Instructions to use TuralBayev/axeron-forge-0646b223 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TuralBayev/axeron-forge-0646b223 with Transformers:

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

pipe = pipeline("text-generation", model="TuralBayev/axeron-forge-0646b223")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TuralBayev/axeron-forge-0646b223")
model = AutoModelForCausalLM.from_pretrained("TuralBayev/axeron-forge-0646b223", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TuralBayev/axeron-forge-0646b223 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TuralBayev/axeron-forge-0646b223"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TuralBayev/axeron-forge-0646b223",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TuralBayev/axeron-forge-0646b223

SGLang

How to use TuralBayev/axeron-forge-0646b223 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 "TuralBayev/axeron-forge-0646b223" \
    --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": "TuralBayev/axeron-forge-0646b223",
		"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 "TuralBayev/axeron-forge-0646b223" \
        --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": "TuralBayev/axeron-forge-0646b223",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TuralBayev/axeron-forge-0646b223 with Docker Model Runner:
```
docker model run hf.co/TuralBayev/axeron-forge-0646b223
```

0646b223-c5c2-4504-860c-1845dbe5bd86

This is a forge of pre-trained language models created using forgelm.

Forge Details

Forge Method

This model was forged using the DELLA forge method using meta-llama/Llama-3.1-8B as a base.

Models Forged

The following models were included in the forge:

meta-llama/Llama-3.1-8B-Instruct

Configuration

The following YAML configuration was used to produce this model:

base_model: meta-llama/Llama-3.1-8B
dtype: bfloat16
forge_method: della
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 32]
        model: meta-llama/Llama-3.1-8B-Instruct
        parameters:
          density: 1.0
          weight: 0.5
      - layer_range: [0, 32]
        model: meta-llama/Llama-3.1-8B

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for TuralBayev/axeron-forge-0646b223

Base model

meta-llama/Llama-3.1-8B

Finetuned

(1470)

this model

Paper for TuralBayev/axeron-forge-0646b223

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

Paper • 2406.11617 • Published Jun 17, 2024 • 12