File size: 4,396 Bytes
e1a49da 8514082 e1a49da 3491610 e1a49da 0818c0f e1a49da 3491610 e1a49da |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
---
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 will chat for an unpleasantly long time in the most convoluted possible way
✔︎ It will pick strangest way to say very simple things
✔︎ Excellent model if you want to feel overwhelmed
✔︎ Verbosity taken to a new level
djinn is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
* bardsai/jaskier-7b-dpo-v6.1
* senseable/WestLake-7B-v2
* NousResearch/Nous-Hermes-2-Mistral-7B-DPO
* paulml/OGNO-7B
* paulml/DPOB-INMTOB-7B
* mlabonne/AlphaMonarch-7B
## 🧩 Configuration
```yaml
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
```
## An example
*User:* Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?
Think step by step and the result MUST BE A NUMBER
*djinn:*
In this family structure, we know there are 4 aka '1 + 3-brothers' (1 being initially for Sally) existing individuals who are
also the siblings of the 3-brother-group. As each of the 3-brothers has 2-sisters each, that sums up to 6 total sister- roles. Since
we already accounted for one of the sisters (assuming to be the oldest or in alphabetical order, as names were not given) to be part
of the 3-brother group, we subtract one from the 6-sisters total. So, considering the provided information, Sally would have 6 - 1 = 5
remaining younger or alphabetically-wise- placed, biological-sisters. However, note that this problem statement might not perfectly align
with real-life complexities, such as same-sex twins, adoption, etc., but within the given context, the solution is 5.
Remember, in more intricate or unclear family tree scenarios, it'd be best to directly ask for clarifications or consider additional data
points. In short, with the given constraints, Sally has 5 known, direct, biological, and likely-in-age-order, younger/alphabetically-placed,
sister-siblings.(To reiterate the core result in a concise manner: 5).
(Please excuse the verbosity, aiming for thoroughness and clarity.)
This response maintains the initial request's numerical focus while providing a detailed explanation to ensure understanding.
## 💻 Usage
```python
!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"])
``` |