LLM EXPLORER 59,420 MODELS INDEXED

Llama 13B Hf Prompt Answering by Sandiago21

By Sandiago21 · 24 downloads

Llama 13B Hf Prompt Answering is an open-source language model by Sandiago21. Features: 13b LLM, License: other, LLM Explorer Score: 0.07.

  8-bit   Decapoda-research-13b-hf   En   Endpoints compatible   Llama   Lora   Peft   Prompt answering   Pytorch   Region:us   Safetensors

Llama 13B Hf Prompt Answering Parameters and Internals

Model Type 
Causal LM
Use Cases 
Primary Use Cases:
Prompt answering, Generating text
Considerations:
Users should be aware of the risks, biases, and limitations of the model.
Training Details 
Training Time:
approximately 10 hours on a single GPU
Model Architecture:
Model is based on decapoda-research/llama-7b-hf and finetuned adapters on top of the main model on conversations and question answering data.
LLM NameLlama 13B Hf Prompt Answering
Repository πŸ€—https://huggingface.co/Sandiago21/llama-13b-hf-prompt-answering 
Model Size13b
Required VRAM0 GB
Updated2026-07-25
MaintainerSandiago21
Model Files  0.0 GB   14.0 GB   14.0 GB   0.0 GB
Supported Languagesen
Model ArchitectureAutoModelForCausalLM
Licenseother
Is Biasednone
Tokenizer ClassLlamaTokenizer
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj
LoRA Alpha16
LoRA Dropout0.05
R Param4

Best Alternatives to Llama 13B Hf Prompt Answering

Best Alternatives
Context / RAM
Downloads
Likes
ALMA 13B R0K / 26 GB876682
Small Tiny V10K / 0.1 GB100
...ama2 13B No Robots Alpaca Lora0K / 4 GB5811
Llava V1.5 13B S2 Lora0K / 0.1 GB92
Llama 2 13B Chat Hf GPT 4 80K0K / 26 GB630
Llava Chart 13b Lora0K / 0.1 GB42
ChartLlama 13B0K / 0.1 GB1120
Orca 2 13B Pygmalion LoRA0K / 0.5 GB122
Leyley 13B Lora0K / 4 GB44
GTS Lewd 13B V0.20K / 52.3 GB41
Note: green Score (e.g. "73.2") means that the model is better than Sandiago21/llama-13b-hf-prompt-answering.