v2 is live

add raw llama-7B model

Upload LlamaForCausalLM

add GPTQ-trained

turning inference off as the model is too large (>10 GB)

try turning on hosted inference

Add 13B GPTQ link

add improved inference options

add gptq

add - ggml tag

add GGML for fLlama 7B

make 7B model license Llama 2.

Upload LlamaForCausalLM

move up inference guide

Update README.md

Upload LlamaForCausalLM

Delete pytorch_model-00007-of-00007.bin

Delete pytorch_model-00006-of-00007.bin

Delete pytorch_model-00005-of-00007.bin

Delete pytorch_model-00004-of-00007.bin

Delete pytorch_model-00003-of-00007.bin

Delete pytorch_model-00002-of-00007.bin

Delete pytorch_model-00001-of-00007.bin

Upload LlamaForCausalLM

update dataset info

Update README.md

Upload LlamaForCausalLM

Update README.md

Delete pytorch_model-00002-of-00002.bin

Delete pytorch_model-00001-of-00002.bin

Update README.md

Update README.md

Upload LlamaForCausalLM

Upload tokenizer

Upload LlamaForCausalLM

remove space between <s> and [INST]

Update README.md

update license now that model has been updated

Upload tokenizer

Upload LlamaForCausalLM

Update README.md

add instructions on function calling

Upload tokenizer

Upload tokenizer

Upload LlamaForCausalLM

initial commit