EXPERIMENT WIP KNOWLEDGE by DreadPoor

 ยป  All LLMs  ยป  DreadPoor  ยป  EXPERIMENT WIP KNOWLEDGE   URL Share it on

  Merged Model   Arxiv:2403.19522   Autotrain compatible Base model:cognitivecomputatio...   Base model:kloodia/lora-8b-bio Base model:kloodia/lora-8b-cod... Base model:kloodia/lora-8b-mat... Base model:kloodia/lora-8b-med... Base model:kloodia/lora-8b-phy... Base model:nousresearch/hermes... Base model:zementalist/llama-3...   Conversational   Endpoints compatible   Llama   Lora   Region:us   Safetensors   Sharded   Tensorflow

EXPERIMENT WIP KNOWLEDGE Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

EXPERIMENT WIP KNOWLEDGE Parameters and Internals

LLM NameEXPERIMENT WIP KNOWLEDGE
Repository ๐Ÿค—https://huggingface.co/DreadPoor/EXPERIMENT-WIP-KNOWLEDGE 
Base Model(s)  Hermes 2 Pro Llama 3 8B   Lora 8B Medic   cognitivecomputations/dolphin-2.9.1-llama-3-8b   Lora 8B Math   Hermes 2 Pro Llama 3 8B   ...lama 3 8B Chat Psychotherapist   Hermes 2 Pro Llama 3 8B   Lora 8B Bio   cognitivecomputations/dolphin-2.9.1-llama-3-8b   Lora 8B Physic   cognitivecomputations/dolphin-2.9.1-llama-3-8b   Lora 8B Code   NousResearch/Hermes-2-Pro-Llama-3-8B   kloodia/lora-8b-medic   cognitivecomputations/dolphin-2.9.1-llama-3-8b   kloodia/lora-8b-math   NousResearch/Hermes-2-Pro-Llama-3-8B   zementalist/llama-3-8B-chat-psychotherapist   NousResearch/Hermes-2-Pro-Llama-3-8B   kloodia/lora-8b-bio   cognitivecomputations/dolphin-2.9.1-llama-3-8b   kloodia/lora-8b-physic   cognitivecomputations/dolphin-2.9.1-llama-3-8b   kloodia/lora-8b-code
Merged ModelYes
Model Size8b
Required VRAM16.1 GB
Updated2024-09-09
MaintainerDreadPoor
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.44.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128258
LoRA ModelYes
Torch Data Typebfloat16
EXPERIMENT WIP KNOWLEDGE (DreadPoor/EXPERIMENT-WIP-KNOWLEDGE)

Best Alternatives to EXPERIMENT WIP KNOWLEDGE

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3284108
UltraLong Thinking4192K / 16.1 GB3672
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB52615
Zero Llama 3.1 8B Beta61048K / 16.1 GB9581
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB180845
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB634
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB902
Note: green Score (e.g. "73.2") means that the model is better than DreadPoor/EXPERIMENT-WIP-KNOWLEDGE.

Rank the EXPERIMENT WIP KNOWLEDGE Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 48046 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124