DeepSeek V2 Lite Aux Free Sft Math7k 1epoch 1e 4 Gamma by HectorHe

 »  All LLMs  »  HectorHe  »  DeepSeek V2 Lite Aux Free Sft Math7k 1epoch 1e 4 Gamma   URL Share it on

DeepSeek V2 Lite Aux Free Sft Math7k 1epoch 1e 4 Gamma is an open-source language model by HectorHe. Features: 15.7b LLM, VRAM: 31.4GB, Context: 160K, LLM Explorer Score: 0.22.

Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Custom code   Dataset:hectorhe/math7k   Deepseek v2   Endpoints compatible   Generated from trainer   Open-r1   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl

DeepSeek V2 Lite Aux Free Sft Math7k 1epoch 1e 4 Gamma Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

DeepSeek V2 Lite Aux Free Sft Math7k 1epoch 1e 4 Gamma Parameters and Internals

LLM NameDeepSeek V2 Lite Aux Free Sft Math7k 1epoch 1e 4 Gamma
Repository 🤗https://huggingface.co/HectorHe/DeepSeek-V2-Lite-aux-free-sft-math7k-1epoch-1e-4-gamma 
Model NameDeepSeek-V2-Lite-aux-free-sft-math7k-1epoch-1e-4-gamma
Base Model(s)  DeepSeek V2 Lite   deepseek-ai/DeepSeek-V2-Lite
Model Size15.7b
Required VRAM31.4 GB
Updated2026-02-09
MaintainerHectorHe
Model Typedeepseek_v2
Model Files  5.0 GB: 1-of-7   5.0 GB: 2-of-7   5.0 GB: 3-of-7   5.0 GB: 4-of-7   5.0 GB: 5-of-7   5.0 GB: 6-of-7   1.4 GB: 7-of-7   0.0 GB
Model ArchitectureDeepseekV2ForCausalLM
Context Length163840
Model Max Length163840
Transformers Version4.51.0
Tokenizer ClassLlamaTokenizerFast
Padding Token<|end▁of▁sentence|>
Vocabulary Size102400
Torch Data Typebfloat16

Best Alternatives to DeepSeek V2 Lite Aux Free Sft Math7k 1epoch 1e 4 Gamma

Best Alternatives
Context / RAM
Downloads
Likes
...eepSeek Coder V2 Lite Instruct160K / 31.4 GB367294572
DeepSeek V2 Lite160K / 31.4 GB246467168
DeepSeek V2 Lite Chat160K / 31.4 GB811609135
KwaiCoder DS V2 Lite Base160K / 31.4 GB12587
Dsv2 Lite Coder Codeio Pp160K / 31.4 GB112
DeepSeek Coder V2 Lite Base160K / 31.4 GB2312105
...2 Lite Instruct FlashAttnPatch160K / 31.4 GB60
ESFT Vanilla Lite4K / 31.4 GB35719
LunarAI160K / 31.4 GB50
...eek Coder V2 Lite Instruct AWQ160K / 9.1 GB34589
Note: green Score (e.g. "73.2") means that the model is better than HectorHe/DeepSeek-V2-Lite-aux-free-sft-math7k-1epoch-1e-4-gamma.

Rank the DeepSeek V2 Lite Aux Free Sft Math7k 1epoch 1e 4 Gamma Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a