LLM EXPLORER 59,420 MODELS INDEXED

Reflect Mini8Bit Om2 460K Sft DPO T1 by RyanYr

By RyanYr · 5 downloads

Reflect Mini8Bit Om2 460K Sft DPO T1 is an open-source language model by RyanYr. Features: 8b LLM, VRAM: 16.1GB, Context: 32K, LLM Explorer Score: 0.15.

  Arxiv:2305.18290   Autotrain compatible Base model:finetune:ryanyr/ref... Base model:ryanyr/reflect mini...   Conversational   Dpo   Endpoints compatible   Generated from trainer   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Trl

Reflect Mini8Bit Om2 460K Sft DPO T1 Parameters and Internals

LLM NameReflect Mini8Bit Om2 460k Sft DPO T1
Repository πŸ€—https://huggingface.co/RyanYr/reflect_mini8Bit_om2-460k_sft-dpo-t1 
Model Namereflect_mini8Bit_om2-460k_sft-dpo-t1
Base Model(s)  ...flect Mini8Bit Om2 460k Sft T1   RyanYr/reflect_mini8Bit_om2-460k_sft-t1
Model Size8b
Required VRAM16.1 GB
Updated2025-09-15
MaintainerRyanYr
Model Typemistral
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.1 GB: 4-of-4   0.0 GB
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.45.2
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size131073
Torch Data Typebfloat16

Best Alternatives to Reflect Mini8Bit Om2 460K Sft DPO T1

Best Alternatives
Context / RAM
Downloads
Likes
Ministral 8B Instruct 2410 HF32K / 32 GB2112
Ministrations 8B V132K / 16.1 GB2029
Minerva 8B32K / 14.5 GB70
...l 8B Instruct 2410 Abliterated32K / 16.1 GB463
Ministral 8B Slerp32K / 29.2 GB70
The Omega Directive M 8B V1.032K / 16.1 GB309
Mistral Pro 8B V0.132K / 17.9 GB8367
Deeplm Mistral V0.1 8B Stage132K / 14.5 GB161
Forgotten Abomination 8B V2.232K / 16.1 GB112
Forgotten Safeword 8B V2.232K / 16.1 GB41
Note: green Score (e.g. "73.2") means that the model is better than RyanYr/reflect_mini8Bit_om2-460k_sft-dpo-t1.