LLM EXPLORER 60,277 MODELS INDEXED

Ice0.88 07.02 RP DPO Merged 16bit 3 by icefog72

By icefog72 · 25 downloads
HF Repo ↗ Copy URL

Ice0.88 07.02 RP DPO Merged 16bit 3 is an open-source language model by icefog72. Features: 7.2b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Quantized, Merged, LLM Explorer Score: 0.16.

  Merged Model   16bit Base model:finetune:icefog72/i... Base model:icefog72/ice0.88-07...   Conversational   En   Endpoints compatible   Mistral   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/icefog72/Ice0.88-07.02-RP-dpo-merged_16bit-3 

Ice0.88 07.02 RP DPO Merged 16bit 3 Parameters and Internals

LLM NameIce0.88 07.02 RP DPO Merged 16bit 3
Repository 🤗https://huggingface.co/icefog72/Ice0.88-07.02-RP-dpo-merged_16bit-3 
Base Model(s)  icefog72/Ice0.88-07.02-RP-dpo-merged_16bit   icefog72/Ice0.88-07.02-RP-dpo-merged_16bit
Merged ModelYes
Model Size7.2b
Required VRAM14.4 GB
Updated2026-08-03
Maintainericefog72
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3   4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Quantization Type16bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.48.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Ice0.88 07.02 RP DPO Merged 16bit 3

Best Alternatives
Context / RAM
Downloads
Likes
...Sft Bnb 4bit DPO Mtbr 180steps32K / 14.4 GB50
...Sft Bnb 4bit DPO Mtbc 213steps32K / 14.4 GB50
...Sft Bnb 4bit DPO Mtbo 180steps32K / 14.4 GB60
Mixtral V0.3 Full 16bit V232K / 14.5 GB60
Rezephyr DPO32K / 14.4 GB200
Autogen Mistral 16bit Merged32K / 14.5 GB1430
Zephyr DPO V232K / 14.4 GB191
Tools Mistral 16bit Merged New32K / 14.5 GB50
AI Tutor32K / 14.5 GB60
...Web AI HumanAI 012 INSTRUCT XA512K / 14.4 GB90
Note: green Score (e.g. "73.2") means that the model is better than icefog72/Ice0.88-07.02-RP-dpo-merged_16bit-3.