cafaxo / Llama2.jl

Julia package for inference and training of Llama-style language models

cafaxo/Llama2.jl Issues

Pointer to supported gguf models?
Closed 3 months ago1
Support chat templates
Updated 3 months ago1
ERROR: UndefVarError: `load_gguf_model` not defined
Closed 3 months ago1
Reproduce temp=0 llama.cpp results with some consistency.
Closed 3 months ago5
Make the quantization code less insane
Closed 3 months ago2
A GPU version of inference code
Updated 5 months ago3
Hope support more model formats
Closed 6 months ago
Support saving weights to a standard format
Updated 6 months ago1
How to find and download a suitable GGMLV3 model?
Closed 6 months ago1
Training code
Closed 6 months ago3
interrupt output
Updated 7 months ago
Support weight decay for Adam optimizer
Updated 10 months ago
ERROR: git repository not found at `https://github.com/cafaxo/Llama2.jl`
Closed a year ago3
LoRA and finetuning
Updated a year ago2
Create vocabulary from text
Updated a year ago
Speed up tokenizer
Updated a year ago
amazing speed!
Closed a year ago3
More high-level operations
Closed a year ago3
ggml model ERROR: TaskFailedException nested task error: bitcast: target type not a leaf primitive type
Closed a year ago4
Test perplexity
Updated a year ago
Quantization support
Closed a year ago5
adding prompting
Closed a year ago1
Readme
Closed a year ago
Adapt to new tokenizer.bin format
Closed a year ago