Instructions to use bruhzair/prototype0.4x52 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bruhzair/prototype0.4x52 with Transformers:

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

pipe = pipeline("text-generation", model="bruhzair/prototype0.4x52")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bruhzair/prototype0.4x52")
model = AutoModelForCausalLM.from_pretrained("bruhzair/prototype0.4x52", device_map="auto")
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/prototype0.4x52 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bruhzair/prototype0.4x52"
# 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/prototype0.4x52",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bruhzair/prototype0.4x52

SGLang

How to use bruhzair/prototype0.4x52 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/prototype0.4x52" \
    --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/prototype0.4x52",
		"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/prototype0.4x52" \
        --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/prototype0.4x52",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bruhzair/prototype0.4x52 with Docker Model Runner:
```
docker model run hf.co/bruhzair/prototype0.4x52
```

prototype0.4x52

File size: 1,201 Bytes

b8e7adc

---
base_model: []
library_name: transformers
tags:
- mergekit
- merge

---
# prototype-0.4x52

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using /workspace/prototype-0.4x50 as a base.

### Models Merged

The following models were included in the merge:
* /workspace/prototype-0.4x45
* /workspace/prototype-0.4x51
* /workspace/prototype-0.4x49

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: /workspace/prototype-0.4x49
    parameters:
      weight: 0.25
      density: 0.5
  - model: /workspace/prototype-0.4x45
    parameters:
      weight: 0.25
      density: 0.5
  - model: /workspace/prototype-0.4x51
    parameters:
      weight: 0.25
      density: 0.5
  - model: /workspace/prototype-0.4x50
    parameters:
      weight: 0.25
      density: 0.5
merge_method: dare_ties
base_model: /workspace/prototype-0.4x50
parameters:
  lambda: 0.95
  normalize: true
dtype: bfloat16
int8_mask: true
chat_template: llama3
tokenizer:
 source: base
```