初始化项目，由ModelHub XC社区提供模型
Model: Goekdeniz-Guelmez/J.O.S.I.E.3-Beta4-slerp Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
452
README.md
Normal file
452
README.md
Normal file
@@ -0,0 +1,452 @@
|
||||
---
|
||||
tags:
|
||||
- merge
|
||||
- mergekit
|
||||
- lazymergekit
|
||||
- Weyaxi/Einstein-v4-7B
|
||||
- cognitivecomputations/dolphin-2.8-experiment26-7b
|
||||
base_model:
|
||||
- Weyaxi/Einstein-v4-7B
|
||||
- cognitivecomputations/dolphin-2.8-experiment26-7b
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
# JOSIE_Beta-4-7B-slerp
|
||||
|
||||
JOSIE_Beta-4-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
||||
* [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
|
||||
* [cognitivecomputations/dolphin-2.8-experiment26-7b](https://huggingface.co/cognitivecomputations/dolphin-2.8-experiment26-7b)
|
||||
|
||||
# IMPORTANT!!!
|
||||
|
||||
Upon seeing the eval results on the LLM Leaderboard, this is my second best performing model, the best one it beta 3.
|
||||
|
||||
```json
|
||||
{
|
||||
"all": {
|
||||
"acc": 0.6395082113582112,
|
||||
"acc_stderr": 0.0321581453772247,
|
||||
"acc_norm": 0.6406802207782241,
|
||||
"acc_norm_stderr": 0.032807499003593296,
|
||||
"mc1": 0.379436964504284,
|
||||
"mc1_stderr": 0.01698703926614299,
|
||||
"mc2": 0.5593281467190233,
|
||||
"mc2_stderr": 0.0156123862411416
|
||||
},
|
||||
"harness|arc:challenge|25": {
|
||||
"acc": 0.6143344709897611,
|
||||
"acc_stderr": 0.014224250973257182,
|
||||
"acc_norm": 0.6356655290102389,
|
||||
"acc_norm_stderr": 0.014063260279882419
|
||||
},
|
||||
"harness|hellaswag|10": {
|
||||
"acc": 0.6618203545110536,
|
||||
"acc_stderr": 0.004721231637092722,
|
||||
"acc_norm": 0.8409679346743677,
|
||||
"acc_norm_stderr": 0.0036495858528211842
|
||||
},
|
||||
"harness|hendrycksTest-abstract_algebra|5": {
|
||||
"acc": 0.34,
|
||||
"acc_stderr": 0.047609522856952365,
|
||||
"acc_norm": 0.34,
|
||||
"acc_norm_stderr": 0.047609522856952365
|
||||
},
|
||||
"harness|hendrycksTest-anatomy|5": {
|
||||
"acc": 0.6,
|
||||
"acc_stderr": 0.04232073695151589,
|
||||
"acc_norm": 0.6,
|
||||
"acc_norm_stderr": 0.04232073695151589
|
||||
},
|
||||
"harness|hendrycksTest-astronomy|5": {
|
||||
"acc": 0.6973684210526315,
|
||||
"acc_stderr": 0.037385206761196686,
|
||||
"acc_norm": 0.6973684210526315,
|
||||
"acc_norm_stderr": 0.037385206761196686
|
||||
},
|
||||
"harness|hendrycksTest-business_ethics|5": {
|
||||
"acc": 0.6,
|
||||
"acc_stderr": 0.04923659639173309,
|
||||
"acc_norm": 0.6,
|
||||
"acc_norm_stderr": 0.04923659639173309
|
||||
},
|
||||
"harness|hendrycksTest-clinical_knowledge|5": {
|
||||
"acc": 0.6943396226415094,
|
||||
"acc_stderr": 0.028353298073322666,
|
||||
"acc_norm": 0.6943396226415094,
|
||||
"acc_norm_stderr": 0.028353298073322666
|
||||
},
|
||||
"harness|hendrycksTest-college_biology|5": {
|
||||
"acc": 0.7638888888888888,
|
||||
"acc_stderr": 0.03551446610810826,
|
||||
"acc_norm": 0.7638888888888888,
|
||||
"acc_norm_stderr": 0.03551446610810826
|
||||
},
|
||||
"harness|hendrycksTest-college_chemistry|5": {
|
||||
"acc": 0.46,
|
||||
"acc_stderr": 0.05009082659620333,
|
||||
"acc_norm": 0.46,
|
||||
"acc_norm_stderr": 0.05009082659620333
|
||||
},
|
||||
"harness|hendrycksTest-college_computer_science|5": {
