-
Update inference-cache-config/llama-variants.json
dacorvo HF Staff -
Rename inference-cache-config/llama2.json to inference-cache-config/llama2-7b-13b.json
dacorvo HF Staff -
Create llama2-70b.json
dacorvo HF Staff -
Rename inference-cache-config/llama3.json to inference-cache-config/llama3-8b.json
dacorvo HF Staff -
Create llama3-70b.json
dacorvo HF Staff
-
Create mixtral.json
dacorvo HF Staff
-
Add more batch_size for mistral on smaller instances
dacorvo HF Staff -
Update Mistral cached configurations
dacorvo HF Staff
-
Use princeton-nlp/Sheared-LLaMA-1.3B as a test model
dacorvo HF Staff
-
Remove llama2 7B config for 24 cores
dacorvo HF Staff
-
Update inference-cache-config/llama3.json
dacorvo HF Staff Switch to fp16 for Llama3
-
Update inference-cache-config/llama3.json
dacorvo HF Staff
-
Create llama3.json
dacorvo HF Staff -
Rename inference-cache-config/llama.json to inference-cache-config/llama2.json
dacorvo HF Staff
-
Add more gpt2 configurations
dacorvo HF Staff -
Add more llama config
dacorvo HF Staff -
Add Mistral-v2
dacorvo HF Staff
-
Create stable-diffusion.json (#43)
philschmid +1: Jingya
-
Remove SalesForce embedding model
dacorvo HF Staff
-
Add Zephyr to mistral variants
dacorvo HF Staff -
Remove variants from main mistral config
dacorvo HF Staff -
Add mistral most popular variants
dacorvo HF Staff -
Add most popular llama variants
dacorvo HF Staff
-
Added teknium/OpenHermes-2.5-Mistral-7B
dacorvo HF Staff -
Added Llama-70b batch_size 4 to inference cache
dacorvo HF Staff
-
Create mistral.json
-
Create gpt2.json
-
Create inference-cache-config/llama.json
