Instructions to use bruhzair/prototype0.4x96 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bruhzair/prototype0.4x96 with Transformers:

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

pipe = pipeline("text-generation", model="bruhzair/prototype0.4x96")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bruhzair/prototype0.4x96")
model = AutoModelForCausalLM.from_pretrained("bruhzair/prototype0.4x96", 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/prototype0.4x96 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bruhzair/prototype0.4x96"
# 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/prototype0.4x96",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bruhzair/prototype0.4x96

SGLang

How to use bruhzair/prototype0.4x96 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/prototype0.4x96" \
    --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/prototype0.4x96",
		"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/prototype0.4x96" \
        --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/prototype0.4x96",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bruhzair/prototype0.4x96 with Docker Model Runner:
```
docker model run hf.co/bruhzair/prototype0.4x96
```

prototype0.4x96

File size: 1,906 Bytes

d9b8bf0

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

---
# prototype-0.4x96

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 [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c as a base.

### Models Merged

The following models were included in the merge:
* /workspace/cache/models--SentientAGI--Dobby-Unhinged-Llama-3.3-70B/snapshots/30d6a881ec430ede8990cc77fa8e62e72880378c
* /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/097a11b4600eafe333a2be0309bbdf6be2f197c4
* /workspace/cache/models--mlabonne--Hermes-3-Llama-3.1-70B-lorablated/snapshots/4295cb5975cacb8ddf4595557c931b6430cf8d6d

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: /workspace/cache/models--mlabonne--Hermes-3-Llama-3.1-70B-lorablated/snapshots/4295cb5975cacb8ddf4595557c931b6430cf8d6d
    parameters:
      select_topk: 0.15
  - model: /workspace/cache/models--SentientAGI--Dobby-Unhinged-Llama-3.3-70B/snapshots/30d6a881ec430ede8990cc77fa8e62e72880378c
    parameters:
      select_topk: 0.35
  - model: /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/097a11b4600eafe333a2be0309bbdf6be2f197c4
    parameters:
      select_topk: 0.5
  - model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
    parameters:
      select_topk: 0.65
base_model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
merge_method: sce
tokenizer:
  source: base
chat_template: llama3
int8_mask: true
dtype: bfloat16
```