File size: 12,370 Bytes
e1a49da ee5cb91 e1a49da ee5cb91 e1a49da 8514082 e1a49da 3491610 e1a49da 0818c0f e1a49da 4176e65 e1a49da e47f269 e1a49da 3491610 e1a49da ee5cb91 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 |
---
license: apache-2.0
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
model-index:
- name: chatty-djinn-14B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 70.39
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 86.45
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 64.4
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 67.57
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 83.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 60.58
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
name: Open LLM Leaderboard
---
# djinn
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
# 🏆 Benchmarks
Nous benchmarks, find more [details here](https://gist.github.com/majacinka/3f2a797c8872ca9bfdaa2bbf3369edb5)
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|---------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[chatty-djinn-14B](https://huggingface.co/mayacinka/chatty-djinn-14B)| 38.43| 76.29| 68.02| 47.6| 57.59|
### AGIEval
| Task |Version| Metric |Value| |Stderr|
|------------------------------|------:|--------|----:|---|-----:|
|agieval_aqua_rat | 0|acc |23.62|± | 2.67|
| | |acc_norm|21.65|± | 2.59|
|agieval_logiqa_en | 0|acc |32.26|± | 1.83|
| | |acc_norm|33.79|± | 1.86|
|agieval_lsat_ar | 0|acc |23.04|± | 2.78|
| | |acc_norm|23.04|± | 2.78|
|agieval_lsat_lr | 0|acc |38.82|± | 2.16|
| | |acc_norm|39.22|± | 2.16|
|agieval_lsat_rc | 0|acc |59.48|± | 3.00|
| | |acc_norm|54.65|± | 3.04|
|agieval_sat_en | 0|acc |75.73|± | 2.99|
| | |acc_norm|74.27|± | 3.05|
|agieval_sat_en_without_passage| 0|acc |35.92|± | 3.35|
| | |acc_norm|34.47|± | 3.32|
|agieval_sat_math | 0|acc |31.36|± | 3.14|
| | |acc_norm|26.36|± | 2.98|
Average: 38.43%
### GPT4All
| Task |Version| Metric |Value| |Stderr|
|-------------|------:|--------|----:|---|-----:|
|arc_challenge| 0|acc |62.12|± | 1.42|
| | |acc_norm|65.44|± | 1.39|
|arc_easy | 0|acc |83.88|± | 0.75|
| | |acc_norm|78.58|± | 0.84|
|boolq | 1|acc |88.07|± | 0.57|
|hellaswag | 0|acc |65.18|± | 0.48|
| | |acc_norm|86.45|± | 0.34|
|openbookqa | 0|acc |39.60|± | 2.19|
| | |acc_norm|48.60|± | 2.24|
|piqa | 0|acc |82.26|± | 0.89|
| | |acc_norm|83.62|± | 0.86|
|winogrande | 0|acc |83.27|± | 1.05|
Average: 76.29%
### TruthfulQA
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |50.55|± | 1.75|
| | |mc2 |68.02|± | 1.52|
Average: 68.02%
### Bigbench
| Task |Version| Metric |Value| |Stderr|
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|57.89|± | 3.59|
|bigbench_date_understanding | 0|multiple_choice_grade|64.50|± | 2.49|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|32.56|± | 2.92|
|bigbench_geometric_shapes | 0|multiple_choice_grade|26.18|± | 2.32|
| | |exact_str_match | 1.11|± | 0.55|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|30.80|± | 2.07|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|22.86|± | 1.59|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|57.67|± | 2.86|
|bigbench_movie_recommendation | 0|multiple_choice_grade|62.00|± | 2.17|
|bigbench_navigate | 0|multiple_choice_grade|56.20|± | 1.57|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|65.65|± | 1.06|
|bigbench_ruin_names | 0|multiple_choice_grade|64.73|± | 2.26|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|17.33|± | 1.20|
|bigbench_snarks | 0|multiple_choice_grade|76.24|± | 3.17|
|bigbench_sports_understanding | 0|multiple_choice_grade|75.15|± | 1.38|
|bigbench_temporal_sequences | 0|multiple_choice_grade|48.90|± | 1.58|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|22.32|± | 1.18|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|18.17|± | 0.92|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|57.67|± | 2.86|
Average: 47.6%
Average score: 57.59%
## 🧩 Configuration
Inspired by [theprofessor's config](https://huggingface.co/abacusai/TheProfessor-155b)
```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"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mayacinka__chatty-djinn-14B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |72.08|
|AI2 Reasoning Challenge (25-Shot)|70.39|
|HellaSwag (10-Shot) |86.45|
|MMLU (5-Shot) |64.40|
|TruthfulQA (0-shot) |67.57|
|Winogrande (5-shot) |83.11|
|GSM8k (5-shot) |60.58|
|