Isaak-Carter's picture
Update README.md
1417e01 verified
---
tags:
- merge
- mergekit
- lazymergekit
- Weyaxi/Einstein-v6-7B
- argilla/CapybaraHermes-2.5-Mistral-7B
base_model:
- Weyaxi/Einstein-v6-7B
- argilla/CapybaraHermes-2.5-Mistral-7B
license: apache-2.0
language:
- en
- de
- es
- fr
- ja
- zh
---
# J.O.S.I.E.3-Beta12-7B-slerp
J.O.S.I.E.3-Beta12-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Weyaxi/Einstein-v6-7B](https://huggingface.co/Weyaxi/Einstein-v6-7B)
* [argilla/CapybaraHermes-2.5-Mistral-7B](https://huggingface.co/argilla/CapybaraHermes-2.5-Mistral-7B)
This model has been further Finetuned on my custom J.O.S.I.E.v3.11 Dataset, in the ChatML prompt Format.
[-- GGUF Quants --](https://huggingface.co/Isaak-Carter/J.O.S.I.E.3-Beta12-7B-slerp-gguf)
```text
<|im_start|>system
You are JOSIE, my private and superinteligent AI Assistant.<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
{{ .Response }}<|im_end|>
```
#### Run in ollama:
```sh
ollama run goekdenizguelmez/j.o.s.i.e.v3-beta12.1
```
Only q4-k-m for now!
## 🧩 Configuration
```yaml
slices:
- sources:
- model: Weyaxi/Einstein-v6-7B
layer_range: [0, 32]
- model: argilla/CapybaraHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: argilla/CapybaraHermes-2.5-Mistral-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Isaak-Carter/J.O.S.I.E.3-Beta12-7B-slerp"
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"])
```
# Evaluation results:
```json
{
"all": {
"acc": 0.635008846776534,
"acc_stderr": 0.03244450973873997,
"acc_norm": 0.6365238167399629,
"acc_norm_stderr": 0.033101612504829854,
"mc1": 0.397796817625459,
"mc1_stderr": 0.017133934248559635,
"mc2": 0.5816259277988214,
"mc2_stderr": 0.01521267822060948
},
"harness|arc:challenge|25": {
"acc": 0.6220136518771331,
"acc_stderr": 0.0141696645203031,
"acc_norm": 0.6459044368600683,
"acc_norm_stderr": 0.013975454122756557
},
"harness|hellaswag|10": {
"acc": 0.6512646883091018,
"acc_stderr": 0.004755960559929163,
"acc_norm": 0.8397729535949015,
"acc_norm_stderr": 0.003660668242740655
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.4,
"acc_stderr": 0.04923659639173309,
"acc_norm": 0.4,
"acc_norm_stderr": 0.04923659639173309
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.5703703703703704,
"acc_stderr": 0.042763494943765995,
"acc_norm": 0.5703703703703704,
"acc_norm_stderr": 0.042763494943765995
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.6842105263157895,
"acc_stderr": 0.0378272898086547,
"acc_norm": 0.6842105263157895,
"acc_norm_stderr": 0.0378272898086547
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.58,
"acc_stderr": 0.049604496374885836,
"acc_norm": 0.58,
"acc_norm_stderr": 0.049604496374885836
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.6792452830188679,
"acc_stderr": 0.028727502957880267,
"acc_norm": 0.6792452830188679,
"acc_norm_stderr": 0.028727502957880267
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7361111111111112,
"acc_stderr": 0.03685651095897532,
"acc_norm": 0.7361111111111112,
"acc_norm_stderr": 0.03685651095897532
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.54,
"acc_stderr": 0.05009082659620332,
"acc_norm": 0.54,
"acc_norm_stderr": 0.05009082659620332
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.51,
"acc_stderr": 0.05024183937956912,
"acc_norm": 0.51,
"acc_norm_stderr": 0.05024183937956912
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.29,
"acc_stderr": 0.04560480215720684,
"acc_norm": 0.29,
"acc_norm_stderr": 0.04560480215720684
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6416184971098265,
"acc_stderr": 0.036563436533531585,
"acc_norm": 0.6416184971098265,
"acc_norm_stderr": 0.036563436533531585
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.3235294117647059,
"acc_stderr": 0.04655010411319619,
"acc_norm": 0.3235294117647059,
"acc_norm_stderr": 0.04655010411319619
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.76,
"acc_stderr": 0.04292346959909283,
"acc_norm": 0.76,
"acc_norm_stderr": 0.04292346959909283
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5829787234042553,
