LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B by yunconglong

 »  All LLMs  »  yunconglong  »  Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B   URL Share it on

  8294   
  Autotrain compatible   Dpo   Endpoints compatible   Mixtral   Moe   Region:us   Rl-tuned   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B Benchmarks

ARC: 74.91 vs 96.7 (so35)-22.5%
HellaSwag: 89.3 vs 95.3 (gpt4)-6.3%
MMLU: 64.67 vs 88.3 (so35)-26.8%
TruthfulQA: 78.02 vs 59 (gpt4)32.2%
WinoGrande: 88.24 vs 87.5 (gpt4)0.8%
GSM8K: 69.52 vs 96.4 (so35)-27.9%
LLME Score: 0.21541
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B (yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B)

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B Parameters and Internals

Model Type 
moe, DPO, RL-TUNED
Additional Notes 
Supports the DPO Trainer for training language models, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.
Training Details 
Data Sources:
jondurbin/truthy-dpo-v0.1
Methodology:
DPO (Direct Preference Optimization) Trainer for training language models from preference data.
LLM NameTruthful DPO TomGrc FusionNet 7Bx2 MoE 13B
Repository 🤗https://huggingface.co/yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 
Model Size12.9b
Required VRAM25.8 GB
Updated2025-02-05
Maintaineryunconglong
Model Typemixtral
Model Files  5.0 GB: 1-of-6   4.9 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   4.9 GB: 5-of-6   1.0 GB: 6-of-6
Model ArchitectureMixtralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B

Model
Likes
Downloads
VRAM
...rc FusionNet 7Bx2 MoE 13B GPTQ1937 GB
...Grc FusionNet 7Bx2 MoE 13B AWQ3927 GB

Best Alternatives to Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B

Best Alternatives
Context / RAM
Downloads
Likes
MixTAO 7Bx2 MoE V8.132K / 25.8 GB1021455
Inf Silent Kunoichi V0.1 2x7B32K / 25.6 GB50
MixTAO 7Bx2 MoE V8.132K / 25.8 GB876052
Inf Silent Kunoichi V0.2 2x7B32K / 25.6 GB50
LogoS 7Bx2 MoE 13B V0.232K / 25.9 GB314010
MultiMash8 13B Slerp32K / 25.7 GB80
MultiMash11 13B Slerp32K / 25.7 GB60
MultiMash9 13B Slerp32K / 25.7 GB80
MultiMash10 13B Slerp32K / 25.7 GB70
MixTaoTruthful 13B Slerp32K / 25.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.

Rank the Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42577 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer