Instructions to use bruhzair/prototype-0.4x112 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bruhzair/prototype-0.4x112 with Transformers:

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

pipe = pipeline("text-generation", model="bruhzair/prototype-0.4x112")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bruhzair/prototype-0.4x112")
model = AutoModelForCausalLM.from_pretrained("bruhzair/prototype-0.4x112")
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 bruhzair/prototype-0.4x112 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bruhzair/prototype-0.4x112"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bruhzair/prototype-0.4x112",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bruhzair/prototype-0.4x112

SGLang

How to use bruhzair/prototype-0.4x112 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-0.4x112" \
    --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": "bruhzair/prototype-0.4x112",
		"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 "bruhzair/prototype-0.4x112" \
        --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": "bruhzair/prototype-0.4x112",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bruhzair/prototype-0.4x112 with Docker Model Runner:
```
docker model run hf.co/bruhzair/prototype-0.4x112
```

prototype-0.4x112

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

Merge Details

Merge Method

This model was merged using the SCE merge method using /workspace/prototype-0.4x102 as a base.

Models Merged

The following models were included in the merge:

/workspace/cache/models--EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.1/snapshots/7cd63fd3a5519383bfa57bf1f9f2cb008f366f90
/workspace/cache/models--Sao10K--Llama-3.3-70B-Vulpecula-r1/snapshots/12d7254ab9a5ce21905f59f341a3d2a2b3e62fd5
/workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /workspace/cache/models--EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.1/snapshots/7cd63fd3a5519383bfa57bf1f9f2cb008f366f90
    parameters:
      select_topk: 0.4
  - model: /workspace/cache/models--Sao10K--Llama-3.3-70B-Vulpecula-r1/snapshots/12d7254ab9a5ce21905f59f341a3d2a2b3e62fd5
    parameters:
      select_topk: 0.4
  - model: /workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3
    parameters:
      select_topk: 0.4
  - model: /workspace/prototype-0.4x102
    parameters:
      select_topk: 0.45
base_model: /workspace/prototype-0.4x102
merge_method: sce
tokenizer:
  source: base
chat_template: llama3
int8_mask: true
dtype: bfloat16

Downloads last month: 2

Safetensors

Model size

71B params

Tensor type

BF16

Paper for bruhzair/prototype-0.4x112

FuseChat: Knowledge Fusion of Chat Models

Paper • 2408.07990 • Published Aug 15, 2024 • 15