"acc_stderr": 0.03223276266711712,
"acc_norm": 0.5829787234042553,
"acc_norm_stderr": 0.03223276266711712
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.4649122807017544,
"acc_stderr": 0.046920083813689104,
"acc_norm": 0.4649122807017544,
"acc_norm_stderr": 0.046920083813689104
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5517241379310345,
"acc_stderr": 0.04144311810878152,
"acc_norm": 0.5517241379310345,
"acc_norm_stderr": 0.04144311810878152
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.42063492063492064,
"acc_stderr": 0.025424835086924006,
"acc_norm": 0.42063492063492064,
"acc_norm_stderr": 0.025424835086924006
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.4444444444444444,
"acc_stderr": 0.044444444444444495,
"acc_norm": 0.4444444444444444,
"acc_norm_stderr": 0.044444444444444495
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.44,
"acc_stderr": 0.04988876515698589,
"acc_norm": 0.44,
"acc_norm_stderr": 0.04988876515698589
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7548387096774194,
"acc_stderr": 0.024472243840895525,
"acc_norm": 0.7548387096774194,
"acc_norm_stderr": 0.024472243840895525
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.5024630541871922,
"acc_stderr": 0.035179450386910616,
"acc_norm": 0.5024630541871922,
"acc_norm_stderr": 0.035179450386910616
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.66,
"acc_stderr": 0.04760952285695237,
"acc_norm": 0.66,
"acc_norm_stderr": 0.04760952285695237
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7818181818181819,
"acc_stderr": 0.03225078108306289,
"acc_norm": 0.7818181818181819,
"acc_norm_stderr": 0.03225078108306289
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.797979797979798,
"acc_stderr": 0.02860620428922988,
"acc_norm": 0.797979797979798,
"acc_norm_stderr": 0.02860620428922988
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.8756476683937824,
"acc_stderr": 0.023814477086593552,
"acc_norm": 0.8756476683937824,
"acc_norm_stderr": 0.023814477086593552
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.658974358974359,
"acc_stderr": 0.02403548967633509,
"acc_norm": 0.658974358974359,
"acc_norm_stderr": 0.02403548967633509
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.32592592592592595,
"acc_stderr": 0.02857834836547308,
"acc_norm": 0.32592592592592595,
"acc_norm_stderr": 0.02857834836547308
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6638655462184874,
"acc_stderr": 0.030684737115135363,
"acc_norm": 0.6638655462184874,
"acc_norm_stderr": 0.030684737115135363
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.304635761589404,
"acc_stderr": 0.03757949922943344,
"acc_norm": 0.304635761589404,
"acc_norm_stderr": 0.03757949922943344
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8238532110091743,
"acc_stderr": 0.016332882393431353,
"acc_norm": 0.8238532110091743,
"acc_norm_stderr": 0.016332882393431353
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5092592592592593,
"acc_stderr": 0.03409386946992699,
"acc_norm": 0.5092592592592593,
"acc_norm_stderr": 0.03409386946992699
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.7990196078431373,
"acc_stderr": 0.02812597226565437,
"acc_norm": 0.7990196078431373,
"acc_norm_stderr": 0.02812597226565437
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.759493670886076,
"acc_stderr": 0.027820781981149685,
"acc_norm": 0.759493670886076,
"acc_norm_stderr": 0.027820781981149685
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6681614349775785,
"acc_stderr": 0.03160295143776679,
"acc_norm": 0.6681614349775785,
"acc_norm_stderr": 0.03160295143776679
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7404580152671756,
"acc_stderr": 0.03844876139785271,
"acc_norm": 0.7404580152671756,
"acc_norm_stderr": 0.03844876139785271
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.8016528925619835,
"acc_stderr": 0.036401182719909456,
"acc_norm": 0.8016528925619835,
"acc_norm_stderr": 0.036401182719909456
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.7777777777777778,
"acc_stderr": 0.040191074725573483,
