 Matthias Reso
|
190d543b53
Add fp8 references
|
пре 7 месеци |
|
Matthias Reso
|
c167945448
remove 405B ft doc
|
пре 7 месеци |
|
Matthias Reso
|
b0b4e16aec
Update docs/multi_gpu.md
|
пре 7 месеци |
 Suraj
|
a81524c27c
spellcheck appeasement
|
пре 7 месеци |
|
Suraj
|
7296833d43
Add codeshield to requirements
|
пре 7 месеци |
|
Suraj
|
7cac948093
Update special tokens table and URL
|
пре 7 месеци |
|
Suraj
|
88167d59ca
Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into main
|
пре 7 месеци |
|
Suraj
|
a9e8f810e7
Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into hf_model_id
|
пре 7 месеци |
|
Matthias Reso
|
e2f77dbc21
fix quant config
|
пре 7 месеци |
|
Matthias Reso
|
6ef9a78458
Fix issues with quantization_config == None
|
пре 7 месеци |
|
Matthias Reso
|
b319a9fb8c
Fix lint issue
|
пре 7 месеци |
|
Matthias Reso
|
a3fd369127
Ref from infernce recipes to vllm for 405B
|
пре 7 месеци |
|
Matthias Reso
|
a8f2267324
Added multi node doc to multigpu_finetuning.md
|
пре 7 месеци |
|
Matthias Reso
|
afb3b75892
Add 405B + QLoRA + FSDP to multi_gpu.md doc
|
пре 7 месеци |
|
Matthias Reso
|
939c88fb04
Add 405B + QLoRA ref to LLM finetung
|
пре 7 месеци |
|
Matthias Reso
|
d2fd9c163a
Added doc for multi-node vllm inference
|
пре 7 месеци |
 Thomas Robinson
|
1a183c0a5e
Introduce Llama guard customization notebook and associated dataset loader example
|
пре 7 месеци |
 Cyrus Nikolaidis
|
301e51a340
Merge branch 'main' of github.com:meta-llama/llama-recipes-alpha
|
пре 7 месеци |
|
Cyrus Nikolaidis
|
883def17f0
Prompt Guard Inference for long strings
|
пре 7 месеци |
 Suraj Subramanian
|
0d00616b34
Move MediaGen notebook to octoai folder (#601)
|
пре 7 месеци |
|
Suraj Subramanian
|
5a9858f0f0
Update README.md to remove mediagen reference
|
пре 7 месеци |
|
Suraj Subramanian
|
5a878654ec
Move MediaGen notebook to octoai folder
|
пре 7 месеци |
|
Suraj
|
4be3eb0d17
Updates HF model_ids and readmes for 3.1
|
пре 7 месеци |
|
Matthias Reso
|
c9ae014459
Enable pipeline parallelism through use of AsyncLLMEngine in vllm inferecen + enable use of lora adapter
|
пре 7 месеци |
|
Suraj
|
d1d08f9b82
Update promptguard model-id
|
пре 7 месеци |
|
Suraj
|
308026aad5
Adds tentative llamaguard HF model id, eos_token_id for model.generate
|
пре 7 месеци |
|
Matthias Reso
|
0920b1a415
Fix quantization for inference
|
пре 7 месеци |
|
Matthias Reso
|
b36830fdf6
Fix reading in stdin for chat_completion, remove padding as we're feeding single samples
|
пре 7 месеци |
|
Matthias Reso
|
f0aa8e31ca
Update url
|
пре 7 месеци |
|
Matthias Reso
|
9db61e5235
Refactored infeence to allow multiple requests through gradio
|
пре 7 месеци |
