Hugging Face's logo

vidhirambhia
/
test-llama-math-coder

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
text-generation-inference
Inference Endpoints
Model card Files Community
Edit model card

mathcoder_8b_0.3_0.8_generated_ties_0.5_sparsity_15_samples-merged

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using meta-llama/Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: meta-llama/Llama-3.1-8B
dtype: bfloat16
merge_method: ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 32]
    model: meta-llama/Llama-3.1-8B
  - layer_range: [0, 32]
    model: MathGenie/MathCoder2-Llama-3-8B
    parameters:
      density:
      - value: 1.0
      weight:
      - filter: model.layers.0.self_attn.q_proj
        value: 0.34567118839365213
      - filter: model.layers.1.self_attn.q_proj
        value: 0.3194050175456974
      - filter: model.layers.2.self_attn.q_proj
        value: 0.35258471691195725
      - filter: model.layers.3.self_attn.q_proj
        value: 0.3345938301995496
      - filter: model.layers.4.self_attn.q_proj
        value: 0.30193788299376734
      - filter: model.layers.5.self_attn.q_proj
        value: 0.3173885717278584
      - filter: model.layers.6.self_attn.q_proj
        value: 0.3099251034410517
      - filter: model.layers.7.self_attn.q_proj
        value: 0.32521866652699943
      - filter: model.layers.8.self_attn.q_proj
        value: 0.3688734091028125
      - filter: model.layers.9.self_attn.q_proj
        value: 0.3703137275441261
      - filter: model.layers.10.self_attn.q_proj
        value: 0.31995495731419893
      - filter: model.layers.11.self_attn.q_proj
        value: 0.3247211019745456
      - filter: model.layers.12.self_attn.q_proj
        value: 0.31401037029277745
      - filter: model.layers.13.self_attn.q_proj
        value: 0.3123343633792489
      - filter: model.layers.14.self_attn.q_proj
        value: 0.30020950086419107
      - filter: model.layers.15.self_attn.q_proj
        value: 0.3220499659561096
      - filter: model.layers.16.self_attn.q_proj
        value: 0.3007856282407165
      - filter: model.layers.17.self_attn.q_proj
        value: 0.3021473838579584
      - filter: model.layers.18.self_attn.q_proj
        value: 0.3078562824071649
      - filter: model.layers.19.self_attn.q_proj
        value: 0.3117844236107474
      - filter: model.layers.20.self_attn.q_proj
        value: 0.3057088985492065
      - filter: model.layers.21.self_attn.q_proj
        value: 0.3555962918347038
      - filter: model.layers.22.self_attn.q_proj
        value: 0.3584245535012832
      - filter: model.layers.23.self_attn.q_proj
        value: 0.4073430052898968
      - filter: model.layers.24.self_attn.q_proj
        value: 0.451652438066307
      - filter: model.layers.25.self_attn.q_proj
        value: 0.47265489970146124
      - filter: model.layers.26.self_attn.q_proj
        value: 0.5172262085581103
      - filter: model.layers.27.self_attn.q_proj
        value: 0.5207091604252867
      - filter: model.layers.28.self_attn.q_proj
        value: 0.5678730424763002
      - filter: model.layers.29.self_attn.q_proj
        value: 0.5689467344052794
      - filter: model.layers.30.self_attn.q_proj
        value: 0.7031844131357041
      - filter: model.layers.31.self_attn.q_proj
        value: 0.5159692033729639
      - filter: model.layers.0.self_attn.k_proj
        value: 0.32548054260723824
      - filter: model.layers.1.self_attn.k_proj
        value: 0.32346409678939925
      - filter: model.layers.2.self_attn.k_proj
        value: 0.3201120829623422
      - filter: model.layers.3.self_attn.k_proj
        value: 0.30683496569423346
      - filter: model.layers.4.self_attn.k_proj
        value: 0.31762426020007334
      - filter: model.layers.5.self_attn.k_proj
        value: 0.30327345100298536
