Instructions to use bruhzair/prototype-0.4x110 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bruhzair/prototype-0.4x110 with Transformers:

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

pipe = pipeline("text-generation", model="bruhzair/prototype-0.4x110")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bruhzair/prototype-0.4x110")
model = AutoModelForCausalLM.from_pretrained("bruhzair/prototype-0.4x110", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bruhzair/prototype-0.4x110 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bruhzair/prototype-0.4x110"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bruhzair/prototype-0.4x110",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bruhzair/prototype-0.4x110

SGLang

How to use bruhzair/prototype-0.4x110 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 "bruhzair/prototype-0.4x110" \
    --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": "bruhzair/prototype-0.4x110",
		"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 "bruhzair/prototype-0.4x110" \
        --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": "bruhzair/prototype-0.4x110",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bruhzair/prototype-0.4x110 with Docker Model Runner:
```
docker model run hf.co/bruhzair/prototype-0.4x110
```

prototype-0.4x110

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:

/workspace/prototype-0.4x109

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: passthrough
int8_mask: true
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 4]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [2, 4]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [4, 8]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [6, 8]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [8, 12]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [10, 12]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [12, 16]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [14, 16]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [16, 20]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [18, 20]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [20, 24]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [22, 24]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [24, 28]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [26, 28]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [28, 32]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [30, 32]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [32, 36]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [34, 36]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [36, 40]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [38, 40]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [40, 44]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [42, 44]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [44, 48]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [46, 48]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [48, 52]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [50, 52]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [52, 56]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [54, 56]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [56, 60]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [58, 60]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [60, 64]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [62, 64]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [64, 68]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [66, 68]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [68, 72]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [70, 72]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [72, 76]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [74, 76]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
    - sources:
      - layer_range: [76, 80]
        model: /workspace/prototype-0.4x109
    - sources:
      - layer_range: [78, 80]
        model: /workspace/prototype-0.4x109
        parameters:
          scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0

Downloads last month: 6

Safetensors

Model size

105B params

Tensor type

BF16