ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Inference bug fix (#134)

Browse source 
* faster saving & inference

* Update llama.py

* Update save.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update mistral.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* fast inference

* Update llama.py

* Update save.py

* Update llama.py

* Mistral correct RoPE scaling

* Max sequence lengths

* Apache 2

* fast_linear_forward

* Update utils.py

* Update utils.py

* No print

* Update utils.py

* Update utils.py

* inference

* Update llama.py

* Fast inference RoPE

* Update llama.py

* Update llama.py

* RoPE

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* LoRA

* Fast LoRA saving

* Update llama.py

* hidden_states

* q_len == 1

* q_len issue

* Update mistral.py

* Update mistral.py

* incorrect inference

* Update to transformers 4.37

* Graceful FA2 error + torch 2.1.1

* Update mapper.py

* Update pyproject.toml

* Fix saving and bnb-4bit

* Update fast_lora.py

* Update fast_lora.py

* remove patching

* Update llama.py

* Update llama.py

* Update swiglu.py

* Repatch

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update llama.py

* Update fast_lora.py

* Update llama.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update swiglu.py

* Update fast_lora.py

* Update swiglu.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update save.py

* Update fast_lora.py

* Update utils.py

* Update llama.py

* Update fast_lora.py

* Update swiglu.py

* Update save.py

* Update save.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Revert "Update llama.py"

This reverts commit 9c9dc55bef7e71960bd48941e987e8b6239d6783.

* Update llama.py
This commit is contained in:
Daniel Han 2024-01-27 04:50:22 +11:00 • committed by GitHub
commit 092d5585b6
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/llama.py
View file

@ -234,7 +234,7 @@ def LlamaAttention_fast_forward(
bsz, q_len, _ = hidden_states.size()
# Check for inference
if past_key_value is not None and q_len == 1 and bsz == 1:
if False: #past_key_value is not None and q_len == 1 and bsz == 1:
A, past_key_value = LlamaAttention_fast_forward_inference(
self,
hidden_states,
@ -350,7 +350,7 @@ def LlamaDecoderLayer_fast_forward(
past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states
"""
bsz, q_len, hd = hidden_states.size()
if (past_key_value is not None and q_len == 1 and bsz == 1):
if False: #(past_key_value is not None and q_len == 1 and bsz == 1):
# Self Attention
residual = hidden_states
hidden_states = fast_rms_layernorm_inference(self.input_layernorm, hidden_states)