 Suraj Subramanian
|
3516a5cea7
Merge pull request #2 from meta-llama/inference_changes
|
hai 1 ano |
|
Suraj Subramanian
|
935f66f7d0
Merge branch 'main' into inference_changes
|
hai 1 ano |
 albertodepaola
|
b15bad976b
Merge pull request #8 from meta-llama/responsible_ai
|
hai 1 ano |
 Suraj
|
d28400efb5
Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into responsible_ai
|
hai 1 ano |
|
albertodepaola
|
60e3159c4e
Merge pull request #7 from meta-llama/update-prompt-template
|
hai 1 ano |
|
albertodepaola
|
c6ac7db568
Merge pull request #6 from meta-llama/hf_model_id
|
hai 1 ano |
|
Suraj
|
acf0a74297
Updates for commit review
|
hai 1 ano |
 varunfb
|
811e09d022
Merge pull request #4 from meta-llama/LG3notebook
|
hai 1 ano |
 Thomas Robinson
|
f6ad82a976
Correct model card link in llama_guard_customization_via_prompting_and_fine_tuning.ipynb
|
hai 1 ano |
|
Thomas Robinson
|
c13f636919
Updated and renamed llama_guard_customization_via_prompting_and_fine_tuning.ipynb based on feedback in PR
|
hai 1 ano |
|
Suraj
|
a46d0422cf
Add note about LG3 finetuning notebook
|
hai 1 ano |
 Matthias Reso
|
00e0b0be6c
Apply suggestions from code review
|
hai 1 ano |
|
Matthias Reso
|
190d543b53
Add fp8 references
|
hai 1 ano |
|
Matthias Reso
|
c167945448
remove 405B ft doc
|
hai 1 ano |
|
Matthias Reso
|
b0b4e16aec
Update docs/multi_gpu.md
|
hai 1 ano |
|
Suraj
|
a81524c27c
spellcheck appeasement
|
hai 1 ano |
|
Suraj
|
7296833d43
Add codeshield to requirements
|
hai 1 ano |
|
Suraj
|
7cac948093
Update special tokens table and URL
|
hai 1 ano |
|
Suraj
|
88167d59ca
Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into main
|
hai 1 ano |
|
Suraj
|
a9e8f810e7
Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into hf_model_id
|
hai 1 ano |
|
Matthias Reso
|
e2f77dbc21
fix quant config
|
hai 1 ano |
|
Matthias Reso
|
6ef9a78458
Fix issues with quantization_config == None
|
hai 1 ano |
|
Matthias Reso
|
b319a9fb8c
Fix lint issue
|
hai 1 ano |
|
Matthias Reso
|
a3fd369127
Ref from infernce recipes to vllm for 405B
|
hai 1 ano |
|
Matthias Reso
|
a8f2267324
Added multi node doc to multigpu_finetuning.md
|
hai 1 ano |
|
Matthias Reso
|
afb3b75892
Add 405B + QLoRA + FSDP to multi_gpu.md doc
|
hai 1 ano |
|
Matthias Reso
|
939c88fb04
Add 405B + QLoRA ref to LLM finetung
|
hai 1 ano |
|
Matthias Reso
|
d2fd9c163a
Added doc for multi-node vllm inference
|
hai 1 ano |
|
Thomas Robinson
|
1a183c0a5e
Introduce Llama guard customization notebook and associated dataset loader example
|
hai 1 ano |
 Cyrus Nikolaidis
|
301e51a340
Merge branch 'main' of github.com:meta-llama/llama-recipes-alpha
|
hai 1 ano |
