LLM EXPLORER 55,709 MODELS INDEXED

Gecko 7B V0.1 by NeuralNovel

By NeuralNovel · 54 downloads
HF Repo ↗ Copy URL

Gecko 7B V0.1 is an open-source language model by NeuralNovel. Features: 7b LLM, VRAM: 10.2GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.12, Arc: 61.4, HellaSwag: 83.4, MMLU: 61.1, GSM8K: 41.6.

Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational   Instruct   Mistral   Model-index   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NeuralNovel/Gecko-7B-v0.1 

Gecko 7B V0.1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
instructive and narrative text generation, mathematics & numeracy, roleplay, problem solving
Limitations:
The model may not perform well in scenarios unrelated to instructive and narrative text generation
Considerations:
Use the model with caution and respect
Additional Notes 
Fine-tuned to follow prompt directions, making it more suitable for specific applications.
Training Details 
Data Sources:
Neural-Mini-Math dataset (Currently Private)
Methodology:
Fine-tuned with the intention of following all prompt directions
Responsible Ai Considerations 
Accountability:
The user is responsible for their output
LLM NameGecko 7B V0.1
Repository 🤗https://huggingface.co/NeuralNovel/Gecko-7B-v0.1 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   mistralai/Mistral-7B-Instruct-v0.2
Model Size7b
Required VRAM10.2 GB
Updated2026-07-31
MaintainerNeuralNovel
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3   4.8 GB: 1-of-4   5.0 GB: 2-of-4   0.4 GB: 3-of-4
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Gecko 7B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB22020
SpydazWeb AI HumanAI RP512K / 14.4 GB161
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB50
...1 Summarize 64K LoRANET Merged128K / 14.4 GB70
Mistral 7B Instruct V0.232K / 14.4 GB11153373184
Mistral 7B Instruct V0.132K / 14.4 GB2536291846
Mistral 7B Instruct V0.232K / 14.4 GB13380
Mixtral AI CyberCoder32K / 14.3 GB00
Note: green Score (e.g. "73.2") means that the model is better than NeuralNovel/Gecko-7B-v0.1.