LLM EXPLORER 59,420 MODELS INDEXED

Internlm2 Limarp Lora by intervitens

By intervitens · 8 downloads
HF Repo ↗ Copy URL

Internlm2 Limarp Lora is an open-source language model by intervitens. Features: 20b LLM, VRAM: 2.6GB, LLM Explorer Score: 0.11.

  8-bit   Adapter Base model:adapter:intervitens... Base model:intervitens/internl...   Bitsandbytes   Finetuned   Generated from trainer   Llama   Lora   Peft   Region:us
Model Card on HF 🤗: https://huggingface.co/intervitens/internlm2-limarp-lora 

Internlm2 Limarp Lora Parameters and Internals

Model Type 
LlamaForCausalLM
Additional Notes 
It appears that there's a problem with the llamafied internlm2 tokenizer.
Training Details 
Data Sources:
/data/train-all-8k.jsonl
Context Length:
8192
LLM NameInternlm2 Limarp Lora
Repository 🤗https://huggingface.co/intervitens/internlm2-limarp-lora 
Base Model(s)  Internlm2 Base 20B Llama   intervitens/internlm2-base-20b-llama
Model Size20b
Required VRAM2.6 GB
Updated2026-08-06
Maintainerintervitens
Model Files  2.6 GB
Model ArchitectureAdapter
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleso_proj|down_proj|gate_proj|q_proj|up_proj|v_proj|k_proj
LoRA Alpha64
LoRA Dropout0.05
R Param128

Best Alternatives to Internlm2 Limarp Lora

Best Alternatives
Context / RAM
Downloads
Likes
...x 20B Finetuned English Quotes0K / 0 GB50
Jennifer Gptneox 20b0K / 0 GB21
...eox 20B Medical Reports Splits0K / 0 GB01
GPT Neox 20B 4bit Alpaca0K / 0 GB122
Rose Kimiko 20B0K / 0.2 GB22
Note: green Score (e.g. "73.2") means that the model is better than intervitens/internlm2-limarp-lora.