|
||||
"acc": 0.52,
|
||||
"acc_stderr": 0.050211673156867795,
|
||||
"acc_norm": 0.52,
|
||||
"acc_norm_stderr": 0.050211673156867795
|
||||
},
|
||||
"harness|hendrycksTest-college_mathematics|5": {
|
||||
"acc": 0.32,
|
||||
"acc_stderr": 0.04688261722621504,
|
||||
"acc_norm": 0.32,
|
||||
"acc_norm_stderr": 0.04688261722621504
|
||||
},
|
||||
"harness|hendrycksTest-college_medicine|5": {
|
||||
"acc": 0.6705202312138728,
|
||||
"acc_stderr": 0.03583901754736412,
|
||||
"acc_norm": 0.6705202312138728,
|
||||
"acc_norm_stderr": 0.03583901754736412
|
||||
},
|
||||
"harness|hendrycksTest-college_physics|5": {
|
||||
"acc": 0.3627450980392157,
|
||||
"acc_stderr": 0.04784060704105654,
|
||||
"acc_norm": 0.3627450980392157,
|
||||
"acc_norm_stderr": 0.04784060704105654
|
||||
},
|
||||
"harness|hendrycksTest-computer_security|5": {
|
||||
"acc": 0.75,
|
||||
"acc_stderr": 0.04351941398892446,
|
||||
"acc_norm": 0.75,
|
||||
"acc_norm_stderr": 0.04351941398892446
|
||||
},
|
||||
"harness|hendrycksTest-conceptual_physics|5": {
|
||||
"acc": 0.5574468085106383,
|
||||
"acc_stderr": 0.03246956919789958,
|
||||
"acc_norm": 0.5574468085106383,
|
||||
"acc_norm_stderr": 0.03246956919789958
|
||||
},
|
||||
"harness|hendrycksTest-econometrics|5": {
|
||||
"acc": 0.4473684210526316,
|
||||
"acc_stderr": 0.04677473004491199,
|
||||
"acc_norm": 0.4473684210526316,
|
||||
"acc_norm_stderr": 0.04677473004491199
|
||||
},
|
||||
"harness|hendrycksTest-electrical_engineering|5": {
|
||||
"acc": 0.5586206896551724,
|
||||
"acc_stderr": 0.04137931034482758,
|
||||
"acc_norm": 0.5586206896551724,
|
||||
"acc_norm_stderr": 0.04137931034482758
|
||||
},
|
||||
"harness|hendrycksTest-elementary_mathematics|5": {
|
||||
"acc": 0.41005291005291006,
|
||||
"acc_stderr": 0.025331202438944444,
|
||||
"acc_norm": 0.41005291005291006,
|
||||
"acc_norm_stderr": 0.025331202438944444
|
||||
},
|
||||
"harness|hendrycksTest-formal_logic|5": {
|
||||
"acc": 0.42857142857142855,
|
||||
"acc_stderr": 0.0442626668137991,
|
||||
"acc_norm": 0.42857142857142855,
|
||||
"acc_norm_stderr": 0.0442626668137991
|
||||
},
|
||||
"harness|hendrycksTest-global_facts|5": {
|
||||
"acc": 0.34,
|
||||
"acc_stderr": 0.04760952285695235,
|
||||
"acc_norm": 0.34,
|
||||
"acc_norm_stderr": 0.04760952285695235
|
||||
},
|
||||
"harness|hendrycksTest-high_school_biology|5": {
|
||||
"acc": 0.7709677419354839,
|
||||
"acc_stderr": 0.023904914311782648,
|
||||
"acc_norm": 0.7709677419354839,
|
||||
"acc_norm_stderr": 0.023904914311782648
|
||||
},
|
||||
"harness|hendrycksTest-high_school_chemistry|5": {
|
||||
"acc": 0.5073891625615764,
|
||||
"acc_stderr": 0.035176035403610105,
|
||||
"acc_norm": 0.5073891625615764,
|
||||
"acc_norm_stderr": 0.035176035403610105
|
||||
},
|
||||
"harness|hendrycksTest-high_school_computer_science|5": {
|
||||
"acc": 0.69,
|
||||
"acc_stderr": 0.04648231987117316,
|
||||
"acc_norm": 0.69,
|
||||
"acc_norm_stderr": 0.04648231987117316
|
||||
},
|
||||
"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": 0.8080808080808081,
|
||||
"acc_stderr": 0.028057791672989017,
|
||||
"acc_norm": 0.8080808080808081,
|
||||
"acc_norm_stderr": 0.028057791672989017
|
||||
},
|
||||
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
||||
