

assistant_model = AutoModelForCausalLM.from_pretrained(MA, 
                                                       dtype=torch.bfloat16, 
                                                       device_map="auto"
                                                       )

processor = AutoProcessor.from_pretrained(MODEL_ID_HUB)


# Prompt - add image before text
messages = [
    {
        "role": "user", "content": [
            {"type": "image", "url": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/apps/sample-data/GoldenGate.png"},
            {"type": "text", "text": "What is shown in this image?"}
        ]
    }
]

# Process input
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
    add_generation_prompt=True,
    enable_thinking=True
).to(model.device)
input_len = inputs["input_ids"].shape[-1]

# Generate output
outputs = model.generate(**inputs, max_new_tokens=3512, assistant_model=assistant_model)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)

# Parse output
processor.parse_response(response)

Model provider

tepirale

Model tree

Base

tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1

Base

google/gemma-4-12B-it

Base

tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1

Merged

this model

Modalities

Input

Video, Audio, Text, Image

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Model card

yaml

merge_method: linear
parameters:
  normalize: true
dtype: bfloat16
models:
  - model: tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1
    parameters:
      weight: 0.4
  - model: tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1
    parameters:
      weight: 0.4
  - model: google/gemma-4-12B-it
    parameters:
      weight: 0.2

import torch
from transformers import AutoProcessor, AutoModelForMultimodalLM, AutoModelForCausalLM


MODEL_ID_HUB = "tepirale/gemma-4-12B-merge-coder40-agentic40-it20" 
MA= "tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-assistant-safetensors-yuxinlu1"


model = AutoModelForMultimodalLM.from_pretrained(
    MODEL_ID_HUB,
    dtype="auto",
    device_map="auto",
    # local_files_only=True
)

assistant_model = AutoModelForCausalLM.from_pretrained(MA, 
                                                       dtype=torch.bfloat16, 
                                                       device_map="auto"
                                                       )

processor = AutoProcessor.from_pretrained(MODEL_ID_HUB)


# Prompt - add image before text
messages = [
    {
        "role": "user", "content": [
            {"type": "image", "url": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/apps/sample-data/GoldenGate.png"},
            {"type": "text", "text": "What is shown in this image?"}
        ]
    }
]

# Process input
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
    add_generation_prompt=True,
    enable_thinking=True
).to(model.device)
input_len = inputs["input_ids"].shape[-1]

# Generate output
outputs = model.generate(**inputs, max_new_tokens=3512, assistant_model=assistant_model)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)

# Parse output
processor.parse_response(response)

gemma-4-12B-merge-coder40-agentic40-it20-linear

Get help setting up a custom Dedicated Endpoints.

Merge Details

Merge Method

Models Merged

Configuration

Explore FriendliAI today

Merge Details

Merge Method

Models Merged

Configuration