01-ai/Yi-34B with tensors renamed to match standard Llama modelling code. Model can be loaded without trust_remote_code, but the tokenizer can not.

The branch llama-tokenizer uses the Llama tokenizer class as well.

Safetensors

Model size

34.4B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for chargoddard/Yi-34B-Llama

Adapters

Quantizations

Space using chargoddard/Yi-34B-Llama 1