"acc": 0.8963730569948186,
|
||||
"acc_stderr": 0.02199531196364424,
|
||||
"acc_norm": 0.8963730569948186,
|
||||
"acc_norm_stderr": 0.02199531196364424
|
||||
},
|
||||
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
||||
"acc": 0.6435897435897436,
|
||||
"acc_stderr": 0.02428314052946731,
|
||||
"acc_norm": 0.6435897435897436,
|
||||
"acc_norm_stderr": 0.02428314052946731
|
||||
},
|
||||
"harness|hendrycksTest-high_school_mathematics|5": {
|
||||
"acc": 0.32592592592592595,
|
||||
"acc_stderr": 0.028578348365473072,
|
||||
"acc_norm": 0.32592592592592595,
|
||||
"acc_norm_stderr": 0.028578348365473072
|
||||
},
|
||||
"harness|hendrycksTest-high_school_microeconomics|5": {
|
||||
"acc": 0.6764705882352942,
|
||||
"acc_stderr": 0.030388353551886797,
|
||||
"acc_norm": 0.6764705882352942,
|
||||
"acc_norm_stderr": 0.030388353551886797
|
||||
},
|
||||
"harness|hendrycksTest-high_school_physics|5": {
|
||||
"acc": 0.3576158940397351,
|
||||
"acc_stderr": 0.03913453431177258,
|
||||
"acc_norm": 0.3576158940397351,
|
||||
"acc_norm_stderr": 0.03913453431177258
|
||||
},
|
||||
"harness|hendrycksTest-high_school_psychology|5": {
|
||||
"acc": 0.8440366972477065,
|
||||
"acc_stderr": 0.015555802713590167,
|
||||
"acc_norm": 0.8440366972477065,
|
||||
"acc_norm_stderr": 0.015555802713590167
|
||||
},
|
||||
"harness|hendrycksTest-high_school_statistics|5": {
|
||||
"acc": 0.5324074074074074,
|
||||
"acc_stderr": 0.03402801581358966,
|
||||
"acc_norm": 0.5324074074074074,
|
||||
"acc_norm_stderr": 0.03402801581358966
|
||||
},
|
||||
"harness|hendrycksTest-high_school_us_history|5": {
|
||||
"acc": 0.803921568627451,
|
||||
"acc_stderr": 0.027865942286639318,
|
||||
"acc_norm": 0.803921568627451,
|
||||
"acc_norm_stderr": 0.027865942286639318
|
||||
},
|
||||
"harness|hendrycksTest-high_school_world_history|5": {
|
||||
"acc": 0.7932489451476793,
|
||||
"acc_stderr": 0.0263616516683891,
|
||||
"acc_norm": 0.7932489451476793,
|
||||
"acc_norm_stderr": 0.0263616516683891
|
||||
},
|
||||
"harness|hendrycksTest-human_aging|5": {
|
||||
"acc": 0.6905829596412556,
|
||||
"acc_stderr": 0.03102441174057221,
|
||||
"acc_norm": 0.6905829596412556,
|
||||
"acc_norm_stderr": 0.03102441174057221
|
||||
},
|
||||
"harness|hendrycksTest-human_sexuality|5": {
|
||||
"acc": 0.7938931297709924,
|
||||
"acc_stderr": 0.035477710041594654,
|
||||
"acc_norm": 0.7938931297709924,
|
||||
"acc_norm_stderr": 0.035477710041594654
|
||||
},
|
||||
"harness|hendrycksTest-international_law|5": {
|
||||
"acc": 0.7851239669421488,
|
||||
"acc_stderr": 0.03749492448709696,
|
||||
"acc_norm": 0.7851239669421488,
|
||||
"acc_norm_stderr": 0.03749492448709696
|
||||
},
|
||||
"harness|hendrycksTest-jurisprudence|5": {
|
||||
"acc": 0.8240740740740741,
|
||||
"acc_stderr": 0.036809181416738807,
|
||||
"acc_norm": 0.8240740740740741,
|
||||
"acc_norm_stderr": 0.036809181416738807
|
||||
},
|
||||
"harness|hendrycksTest-logical_fallacies|5": {
|
||||
"acc": 0.7239263803680982,
|
||||
"acc_stderr": 0.035123852837050475,
|
||||
"acc_norm": 0.7239263803680982,
|
||||
"acc_norm_stderr": 0.035123852837050475
|
||||
},
|
||||
"harness|hendrycksTest-machine_learning|5": {
|
||||
"acc": 0.44642857142857145,
|
||||
"acc_stderr": 0.04718471485219588,
|
||||
