metadata
tags:
- merge
- mergekit
- lazymergekit
- openchat/openchat-3.5-0106
- teknium/OpenHermes-2.5-Mistral-7B
base_model:
- openchat/openchat-3.5-0106
- teknium/OpenHermes-2.5-Mistral-7B
djinn
djinn is a merge of the following models using LazyMergekit:
🧩 Configuration
merge_method: linear # use linear so we can include multiple models, albeit at a zero weight
parameters:
weight: 1.0 # weight everything as 1 unless specified otherwise - linear with one model weighted at 1 is a no-op like passthrough
slices:
- sources:
- model: openchat/openchat-3.5-0106
layer_range: [0, 1]
- model: teknium/OpenHermes-2.5-Mistral-7B
layer_range: [0, 1]
parameters:
weight: 0
- sources:
- model: bardsai/jaskier-7b-dpo-v6.1
layer_range: [1, 10]
- sources:
- model: senseable/WestLake-7B-v2
layer_range: [10, 20]
- sources:
- model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
layer_range: [20, 30]
- sources:
- model: paulml/OGNO-7B
layer_range: [15, 25]
- sources:
- model: paulml/DPOB-INMTOB-7B
layer_range: [22, 32]
- sources:
- model: mlabonne/AlphaMonarch-7B
layer_range: [5, 15]
- sources:
- model: openchat/openchat-3.5-0106
layer_range: [31, 32]
- model: teknium/OpenHermes-2.5-Mistral-7B
layer_range: [31, 32]
parameters:
weight: 0
dtype: float16
tokenizer_source: model:openchat/openchat-3.5-0106
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mayacinka/djinn"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])