702 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
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
Sebastian Raschka	68123a5433	Merge pull request #183 from superkostya/fix-mha-wrapper-class ... Fix an incorrect input dimension	2024-05-26 17:09:19 -04:00
rasbt	ec6e09136a	update pr	2024-05-26 15:38:35 -05:00
Sebastian Raschka	2088d75966	Merge branch 'main' into fix-mha-wrapper-class	2024-05-26 16:20:06 -04:00
Sebastian Raschka	3853ce48c5	Merge pull request #182 from rasbt/refine-duplicate-search ... Refine duplicate search utility function	2024-05-26 16:19:17 -04:00
Kostyantyn Borysenko	18b5724e75	Fix an incorrect input dimension	2024-05-26 13:05:07 -07:00
rasbt	5044ee2dda	fixes	2024-05-26 14:28:30 -05:00