"acc_norm": 0.44642857142857145,
|
||||
"acc_norm_stderr": 0.04718471485219588
|
||||
},
|
||||
"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": 0.8760683760683761,
|
||||
"acc_stderr": 0.021586494001281376,
|
||||
"acc_norm": 0.8760683760683761,
|
||||
"acc_norm_stderr": 0.021586494001281376
|
||||
},
|
||||
"harness|hendrycksTest-medical_genetics|5": {
|
||||
"acc": 0.73,
|
||||
"acc_stderr": 0.044619604333847394,
|
||||
"acc_norm": 0.73,
|
||||
"acc_norm_stderr": 0.044619604333847394
|
||||
},
|
||||
"harness|hendrycksTest-miscellaneous|5": {
|
||||
"acc": 0.8212005108556832,
|
||||
"acc_stderr": 0.01370264371536898,
|
||||
"acc_norm": 0.8212005108556832,
|
||||
"acc_norm_stderr": 0.01370264371536898
|
||||
},
|
||||
"harness|hendrycksTest-moral_disputes|5": {
|
||||
"acc": 0.7167630057803468,
|
||||
"acc_stderr": 0.024257901705323374,
|
||||
"acc_norm": 0.7167630057803468,
|
||||
"acc_norm_stderr": 0.024257901705323374
|
||||
},
|
||||
"harness|hendrycksTest-moral_scenarios|5": {
|
||||
"acc": 0.2759776536312849,
|
||||
"acc_stderr": 0.014950103002475356,
|
||||
"acc_norm": 0.2759776536312849,
|
||||
"acc_norm_stderr": 0.014950103002475356
|
||||
},
|
||||
"harness|hendrycksTest-nutrition|5": {
|
||||
"acc": 0.7189542483660131,
|
||||
"acc_stderr": 0.02573885479781873,
|
||||
"acc_norm": 0.7189542483660131,
|
||||
"acc_norm_stderr": 0.02573885479781873
|
||||
},
|
||||
"harness|hendrycksTest-philosophy|5": {
|
||||
"acc": 0.7202572347266881,
|
||||
"acc_stderr": 0.02549425935069491,
|
||||
"acc_norm": 0.7202572347266881,
|
||||
"acc_norm_stderr": 0.02549425935069491
|
||||
},
|
||||
"harness|hendrycksTest-prehistory|5": {
|
||||
"acc": 0.7314814814814815,
|
||||
"acc_stderr": 0.024659685185967284,
|
||||
"acc_norm": 0.7314814814814815,
|
||||
"acc_norm_stderr": 0.024659685185967284
|
||||
},
|
||||
"harness|hendrycksTest-professional_accounting|5": {
|
||||
"acc": 0.475177304964539,
|
||||
"acc_stderr": 0.02979071924382972,
|
||||
"acc_norm": 0.475177304964539,
|
||||
"acc_norm_stderr": 0.02979071924382972
|
||||
},
|
||||
"harness|hendrycksTest-professional_law|5": {
|
||||
"acc": 0.4621903520208605,
|
||||
"acc_stderr": 0.012733671880342504,
|
||||
"acc_norm": 0.4621903520208605,
|
||||
"acc_norm_stderr": 0.012733671880342504
|
||||
},
|
||||
"harness|hendrycksTest-professional_medicine|5": {
|
||||
"acc": 0.6691176470588235,
|
||||
"acc_stderr": 0.028582709753898445,
|
||||
"acc_norm": 0.6691176470588235,
|
||||
"acc_norm_stderr": 0.028582709753898445
|
||||
},
|
||||
"harness|hendrycksTest-professional_psychology|5": {
|
||||
"acc": 0.6535947712418301,
|
||||
"acc_stderr": 0.01924978569171721,
|
||||
"acc_norm": 0.6535947712418301,
|
||||
"acc_norm_stderr": 0.01924978569171721
|
||||
},
|
||||
"harness|hendrycksTest-public_relations|5": {
|
||||
"acc": 0.6636363636363637,
|
||||
"acc_stderr": 0.04525393596302506,
|
||||
"acc_norm": 0.6636363636363637,
|
||||
"acc_norm_stderr": 0.04525393596302506
|
||||
},
|
||||
"harness|hendrycksTest-security_studies|5": {
|
||||
"acc": 0.7428571428571429,
|
||||
"acc_stderr": 0.027979823538744546,
|
||||
"acc_norm": 0.7428571428571429,
|
||||
"acc_norm_stderr": 0.027979823538744546
|
||||
},
|
||||
"harness|hendrycksTest-sociology|5": {
|
||||
"acc": 0.835820895522388,
