SFT PT Best Final by TwinDoc

 ยป  All LLMs  ยป  TwinDoc  ยป  SFT PT Best Final   URL Share it on

  Arxiv:1910.09700   Adapter Base model:twindoc/h100 stage2...   Finetuned   Lora   Peft   Region:us   Safetensors

SFT PT Best Final Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SFT PT Best Final (TwinDoc/SFT-PT_best_final)

SFT PT Best Final Parameters and Internals

LLM NameSFT PT Best Final
Repository ๐Ÿค—https://huggingface.co/TwinDoc/SFT-PT_best_final 
Base Model(s)  ...00 Stage2 59k Checkpoint 30240   TwinDoc/H100_stage2_59k_checkpoint-30240
Required VRAM1 GB
Updated2024-07-22
MaintainerTwinDoc
Model Files  1.0 GB
Model ArchitectureAdapter
Model Max Length4096
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleso_proj|down_proj|gate_proj|embed_tokens|q_proj|k_proj|up_proj|v_proj|lm_head
LoRA Alpha32
LoRA Dropout0.1
R Param32

Best Alternatives to SFT PT Best Final

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Mini 4K Instruct Sa V0.10K / 0 GB80
Samantha Omni Humanlike Lora0K / 0 GB563
...is Violet Toxic GRPO V0.4 Lora0K / 0.5 GB120
Reflection Model0K / 0.2 GB01
SpectraMind0K / 16.1 GB1203
...mall Physics Finetuned Adapter0K / 0.1 GB81
SpectraMindQ0K / 0.2 GB81
L3.1 Spark R64 LoRA0K / 0.4 GB80
Mistral Small Fujin Qlora0K / 0.8 GB472
Mistral Small Dampf Qlora0K / 0.8 GB190
Note: green Score (e.g. "73.2") means that the model is better than TwinDoc/SFT-PT_best_final.

Rank the SFT PT Best Final 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227