"acc_norm": 0.7777777777777778,
"acc_norm_stderr": 0.040191074725573483
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.754601226993865,
"acc_stderr": 0.03380939813943354,
"acc_norm": 0.754601226993865,
"acc_norm_stderr": 0.03380939813943354
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.4732142857142857,
"acc_stderr": 0.047389751192741546,
"acc_norm": 0.4732142857142857,
"acc_norm_stderr": 0.047389751192741546
},
"harness|hendrycksTest-management|5": {
"acc": 0.7766990291262136,
"acc_stderr": 0.04123553189891431,
"acc_norm": 0.7766990291262136,
"acc_norm_stderr": 0.04123553189891431
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8632478632478633,
"acc_stderr": 0.022509033937077802,
"acc_norm": 0.8632478632478633,
"acc_norm_stderr": 0.022509033937077802
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.69,
"acc_stderr": 0.04648231987117316,
"acc_norm": 0.69,
"acc_norm_stderr": 0.04648231987117316
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8173690932311622,
"acc_stderr": 0.013816335389973141,
"acc_norm": 0.8173690932311622,
"acc_norm_stderr": 0.013816335389973141
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7254335260115607,
"acc_stderr": 0.02402774515526502,
"acc_norm": 0.7254335260115607,
"acc_norm_stderr": 0.02402774515526502
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.27039106145251396,
"acc_stderr": 0.014854993938010071,
"acc_norm": 0.27039106145251396,
"acc_norm_stderr": 0.014854993938010071
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7516339869281046,
"acc_stderr": 0.02473998135511359,
"acc_norm": 0.7516339869281046,
"acc_norm_stderr": 0.02473998135511359
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7331189710610932,
"acc_stderr": 0.025122637608816653,
"acc_norm": 0.7331189710610932,
"acc_norm_stderr": 0.025122637608816653
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7222222222222222,
"acc_stderr": 0.024922001168886324,
"acc_norm": 0.7222222222222222,
"acc_norm_stderr": 0.024922001168886324
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.46099290780141844,
"acc_stderr": 0.02973659252642444,
"acc_norm": 0.46099290780141844,
"acc_norm_stderr": 0.02973659252642444
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.4680573663624511,
"acc_stderr": 0.012744149704869647,
"acc_norm": 0.4680573663624511,
"acc_norm_stderr": 0.012744149704869647
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6801470588235294,
"acc_stderr": 0.02833295951403121,
"acc_norm": 0.6801470588235294,
"acc_norm_stderr": 0.02833295951403121
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6470588235294118,
"acc_stderr": 0.01933314202079716,
"acc_norm": 0.6470588235294118,
"acc_norm_stderr": 0.01933314202079716
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6727272727272727,
"acc_stderr": 0.0449429086625209,
"acc_norm": 0.6727272727272727,
"acc_norm_stderr": 0.0449429086625209
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.6816326530612244,
"acc_stderr": 0.029822533793982062,
"acc_norm": 0.6816326530612244,
"acc_norm_stderr": 0.029822533793982062
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8507462686567164,
"acc_stderr": 0.025196929874827072,
"acc_norm": 0.8507462686567164,
"acc_norm_stderr": 0.025196929874827072
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.85,
"acc_stderr": 0.035887028128263734,
"acc_norm": 0.85,
"acc_norm_stderr": 0.035887028128263734
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5180722891566265,
"acc_stderr": 0.03889951252827216,
"acc_norm": 0.5180722891566265,
"acc_norm_stderr": 0.03889951252827216
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8362573099415205,
"acc_stderr": 0.028380919596145866,
"acc_norm": 0.8362573099415205,
"acc_norm_stderr": 0.028380919596145866
},
"harness|truthfulqa:mc|0": {
"mc1": 0.397796817625459,
"mc1_stderr": 0.017133934248559635,
"mc2": 0.5816259277988214,
"mc2_stderr": 0.01521267822060948
},
"harness|winogrande|5": {
"acc": 0.7963693764798737,
"acc_stderr": 0.011317798781626913
},
"harness|gsm8k|5": {
"acc": 0.5966641394996209,
"acc_stderr": 0.013512654781814702
}
}
```