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

Instruct V0.2 Seraph 7B by Weyaxi

 »  All LLMs  »  Weyaxi  »  Instruct V0.2 Seraph 7B   URL Share it on

  1284   
  Autotrain compatible   Endpoints compatible   Instruct   Merge   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Weyaxi/Instruct-v0.2-Seraph-7B 

Instruct V0.2 Seraph 7B Benchmarks

ARC: 64.76 vs 96.7 (so35)-33%
HellaSwag: 84.2 vs 95.3 (gpt4)-11.6%
MMLU: 62.9 vs 88.3 (so35)-28.8%
TruthfulQA: 65.39 vs 59 (gpt4)10.8%
WinoGrande: 79.16 vs 87.5 (gpt4)-9.5%
GSM8K: 54.44 vs 96.4 (so35)-43.5%
LLME Score: 0.19115
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Instruct V0.2 Seraph 7B (Weyaxi/Instruct-v0.2-Seraph-7B)

Instruct V0.2 Seraph 7B Parameters and Internals

Additional Notes 
This model is a result of merging two models: - Weyaxi/Seraph-7B: using layer range 0-32 - Mistralai/Mistral-7B-Instruct-v0.2: using layer range 0-32 The merge method used is SLERP (Spherical Linear Interpolation) with specific parameters for 'self_attn' and 'mlp' filters, and a value parameter of 0.5. Data type used during merging is bfloat16.
Training Details 
Methodology:
mergekit
LLM NameInstruct V0.2 Seraph 7B
Repository 🤗https://huggingface.co/Weyaxi/Instruct-v0.2-Seraph-7B 
Model Size7b
Required VRAM14.4 GB
Updated2024-12-14
MaintainerWeyaxi
Model Typemistral
Instruction-BasedYes
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Instruct V0.2 Seraph 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB27459
SpydazWeb AI HumanAI RP512K / 14.4 GB361
SpydazWeb AI HumanAI 002512K / 14.4 GB161
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB50
...1 Summarize 64K LoRANET Merged128K / 14.4 GB50
Mistral 7B Instruct V0.232K / 14.4 GB13701322593
Mistral 7B Instruct V0.132K / 14.4 GB11806021537
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB56273
...ty Instruct 3M 0625 Mistral 7B32K / 14.4 GB56603
Note: green Score (e.g. "73.2") means that the model is better than Weyaxi/Instruct-v0.2-Seraph-7B.

Rank the Instruct V0.2 Seraph 7B 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? 39237 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 v20241124
  Support LLM Explorer