      - filter: model.layers.6.self_attn.k_proj
        value: 0.3263185460640025
      - filter: model.layers.7.self_attn.k_proj
        value: 0.3229665322369455
      - filter: model.layers.8.self_attn.k_proj
        value: 0.3647619546430629
      - filter: model.layers.9.self_attn.k_proj
        value: 0.3679830304300005
      - filter: model.layers.10.self_attn.k_proj
        value: 0.34794951029172994
      - filter: model.layers.11.self_attn.k_proj
        value: 0.3474519457392762
      - filter: model.layers.12.self_attn.k_proj
        value: 0.3480018855077777
      - filter: model.layers.13.self_attn.k_proj
        value: 0.38031739380924945
      - filter: model.layers.14.self_attn.k_proj
        value: 0.35365840884093647
      - filter: model.layers.15.self_attn.k_proj
        value: 0.35551772901063217
      - filter: model.layers.16.self_attn.k_proj
        value: 0.3715707327292725
      - filter: model.layers.17.self_attn.k_proj
        value: 0.3642382024825852
      - filter: model.layers.18.self_attn.k_proj
        value: 0.3526109045199811
      - filter: model.layers.19.self_attn.k_proj
        value: 0.3439428062640758
      - filter: model.layers.20.self_attn.k_proj
        value: 0.3556224794427277
      - filter: model.layers.21.self_attn.k_proj
        value: 0.390713874194731
      - filter: model.layers.22.self_attn.k_proj
        value: 0.38280521657151834
      - filter: model.layers.23.self_attn.k_proj
        value: 0.3970774629445346
      - filter: model.layers.24.self_attn.k_proj
        value: 0.4266170847954748
      - filter: model.layers.25.self_attn.k_proj
        value: 0.4180275493636411
      - filter: model.layers.26.self_attn.k_proj
        value: 0.4680196930812339
      - filter: model.layers.27.self_attn.k_proj
        value: 0.4603205363222123
      - filter: model.layers.28.self_attn.k_proj
        value: 0.49577855758655004
      - filter: model.layers.29.self_attn.k_proj
        value: 0.49716650081181585
      - filter: model.layers.30.self_attn.k_proj
        value: 0.610715969203373
      - filter: model.layers.31.self_attn.k_proj
        value: 0.46008484784999737
      - filter: model.layers.0.self_attn.v_proj
        value: 0.3039805164196302
      - filter: model.layers.1.self_attn.v_proj
        value: 0.31008222908919497
      - filter: model.layers.2.self_attn.v_proj
        value: 0.3261614204158592
      - filter: model.layers.3.self_attn.v_proj
        value: 0.34339286649557427
      - filter: model.layers.4.self_attn.v_proj
        value: 0.33574608495260044
      - filter: model.layers.5.self_attn.v_proj
        value: 0.3314251296286597
      - filter: model.layers.6.self_attn.v_proj
        value: 0.3357722725606243
      - filter: model.layers.7.self_attn.v_proj
        value: 0.3345938301995496
      - filter: model.layers.8.self_attn.v_proj
        value: 0.33404389043104804
      - filter: model.layers.9.self_attn.v_proj
        value: 0.36114806473576705
      - filter: model.layers.10.self_attn.v_proj
        value: 0.3461163777300581
      - filter: model.layers.11.self_attn.v_proj
        value: 0.34881370135651807
      - filter: model.layers.12.self_attn.v_proj
        value: 0.35465353794584403
      - filter: model.layers.13.self_attn.v_proj
        value: 0.3599958099827162
      - filter: model.layers.14.self_attn.v_proj
        value: 0.36486670507515845
      - filter: model.layers.15.self_attn.v_proj
        value: 0.3886450531608443
      - filter: model.layers.16.self_attn.v_proj
        value: 0.3802650185932017
      - filter: model.layers.17.self_attn.v_proj
        value: 0.3948253286544807
      - filter: model.layers.18.self_attn.v_proj
        value: 0.4028911119258367
      - filter: model.layers.19.self_attn.v_proj
        value: 0.41336615513538993
      - filter: model.layers.20.self_attn.v_proj
        value: 0.4098832032682135
      - filter: model.layers.21.self_attn.v_proj
        value: 0.39906772115434974
      - filter: model.layers.22.self_attn.v_proj
        value: 0.4269051484837375
      - filter: model.layers.23.self_attn.v_proj
        value: 0.4284502173571466
      - filter: model.layers.24.self_attn.v_proj
        value: 0.43452574241868747
      - filter: model.layers.25.self_attn.v_proj
        value: 0.4286073430052899
      - filter: model.layers.26.self_attn.v_proj
        value: 0.421196249934531
      - filter: model.layers.27.self_attn.v_proj
        value: 0.43709212800502806
      - filter: model.layers.28.self_attn.v_proj
        value: 0.4468339181899125
      - filter: model.layers.29.self_attn.v_proj
        value: 0.4439009060912376
      - filter: model.layers.30.self_attn.v_proj
        value: 0.4961451840988844
      - filter: model.layers.31.self_attn.v_proj
        value: 0.36374063793013145
      - filter: model.layers.0.self_attn.o_proj
        value: 0.301335568009218
      - filter: model.layers.1.self_attn.o_proj
        value: 0.30623265070968414
      - filter: model.layers.2.self_attn.o_proj
        value: 0.3042685801078929
      - filter: model.layers.3.self_attn.o_proj
        value: 0.3
      - filter: model.layers.4.self_attn.o_proj
        value: 0.32671136018436076
      - filter: model.layers.5.self_attn.o_proj
        value: 0.3351961451840989
      - filter: model.layers.6.self_attn.o_proj
        value: 0.30518514638872885
      - filter: model.layers.7.self_attn.o_proj
        value: 0.3552820405384172
      - filter: model.layers.8.self_attn.o_proj
        value: 0.358241240245116
      - filter: model.layers.9.self_attn.o_proj
        value: 0.35758655004451895
      - filter: model.layers.10.self_attn.o_proj
        value: 0.3841669721887603
      - filter: model.layers.11.self_attn.o_proj
        value: 0.3434714293196459
      - filter: model.layers.12.self_attn.o_proj
        value: 0.38160058660241974
      - filter: model.layers.13.self_attn.o_proj
        value: 0.3708374797046038
      - filter: model.layers.14.self_attn.o_proj
        value: 0.4145707851044885
      - filter: model.layers.15.self_attn.o_proj
        value: 0.39864871942596763
      - filter: model.layers.16.self_attn.o_proj
        value: 0.41519928769706177
      - filter: model.layers.17.self_attn.o_proj
        value: 0.31864557691300477
      - filter: model.layers.18.self_attn.o_proj
        value: 0.3101084166972189
      - filter: model.layers.19.self_attn.o_proj
        value: 0.3196145184098884
      - filter: model.layers.20.self_attn.o_proj
        value: 0.4667365002880637
      - filter: model.layers.21.self_attn.o_proj
        value: 0.3742418687477086
      - filter: model.layers.22.self_attn.o_proj
        value: 0.3403812915728277
      - filter: model.layers.23.self_attn.o_proj
        value: 0.3232284083171843
      - filter: model.layers.24.self_attn.o_proj
        value: 0.3742418687477086
      - filter: model.layers.25.self_attn.o_proj
        value: 0.6244644634159116
      - filter: model.layers.26.self_attn.o_proj
        value: 0.5438066307023517
      - filter: model.layers.27.self_attn.o_proj
        value: 0.542366312261038
      - filter: model.layers.28.self_attn.o_proj
        value: 0.4544021369088147
      - filter: model.layers.29.self_attn.o_proj
        value: 0.4355732467396428
      - filter: model.layers.30.self_attn.o_proj
        value: 0.4489027392237993
      - filter: model.layers.31.self_attn.o_proj
        value: 0.3717016707693919
      - filter: model.layers.0.mlp.gate_proj
        value: 0.321735714659823
      - filter: model.layers.1.mlp.gate_proj
        value: 0.32713036191274286
      - filter: model.layers.2.mlp.gate_proj
        value: 0.3402765411407322
