GOAT Coder Llama3.1 8B by kshabana

 ยป  All LLMs  ยป  kshabana  ยป  GOAT Coder Llama3.1 8B   URL Share it on

  4bit Base model:quantized:unsloth/m... Base model:unsloth/meta-llama-...   Codegen   Coding   Conversational   Dataset:replete-ai/code bagel   En   Endpoints compatible   Finetuned   Gguf   Instruct   Llama   Lora   Pytorch   Q4   Quantized   Region:us   Safetensors   Safetersors   Sft   Sharded   Tensorflow   Trl   Unsloth

GOAT Coder Llama3.1 8B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GOAT Coder Llama3.1 8B (kshabana/GOAT-coder-llama3.1-8b)

GOAT Coder Llama3.1 8B Parameters and Internals

Model Type 
safetensors, gguf
Use Cases 
Applications:
coding
Limitations:
can sometimes produce wrong answers
Additional Notes 
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Supported Languages 
en (English)
Training Details 
Data Sources:
https://huggingface.co/datasets/Replete-AI/code_bagel
Methodology:
Trained with Unsloth and Huggingface's TRL library
Context Length:
131072
LLM NameGOAT Coder Llama3.1 8B
Repository ๐Ÿค—https://huggingface.co/kshabana/GOAT-coder-llama3.1-8b 
Base Model(s)  unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit   unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Model Size8b
Required VRAM16.1 GB
Updated2024-12-22
Maintainerkshabana
Instruction-BasedYes
Model Files  16.1 GB   4.9 GB   5.7 GB   8.5 GB   0.2 GB   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
GGUF QuantizationYes
Quantization Typeq4|4bit|gguf|q4_k|q5_k
Generates CodeYes
Model ArchitectureAutoModel
Licenseapache-2.0
Model Max Length131072
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleso_proj|k_proj|q_proj|down_proj|gate_proj|up_proj|v_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Rank the GOAT Coder Llama3.1 8B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217