Update inference-cache-config/llama-variants.json

Rename inference-cache-config/llama2.json to inference-cache-config/llama2-7b-13b.json

Create llama2-70b.json

Rename inference-cache-config/llama3.json to inference-cache-config/llama3-8b.json

Create llama3-70b.json

Create mixtral.json

Add more batch_size for mistral on smaller instances

Update Mistral cached configurations

Use princeton-nlp/Sheared-LLaMA-1.3B as a test model

Remove llama2 7B config for 24 cores

Update inference-cache-config/llama3.json

Update inference-cache-config/llama3.json

Create llama3.json

Rename inference-cache-config/llama.json to inference-cache-config/llama2.json

Add more gpt2 configurations

Add more llama config

Add Mistral-v2

Create stable-diffusion.json (#43)

Remove SalesForce embedding model

Add Zephyr to mistral variants

Remove variants from main mistral config

Add mistral most popular variants

Add most popular llama variants

Added teknium/OpenHermes-2.5-Mistral-7B

Added Llama-70b batch_size 4 to inference cache

Create mistral.json

Create gpt2.json

Create inference-cache-config/llama.json