Instructions to use bruhzair/Test-Model-4-105B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bruhzair/Test-Model-4-105B with Transformers:

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

pipe = pipeline("text-generation", model="bruhzair/Test-Model-4-105B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bruhzair/Test-Model-4-105B")
model = AutoModelForCausalLM.from_pretrained("bruhzair/Test-Model-4-105B", 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/Test-Model-4-105B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bruhzair/Test-Model-4-105B"
# 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/Test-Model-4-105B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bruhzair/Test-Model-4-105B

SGLang

How to use bruhzair/Test-Model-4-105B 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/Test-Model-4-105B" \
    --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/Test-Model-4-105B",
		"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/Test-Model-4-105B" \
        --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/Test-Model-4-105B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bruhzair/Test-Model-4-105B with Docker Model Runner:
```
docker model run hf.co/bruhzair/Test-Model-4-105B
```

Purpose

Mergefuel experiment.

Models Merged

The following models were included in the merge:

bruhzair/ignore-merge-7 (Sao10K/L3.1-70B-Hanami-x1 upscaled to 105B)
bruhzair/EVA-x-EVA-105b (EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1 upscaled to 105B)
bruhzair/ignore-merge-16 (Sao10K/70B-L3.3-mhnnn-x1 upscaled to 105B)
bruhzair/ignore-merge-8 (Sao10K/70B-L3.3-Cirrus-x1 upscaled to 105B)
BASE: bruhzair/ignore-merge-19 (mlabonne/Hermes-3-Llama-3.1-70B-lorablated upscaled to 105B)

Configuration

The following YAML configuration was used to produce this model:

base_model: /workspace/cache/models--bruhzair--ignore-merge-19/snapshots/57e2fc7118091e0706844a2e88d4c911d94e1e52
dtype: bfloat16
merge_method: sce
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 120]
        model: /workspace/cache/models--bruhzair--ignore-merge-7/snapshots/e3146f6352c469e3798634e02be758a96d1c5b2c
        parameters:
          select_topk: 0.5
      - layer_range: [0, 120]
        model: /workspace/cache/models--bruhzair--ignore-merge-6/snapshots/87658005d40b593ba3e87e92e5fb3f28321266a1
        parameters:
          select_topk: 0.5
      - layer_range: [0, 120]
        model: /workspace/cache/models--bruhzair--ignore-merge-8/snapshots/253c403660e94c867c277d8408e8cb518ab8bf1b
        parameters:
          select_topk: 0.5
      - layer_range: [0, 120]
        model: /workspace/cache/models--bruhzair--ignore-merge-16/snapshots/26451f702071dc18648067a0f5f730f8d4f94570
        parameters:
          select_topk: 0.5
      - layer_range: [0, 120]
        model: /workspace/cache/models--bruhzair--ignore-merge-19/snapshots/57e2fc7118091e0706844a2e88d4c911d94e1e52
        parameters:
          select_topk: 0.5
parameters:
  normalize: 0.0
tokenizer:
  source: base

Downloads last month: 6

Safetensors

Model size

105B params

Tensor type

BF16