      - filter: model.layers.3.mlp.gate_proj
        value: 0.34344524171162205
      - filter: model.layers.4.mlp.gate_proj
        value: 0.34572356360969986
      - filter: model.layers.5.mlp.gate_proj
        value: 0.34881370135651807
      - filter: model.layers.6.mlp.gate_proj
        value: 0.3491017650447808
      - filter: model.layers.7.mlp.gate_proj
        value: 0.34637825381029697
      - filter: model.layers.8.mlp.gate_proj
        value: 0.351301524118787
      - filter: model.layers.9.mlp.gate_proj
        value: 0.35083014717435707
      - filter: model.layers.10.mlp.gate_proj
        value: 0.35062064631016604
      - filter: model.layers.11.mlp.gate_proj
        value: 0.35083014717435707
      - filter: model.layers.12.mlp.gate_proj
        value: 0.35724611114020843
      - filter: model.layers.13.mlp.gate_proj
        value: 0.36078143822343267
      - filter: model.layers.14.mlp.gate_proj
        value: 0.3717278583774158
      - filter: model.layers.15.mlp.gate_proj
        value: 0.3819410255067302
      - filter: model.layers.16.mlp.gate_proj
        value: 0.3969203372963913
      - filter: model.layers.17.mlp.gate_proj
        value: 0.4064526266170848
      - filter: model.layers.18.mlp.gate_proj
        value: 0.4028387367097889
      - filter: model.layers.19.mlp.gate_proj
        value: 0.40865238569109097
      - filter: model.layers.20.mlp.gate_proj
        value: 0.4113758969255748
      - filter: model.layers.21.mlp.gate_proj
        value: 0.4152778505211334
      - filter: model.layers.22.mlp.gate_proj
        value: 0.41237102603048237
      - filter: model.layers.23.mlp.gate_proj
        value: 0.4021316712931441
      - filter: model.layers.24.mlp.gate_proj
        value: 0.3956895197192688
      - filter: model.layers.25.mlp.gate_proj
        value: 0.407290630073849
      - filter: model.layers.26.mlp.gate_proj
        value: 0.41842036348399936
      - filter: model.layers.27.mlp.gate_proj
        value: 0.43950138794322524
      - filter: model.layers.28.mlp.gate_proj
        value: 0.4232912585764416
      - filter: model.layers.29.mlp.gate_proj
        value: 0.43353061331377996
      - filter: model.layers.30.mlp.gate_proj
        value: 0.4429843398104017
      - filter: model.layers.31.mlp.gate_proj
        value: 0.39241606871628343
      - filter: model.layers.0.mlp.up_proj
        value: 0.31846226365683755
      - filter: model.layers.1.mlp.up_proj
        value: 0.3282826166657937
      - filter: model.layers.2.mlp.up_proj
        value: 0.34148117110983084
      - filter: model.layers.3.mlp.up_proj
        value: 0.34344524171162205
      - filter: model.layers.4.mlp.up_proj
        value: 0.3439951814801236
      - filter: model.layers.5.mlp.up_proj
        value: 0.3482899491960404
      - filter: model.layers.6.mlp.up_proj
        value: 0.34933745351699574
      - filter: model.layers.7.mlp.up_proj
        value: 0.34700675640287015
      - filter: model.layers.8.mlp.up_proj
        value: 0.35025401979783166
      - filter: model.layers.9.mlp.up_proj
        value: 0.34996595610956893
      - filter: model.layers.10.mlp.up_proj
        value: 0.3525585293039334
      - filter: model.layers.11.mlp.up_proj
        value: 0.3536060336248887
      - filter: model.layers.12.mlp.up_proj
        value: 0.358686429581522
      - filter: model.layers.13.mlp.up_proj
        value: 0.3634525742418687
      - filter: model.layers.14.mlp.up_proj
        value: 0.3718849840255591
      - filter: model.layers.15.mlp.up_proj
        value: 0.38311946786780493
      - filter: model.layers.16.mlp.up_proj
        value: 0.3967108364322003
      - filter: model.layers.17.mlp.up_proj
        value: 0.4041481171109831
      - filter: model.layers.18.mlp.up_proj
        value: 0.4013460430524276
      - filter: model.layers.19.mlp.up_proj
