Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Instructions to use mergekit-community/L3.3-Test-Step2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mergekit-community/L3.3-Test-Step2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mergekit-community/L3.3-Test-Step2") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("mergekit-community/L3.3-Test-Step2") model = AutoModelForCausalLM.from_pretrained("mergekit-community/L3.3-Test-Step2", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mergekit-community/L3.3-Test-Step2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mergekit-community/L3.3-Test-Step2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mergekit-community/L3.3-Test-Step2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/mergekit-community/L3.3-Test-Step2
- SGLang
How to use mergekit-community/L3.3-Test-Step2 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 "mergekit-community/L3.3-Test-Step2" \ --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": "mergekit-community/L3.3-Test-Step2", "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 "mergekit-community/L3.3-Test-Step2" \ --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": "mergekit-community/L3.3-Test-Step2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use mergekit-community/L3.3-Test-Step2 with Docker Model Runner:
docker model run hf.co/mergekit-community/L3.3-Test-Step2
|
Download README.md from mergekit-community/L3.3-Test-Step2: direct link, hf CLI and curl.
- Browser
- Download file 1.69 kB
-
https://huggingface.co/mergekit-community/L3.3-Test-Step2/resolve/main/README.md
- Command line
-
hf download hf://mergekit-community/L3.3-Test-Step2/README.md
-
curl -L -o README.md https://huggingface.co/mergekit-community/L3.3-Test-Step2/resolve/main/README.md
1.69 kB
metadata
base_model:
- Nohobby/AbominationSnowPig
- ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4
- mergekit-community/L3.3-Test-Step1
- sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1
library_name: transformers
tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Breadcrumbs with TIES merge method using mergekit-community/L3.3-Test-Step1 as a base.
Models Merged
The following models were included in the merge:
- Nohobby/AbominationSnowPig
- ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4
- sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1
Configuration
The following YAML configuration was used to produce this model:
models:
- model: mergekit-community/L3.3-Test-Step1
- model: sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1
parameters:
density: 0.75
gamma: 0.01
weight: 0.05
- model: Nohobby/AbominationSnowPig
parameters:
density: 0.77
gamma: 0.007
weight: 0.07
- model: ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4
parameters:
density: 0.88
gamma: 0.008
weight: 0.28
base_model: mergekit-community/L3.3-Test-Step1
merge_method: breadcrumbs_ties
parameters:
int8_mask: true
rescale: true
normalize: false
dtype: bfloat16
tokenizer_source: base