LLM EXPLORER 60,828 MODELS INDEXED

Jambatypus V0.1 by mlabonne

By mlabonne · 14 downloads
HF Repo ↗ Copy URL

Jambatypus V0.1 is an open-source language model by mlabonne. Features: 51.6b LLM, VRAM: 0.5GB, License: apache-2.0, LLM Explorer Score: 0.12.

  4-bit   Axolotl   Base model:ai21labs/jamba-v0.1 Base model:quantized:ai21labs/...   Bitsandbytes   Conversational   Custom code   En   Endpoints compatible   Jamba   Lora   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/mlabonne/Jambatypus-v0.1 

Jambatypus V0.1 Parameters and Internals

Model Type 
QLoRA fine-tuned model
Supported Languages 
en (High)
Training Details 
Data Sources:
chargoddard/Open-Platypus-Chat
Context Length:
4096
Hardware Used:
2xA100 80 GB
Input Output 
Accepted Modalities:
text
Performance Tips:
Use ChatML template for optimal performance.
Release Notes 
Version:
0.1
Notes:
The model is a fine-tuned version of ai21labs/Jamba-v0.1 on Open-Platypus-Chat dataset using QLoRA.
LLM NameJambatypus V0.1
Repository 🤗https://huggingface.co/mlabonne/Jambatypus-v0.1 
Base Model(s)  ai21labs/Jamba-v0.1   ai21labs/Jamba-v0.1
Model Size51.6b
Required VRAM0.5 GB
Updated2026-08-01
Maintainermlabonne
Model Files  0.5 GB   0.0 GB
Supported Languagesen
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<|pad|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj|dt_proj|out_proj|in_proj|k_proj|x_proj|o_proj|gate_proj|down_proj|up_proj|router
LoRA Alpha32
LoRA Dropout0.05
R Param16

Best Alternatives to Jambatypus V0.1

Best Alternatives
Context / RAM
Downloads
Likes
MS32 30K / 1.5 GB50
Asdf0K / 0.1 GB160
MS32 20K / 0.7 GB50
...ve Radiology Report Generation0K / 0.2 GB9590515
Tinyllama Cpt0K / 0.5 GB50
Fine Tune Sentimental Llama0K / 0 GB50
VLM2Vec LoRA0K / 0 GB9611
QuietStar Project0K /  GB162
Finetuned Llava Lora0K / 0.1 GB50
Qwen7B Haiguitang0K / 15.3 GB80
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/Jambatypus-v0.1.