        value: 0.40493374535169957
      - filter: model.layers.20.mlp.up_proj
        value: 0.408861886555282
      - filter: model.layers.21.mlp.up_proj
        value: 0.41176871104593304
      - filter: model.layers.22.mlp.up_proj
        value: 0.4101974545645001
      - filter: model.layers.23.mlp.up_proj
        value: 0.4023411721573351
      - filter: model.layers.24.mlp.up_proj
        value: 0.39652752317603307
      - filter: model.layers.25.mlp.up_proj
        value: 0.40742156811396846
      - filter: model.layers.26.mlp.up_proj
        value: 0.4191274289006442
      - filter: model.layers.27.mlp.up_proj
        value: 0.4394490127271775
      - filter: model.layers.28.mlp.up_proj
        value: 0.42931440842193475
      - filter: model.layers.29.mlp.up_proj
        value: 0.44222489917770913
      - filter: model.layers.30.mlp.up_proj
        value: 0.4493741161682292
      - filter: model.layers.31.mlp.up_proj
        value: 0.3794532027444613
      - filter: model.layers.0.mlp.down_proj
        value: 0.3215785890116797
      - filter: model.layers.1.mlp.down_proj
        value: 0.34407374430419524
      - filter: model.layers.2.mlp.down_proj
        value: 0.3128319279317027
      - filter: model.layers.3.mlp.down_proj
        value: 0.32330697114125595
      - filter: model.layers.4.mlp.down_proj
        value: 0.3263185460640025
      - filter: model.layers.5.mlp.down_proj
        value: 0.3317393809249463
      - filter: model.layers.6.mlp.down_proj
        value: 0.3353008956161944
      - filter: model.layers.7.mlp.down_proj
        value: 0.3378934688105588
      - filter: model.layers.8.mlp.down_proj
        value: 0.3421358613104279
      - filter: model.layers.9.mlp.down_proj
        value: 0.3419263604462368
      - filter: model.layers.10.mlp.down_proj
        value: 0.3389933483475619
      - filter: model.layers.11.mlp.down_proj
        value: 0.33818153249882155
      - filter: model.layers.12.mlp.down_proj
        value: 0.3378934688105588
      - filter: model.layers.13.mlp.down_proj
        value: 0.35009689414968836
      - filter: model.layers.14.mlp.down_proj
        value: 0.3351437699680511
      - filter: model.layers.15.mlp.down_proj
        value: 0.3680354056460483
      - filter: model.layers.16.mlp.down_proj
        value: 0.3725920494422039
      - filter: model.layers.17.mlp.down_proj
        value: 0.36947572408736185
      - filter: model.layers.18.mlp.down_proj
        value: 0.3621693814486985
      - filter: model.layers.19.mlp.down_proj
        value: 0.3649452678992301
      - filter: model.layers.20.mlp.down_proj
        value: 0.36468339181899123
      - filter: model.layers.21.mlp.down_proj
        value: 0.3756036243649505
      - filter: model.layers.22.mlp.down_proj
        value: 0.35449641229770074
      - filter: model.layers.23.mlp.down_proj
        value: 0.34637825381029697
      - filter: model.layers.24.mlp.down_proj
        value: 0.3522442780076468
      - filter: model.layers.25.mlp.down_proj
        value: 0.3727491750903472
      - filter: model.layers.26.mlp.down_proj
        value: 0.4206986853820772
      - filter: model.layers.27.mlp.down_proj
        value: 0.4077620070182789
      - filter: model.layers.28.mlp.down_proj
        value: 0.42363169748075213
      - filter: model.layers.29.mlp.down_proj
        value: 0.534091028125491
      - filter: model.layers.30.mlp.down_proj
        value: 0.6001361755617243
      - filter: model.layers.31.mlp.down_proj
        value: 0.8
      - value: 1.0
tokenizer_source: union
Downloads last month
22
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Examples
Text Generation
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for vidhirambhia/test-llama-math-coder

MathGenie/MathCoder2-Llama-3-8B
meta-llama/Llama-3.1-8B
Merge model
this model
Quantizations
1 model