|
||||
"acc_stderr": 0.026193923544454125,
|
||||
"acc_norm": 0.835820895522388,
|
||||
"acc_norm_stderr": 0.026193923544454125
|
||||
},
|
||||
"harness|hendrycksTest-us_foreign_policy|5": {
|
||||
"acc": 0.87,
|
||||
"acc_stderr": 0.033799766898963086,
|
||||
"acc_norm": 0.87,
|
||||
"acc_norm_stderr": 0.033799766898963086
|
||||
},
|
||||
"harness|hendrycksTest-virology|5": {
|
||||
"acc": 0.5481927710843374,
|
||||
"acc_stderr": 0.03874371556587953,
|
||||
"acc_norm": 0.5481927710843374,
|
||||
"acc_norm_stderr": 0.03874371556587953
|
||||
},
|
||||
"harness|hendrycksTest-world_religions|5": {
|
||||
"acc": 0.8187134502923976,
|
||||
"acc_stderr": 0.029547741687640038,
|
||||
"acc_norm": 0.8187134502923976,
|
||||
"acc_norm_stderr": 0.029547741687640038
|
||||
},
|
||||
"harness|truthfulqa:mc|0": {
|
||||
"mc1": 0.379436964504284,
|
||||
"mc1_stderr": 0.01698703926614299,
|
||||
"mc2": 0.5593281467190233,
|
||||
"mc2_stderr": 0.0156123862411416
|
||||
},
|
||||
"harness|winogrande|5": {
|
||||
"acc": 0.7932123125493291,
|
||||
"acc_stderr": 0.011382566829235803
|
||||
},
|
||||
"harness|gsm8k|5": {
|
||||
"acc": 0.6171341925701289,
|
||||
"acc_stderr": 0.013389223491820474
|
||||
}
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
## 🧩 Configuration
|
||||
|
||||
```yaml
|
||||
slices:
|
||||
- sources:
|
||||
- model: Weyaxi/Einstein-v4-7B
|
||||
layer_range: [0, 32]
|
||||
- model: cognitivecomputations/dolphin-2.8-experiment26-7b
|
||||
layer_range: [0, 32]
|
||||
merge_method: slerp
|
||||
base_model: Weyaxi/Einstein-v4-7B
|
||||
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/JOSIE_Beta-4-7B-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"])
|
||||
```
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<|im_end|>": 32000,
|
||||
"<|im_start|>": 32001
|
||||
}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "Weyaxi/Einstein-v4-7B",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 32000,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.38.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32002
|
||||
}
|
||||
17
mergekit_config.yml
Normal file
17
mergekit_config.yml
Normal file
@@ -0,0 +1,17 @@
|
||||
|
||||
slices:
|
||||
- sources:
|
||||
- model: Weyaxi/Einstein-v4-7B
|
||||
layer_range: [0, 32]
|
||||
- model: cognitivecomputations/dolphin-2.8-experiment26-7b
|
||||
layer_range: [0, 32]
|
||||
merge_method: slerp
|
||||
base_model: Weyaxi/Einstein-v4-7B
|
||||
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
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f5df75983cdcc90a28ce45ae60d6ea74f8c6a7b7ddcb77ee21916e1d508177c3
|
||||
size 9942998080
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:819021d1a59fd64a01a5c7ab8cfd3c17157916763da499133357fd7bf2fcf7ce
|
||||
size 4540532728
|
||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91140
tokenizer.json
Normal file
91140
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
62
tokenizer_config.json
Normal file
62
tokenizer_config.json
Normal file
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": true,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32000": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"trust_remote_code": false,
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user