yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-03 19:30:26 +00:00
Code Issues Packages Projects Releases Wiki Activity
508 Commits 11 Branches 0 Tags
Commit Graph

508 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
rasbt
a796b9d657 explain truncation in ch05 2024-06-12 19:50:11 -05:00
rasbt
8fa64806fc dim-consistency 2024-06-12 19:43:25 -05:00
Sebastian Raschka
8d3e58ff81 check gpt files (#208) 2024-06-12 07:19:10 -05:00
Daniel Kleine
e5c3c5ce99 minor bug fixes (#207) 
* fixed path arg for create_dataset_csvs()

* updated assign_check() to remove user warning
 2024-06-12 06:27:56 -05:00
rasbt
b2ff989174 distinguish better between main chapter code and bonus materials 2024-06-11 21:07:42 -05:00
Daniel Kleine
79210eb393 fixes for code (#206) 
* updated .gitignore

* removed unused GELU import

* fixed model_configs, fixed all tensors on same device

* removed unused tiktoken

* update

* update hparam search

* remove redundant tokenizer argument

---------

Co-authored-by: rasbt <mail@sebastianraschka.com>
 2024-06-11 20:59:48 -05:00
Sebastian Raschka
e91718f1e7 Add eos token to each response (#205) 
* add eos token to each response

* remove figure
 2024-06-11 08:57:12 -05:00
rasbt
cbbd4c5600 add performance of llama 3 models for reference 2024-06-10 18:21:58 -05:00
Daniel Kleine
9a81230968 ch07 fixes (#204) 
* updated .gitginore for ch07

* fixed extract_response()
 2024-06-10 17:31:13 -05:00
rasbt
029efee920 reorg first section 2024-06-10 08:20:12 -05:00
rasbt
b9ed5811c3 fix gradient comment 2024-06-09 20:23:18 -05:00
Sebastian Raschka
c3c7e64a63 ch07 first draft (#203) 2024-06-09 10:35:26 -05:00
rasbt
f0e4c99bc3 fix typo in comment 2024-06-09 06:14:02 -05:00
rasbt
e1adeb14f3 add allowed_special={"<|endoftext|>"} 2024-06-09 06:04:02 -05:00
Sebastian Raschka
40ba3a4068 Remove leftover instances of self.tokenizer (#201) 
* Remove leftover instances of self.tokenizer

* add endoftext token
 2024-06-08 14:57:34 -05:00
Sebastian Raschka
98d23751f7 Explain value truncation in some figures (#199) 
* clarify truncation

* typo fix
 2024-06-08 13:24:37 -05:00
rasbt
d4dba08922 make error more explicit 2024-06-08 13:21:40 -05:00
rasbt
a6113fcd33 clarify truncation 2024-06-08 13:13:43 -05:00
rasbt
b80e7804b3 add instruction dataset 2024-06-08 10:38:41 -05:00
Sebastian Raschka
517d86e58e Add A.1 and A.2 solutions (#198) 
* add A.1 and A.2 solutions

* fix links
 2024-06-08 09:50:01 -05:00
rasbt
fbecc2b48b remove redundant file 2024-06-07 08:37:46 -05:00
Daniel Kleine
42ecfc1c81 fixed code (#197) 2024-06-07 06:52:05 -05:00
rasbt
017f73d50c update ollama instructions 2024-06-06 21:03:40 -05:00
Sebastian Raschka
de36026e5a correlation analysis (#196) 2024-06-06 09:15:08 -05:00
rasbt
9e257212b2 explain ollama serve command 2024-06-06 06:42:54 -05:00
Daniel Kleine
e637393056 updated Dockerfile and Additional Classification Finetuning Experiments (#195) 
* accuracy to .2f

* added curl
 2024-06-05 20:17:49 -05:00
rasbt
1efd9313b1 remove empty cell 2024-06-05 18:18:16 -05:00
Sebastian Raschka
429cde81b5 Merge pull request #193 from rasbt/ollama-eval 
Ollama-based model evaluation
 2024-06-05 08:26:06 -05:00
Sebastian Raschka
1c7c937602 Merge branch 'main' into ollama-eval 2024-06-05 08:23:45 -05:00
rasbt
9f8c3f2b35 Ollama-based model evaluation 2024-06-05 08:21:28 -05:00
Sebastian Raschka
cdb7bf71df remove redundant dependency 2024-06-04 20:54:19 -05:00
rasbt
c97c717a7b remove redundant import 2024-06-04 07:11:12 -05:00
rasbt
089dfb756a restore file 2024-06-03 07:17:56 -05:00
rasbt
d51099a9e7 add number of workers to data loader 2024-06-03 07:12:47 -05:00
rasbt
5a1e0eecce fix learning rate scheduler 2024-06-03 07:06:42 -05:00
rasbt
5adc6a8f69 easier to read tensor formatting 2024-06-02 21:08:35 -05:00
rasbt
20f1ef553c update figure 2.13 2024-06-01 09:38:33 -05:00
Sebastian Raschka
64fdb4a249 Merge pull request #189 from rasbt/kuutsav/main 
Fixed possibly wrong token ids in ch05.ipynb plus update the loss
 2024-05-31 08:06:57 -05:00
rasbt
f7e528fca6 update loss 2024-05-31 07:30:57 -05:00
Kumar Utsav
b48d436bfc Update ch05.ipynb 
Fixed incorrect token ids
 2024-05-29 20:34:23 +05:30
Sebastian Raschka
688df76bc0 Merge pull request #184 from rasbt/api-key-approach 
Change API key retrieval approach
 2024-05-27 08:47:04 -04:00
rasbt
c0f564ee87 update mha dim 2024-05-27 07:46:29 -05:00
rasbt
9a4861ee7f revert 2024-05-27 07:37:53 -05:00
rasbt
f86a929665 revert unnecessary changes 2024-05-27 07:37:06 -05:00
rasbt
134334ce21 Revert "Revert "newline"" 
This reverts commit 6aa2a587d22105910bd6f07c6c79a5abf83a5eb6.
 2024-05-27 07:32:45 -05:00
rasbt
6aa2a587d2 Revert "newline" 
This reverts commit 9eeeb67329f6ee0ee562a716586722bf00d68bb8.
 2024-05-27 07:32:22 -05:00
rasbt
9eeeb67329 newline 2024-05-27 07:30:27 -05:00
rasbt
474ad17546 Update API approach and add progress bar 2024-05-27 07:29:06 -05:00
rasbt
b2ad4fb0d6 add comment 2024-05-27 07:18:07 -05:00
rasbt
36e169f3ab add keys 2024-05-27 07:13:59 -05:00