README.md

---
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
pipeline_tag: text-generation
tags:
- text-generation-inference
---
> [!WARNING]
> At the time of this release, llama.cpp did not support the rope scaling required for full context (limit is 8192). Soon this will be updated for full 128K functionality.  
> Depriciated models still listed do not have 128k mark.  
  
> [!NOTE]
> The new release of llama.cpp and transformers have been applied and the gguf was tested.  
> [Meta-Llama-3.1-8B-Instruct-128k](https://huggingface.co/3Simplex/Meta-Llama-3.1-8B-Instruct-gguf/blob/main/Meta-Llama-3.1-8B-Instruct-128k-Q4_0.gguf)  
> You will need to update llama.cpp and transformers to use the full context.  

![image/png](https://cdn-uploads.huggingface.co/production/uploads/645e666bb5c9a8666d0d99c5/9T9q6k90ZGa5EJKeSMbru.png)


## Prompt Template

```
<|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|>
```

```
<|start_header_id|>user<|end_header_id|>

{user_input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{assistant_response}
```

## 128k Context Length
"llama.context_length": 131072