Suraj
|
d1d08f9b82
Update promptguard model-id
|
hai 1 ano |
Suraj
|
308026aad5
Adds tentative llamaguard HF model id, eos_token_id for model.generate
|
hai 1 ano |
Matthias Reso
|
0920b1a415
Fix quantization for inference
|
hai 1 ano |
Matthias Reso
|
b36830fdf6
Fix reading in stdin for chat_completion, remove padding as we're feeding single samples
|
hai 1 ano |
Matthias Reso
|
f0aa8e31ca
Update url
|
hai 1 ano |
Matthias Reso
|
9db61e5235
Refactored infeence to allow multiple requests through gradio
|
hai 1 ano |
Thomas Robinson
|
fd9f52f710
Modify prompt_format_utils with changes necessary for Llama Guard 3 (#1)
|
hai 1 ano |
Cyrus Nikolaidis
|
0c57646481
Prompt Guard Tutorial
|
hai 1 ano |
Suraj Subramanian
|
d3d2cadc4d
Update links in README.md (#589)
|
hai 1 ano |
Suraj Subramanian
|
7dcc7307d8
Fix relative links to images (#596)
|
hai 1 ano |
Suraj Subramanian
|
a4b6a55aaf
Fix broken image link (#597)
|
hai 1 ano |
Suraj Subramanian
|
5b3aaa038c
Fix broken image link
|
hai 1 ano |
Suraj Subramanian
|
78b4a7fcff
Fix relative links to images
|
hai 1 ano |
Hamid Shojanazeri
|
808a3f7a0c
Adding support for FSDP+Qlora. (#572)
|
hai 1 ano |
Jeff Tang
|
ba447971f0
Port of DLAI LlamaIndex Agent short course lessons 2-4 to use Llama 3 (#594)
|
hai 1 ano |
Jeff Tang
|
935ad46a0d
wordlist update for DLAI LlamaIndex Agent short course
|
hai 1 ano |
Jeff Tang
|
af8838463e
added lesson summary in each notebook and README
|
hai 1 ano |
Jeff Tang
|
aaeba04bd6
README update
|
hai 1 ano |
Jeff Tang
|
353ceaae74
fix of cell order issue for L3
|
hai 1 ano |
dongwang218
|
ed3136f117
Update hf weight conversion script to llama 3 (#551)
|
hai 1 ano |
Kai Wu
|
f6617fb86a
changed --pure_bf16 to --fsdp_config.pure_bf16 and corrected "examples/" path (#587)
|
hai 1 ano |
Kai Wu
|
5739231b14
rebased to main, and changed readme
|
hai 1 ano |
Kai Wu
|
81e8a1374a
Merge branch 'main' into raft
|
hai 1 ano |
Jeff Tang
|
2e4ea5b728
cell cleanup
|
hai 1 ano |
Jeff Tang
|
0fef52e846
README links fixed
|
hai 1 ano |
Jeff Tang
|
ebbf362576
L4 - replace groq with fireworks to fix rate limit
|
hai 1 ano |
Jeff Tang
|
945175a2ea
l3 cleanup
|
hai 1 ano |
Jeff Tang
|
b585e1f211
L2 llm fix - use fireworks llama 3 to overcome the groq rate limit
|
hai 1 ano |
Jeff Tang
|
c87fb189f7
Building_Agentic_RAG_with_Llamaindex L2,3,4 and README
|
hai 1 ano |
Jeff Tang
|
7bb72efcc8
colab links fixed for dlai agents notebooks (#593)
|
hai 1 ano |