Instructions to use Muhammad2003/LlamaMerge-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Muhammad2003/LlamaMerge-v3 with Transformers:

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

pipe = pipeline("text-generation", model="Muhammad2003/LlamaMerge-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Muhammad2003/LlamaMerge-v3")
model = AutoModelForCausalLM.from_pretrained("Muhammad2003/LlamaMerge-v3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Muhammad2003/LlamaMerge-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Muhammad2003/LlamaMerge-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Muhammad2003/LlamaMerge-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Muhammad2003/LlamaMerge-v3

SGLang

How to use Muhammad2003/LlamaMerge-v3 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 "Muhammad2003/LlamaMerge-v3" \
    --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": "Muhammad2003/LlamaMerge-v3",
		"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 "Muhammad2003/LlamaMerge-v3" \
        --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": "Muhammad2003/LlamaMerge-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Muhammad2003/LlamaMerge-v3 with Docker Model Runner:
```
docker model run hf.co/Muhammad2003/LlamaMerge-v3
```

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using johnsnowlabs/JSL-MedLlama-3-8B-v2.0 as a base.

Models Merged

The following models were included in the merge:

skumar9/Llama-medx_v3.2

Configuration

The following YAML configuration was used to produce this model:


models: 
  - model: johnsnowlabs/JSL-MedLlama-3-8B-v2.0
    parameters:
      density: 0.53
      weight: 0.4
  - model: skumar9/Llama-medx_v3.2
    parameters:
      density: 0.53
      weight: 0.3

merge_method: dare_ties
base_model: johnsnowlabs/JSL-MedLlama-3-8B-v2.0
parameters:
  int8_mask: true
dtype: bfloat16

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Muhammad2003/LlamaMerge-v3

johnsnowlabs/JSL-MedLlama-3-8B-v2.0

skumar9/Llama-medx_v3.2

Merge model

this model

Papers for Muhammad2003/LlamaMerge-v3

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 33

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19