LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama 3 8B Base Coder V3.5 10K by rombodawg

 »  All LLMs  »  rombodawg  »  Llama 3 8B Base Coder V3.5 10K   URL Share it on

  5   
  Autotrain compatible Base model:finetune:nousresear... Base model:nousresearch/meta-l...   Codegen   En   Endpoints compatible   Llama   Pytorch   Region:us   Sft   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/rombodawg/Llama-3-8B-Base-Coder-v3.5-10k 

Llama 3 8B Base Coder V3.5 10K Benchmarks

ARC: 57.25 vs 96.7 (so35)-40.8%
HellaSwag: 81.13 vs 95.3 (gpt4)-14.9%
MMLU: 65.38 vs 88.3 (so35)-26%
TruthfulQA: 45.13 vs 59 (gpt4)-23.5%
WinoGrande: 78.3 vs 87.5 (gpt4)-10.5%
GSM8K: 42 vs 96.4 (so35)-56.4%
LLME Score: 0.17304
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B Base Coder V3.5 10K (rombodawg/Llama-3-8B-Base-Coder-v3.5-10k)
🌟 Advertise your project 🚀

Llama 3 8B Base Coder V3.5 10K Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, llama, trl, sft
Additional Notes 
This was an experiment to update the training method for future finetunes. The model was trained for 5 epochs at a learning rate of 2e-4, with 20 warm-up steps.
Training Details 
Data Sources:
https://huggingface.co/datasets/Replete-AI/code_test_dataset_10k
Input Output 
Input Format:
Alpaca
LLM NameLlama 3 8B Base Coder V3.5 10K
Repository 🤗https://huggingface.co/rombodawg/Llama-3-8B-Base-Coder-v3.5-10k 
Base Model(s)  Meta Llama 3 8B   NousResearch/Meta-Llama-3-8B
Model Size8b
Required VRAM16.1 GB
Updated2025-09-16
Maintainerrombodawg
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 8B Base Coder V3.5 10K

Best Alternatives
Context / RAM
Downloads
Likes
CoolerCoder 8B Model Stock128K / 16.1 GB342
...ynesthesia 3.1 Task Arithmetic128K / 16.1 GB60
Replete Coder V2 Llama 3.1 8B128K / 16.1 GB199
Seed Coder 8B Reasoning64K / 32.9 GB1325140
Seed Coder 8B Reasoning Bf1664K / 16.5 GB115816
Seed Coder 8B Instruct32K / 16.5 GB4108101
Seed Coder 8B Base32K / 16.5 GB329954
Seed Coder 8B Instruct32K / 16.5 GB4271
Seed Coder 8B Instruct V132K / 32.9 GB432
Wasm Coder 8B Instruct V132K / 32.9 GB143
Note: green Score (e.g. "73.2") means that the model is better than rombodawg/Llama-3-8B-Base-Coder-v3.5-10k.

Rank the Llama 3 8B Base Coder V3.5 10K 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? 51408 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer