Instructions to use melino2000/tiny-llama-merge-evo-server with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use melino2000/tiny-llama-merge-evo-server with Transformers:

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

pipe = pipeline("text-generation", model="melino2000/tiny-llama-merge-evo-server")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("melino2000/tiny-llama-merge-evo-server")
model = AutoModelForCausalLM.from_pretrained("melino2000/tiny-llama-merge-evo-server")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use melino2000/tiny-llama-merge-evo-server with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "melino2000/tiny-llama-merge-evo-server"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "melino2000/tiny-llama-merge-evo-server",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/melino2000/tiny-llama-merge-evo-server

SGLang

How to use melino2000/tiny-llama-merge-evo-server 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 "melino2000/tiny-llama-merge-evo-server" \
    --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": "melino2000/tiny-llama-merge-evo-server",
		"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 "melino2000/tiny-llama-merge-evo-server" \
        --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": "melino2000/tiny-llama-merge-evo-server",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use melino2000/tiny-llama-merge-evo-server with Docker Model Runner:
```
docker model run hf.co/melino2000/tiny-llama-merge-evo-server
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

final_merge

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064 as a base.

Models Merged

The following models were included in the merge:

/home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950

Configuration

The following YAML configuration was used to produce this model:

base_model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 2]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 0.9572415069321948
  - layer_range: [0, 2]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [2, 4]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 1.3027552693206474
  - layer_range: [2, 4]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [4, 6]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 1.1000872891940183
  - layer_range: [4, 6]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [6, 8]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 0.8472430654902018
  - layer_range: [6, 8]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [8, 10]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 0.9915310236895785
  - layer_range: [8, 10]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [10, 12]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 1.1144858726152178
  - layer_range: [10, 12]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [12, 14]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 0.8140779929520541
  - layer_range: [12, 14]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [14, 16]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 1.1599951316231072
  - layer_range: [14, 16]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [16, 18]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 0.5993074778392211
  - layer_range: [16, 18]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [18, 20]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 0.8145134707653817
  - layer_range: [18, 20]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
- sources:
  - layer_range: [20, 22]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
    parameters:
      weight: 0.9579703282891905
  - layer_range: [20, 22]
    model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064

Downloads last month: 4

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for melino2000/tiny-llama-merge-evo-server

Quantizations

1 model

Paper for melino2000/tiny-llama-merge-evo-server

Editing Models with Task Arithmetic

Paper • 2212.04089 • Published Dec 8, 2022 • 9