Hugging Face's logo

lumolabs-ai
/
Lumo-8B-Instruct

Safetensors
GGUF
llama
Inference Endpoints
8-bit precision
bitsandbytes
conversational
Model card Files Community
lumolabs commited on
Commit
6a86cc6
·
verified ·
1 Parent(s): cd111f6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ The **Lumo-8B-Instruct** model is a fine-tuned version of Meta's LLaMa 3.1 8B mo
31
  |----------------------------|----------------------------------------------------------------------------------------------|
32
  | **Base Model** | Meta LLaMa 3.1 8B |
33
  | **Fine-Tuning Framework** | HuggingFace Transformers, LoRA |
34
- | **Dataset Size** | ~10,000 high-quality Q&A pairs |
35
  | **Context Length** | 4,096 tokens |
36
  | **Training Steps** | 10,000 |
37
  | **Learning Rate** | 3e-4 |
 
31
  |----------------------------|----------------------------------------------------------------------------------------------|
32
  | **Base Model** | Meta LLaMa 3.1 8B |
33
  | **Fine-Tuning Framework** | HuggingFace Transformers, LoRA |
34
+ | **Dataset Size** | 5,502 high-quality Q&A pairs |
35
  | **Context Length** | 4,096 tokens |
36
  | **Training Steps** | 10,000 |
37
  | **Learning Rate** | 3e-4 |