fix: make `eos_token`/`pad_token` overridable and add `pickle` support

GGUF Q5_K_M quantize

FP16 GGUF file

fix: add max's latest mt-bench radar plot

fix: stablelm-zephyr-3b rank order in mt-bench

fix: remove alpaca eval mention

Update config.json

feat(tokenizer): expose merge ranks and special tokens for GGUF

Update README.md

fix: intended usage

add: mt-bench plot

fix: remove stale OpenVino mention

update(code): fix tokenizer loading

Rename README.md to update(code): fix tokenizer loading

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Add `flash-attn v2` support

Upload LICENSE

Create README.md

Upload tokenizer

Upload StableLMEpochForCausalLM

initial commit