Edit model card

Llama-3-Groq-70B-Tool-Use-GGUF

Original Model

Prompt template:

prompt template: groq-llama3-tool

Context size:

chat_ctx_size: 8192

Run with GaiaNet:

Quantized with llama.cpp b3463

GGUF

Model size

70.6B params

Architecture

llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples

Inference API (serverless) has been turned off for this model.

Base model

Finetuned

Quantized

(6)

this model