Spell Blade is a chat and general capability finetuned upgrade to Llama 2, focused on improving conversational quality as well as supplementing technical capability.

Performs solidly as-is, user satisfaction will be optimized with further finetuning.

Most training data utilizes the [INST][/INST] chat format.

This is a 'legacy model' offered primarily for reference purposes. I recommend Llama 3 over this model for general use.

Downloads last month
15
Safetensors
Model size
69B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for sequelbox/Llama2-70B-SpellBlade

Quantizations
2 models