TechQA.

Question

Is it possible to fine tune or use RAG on the CoreML version of Llama2?

score 202 · Answer 1 · 2023-10-13 16:11:26

1

Answer

202

Views

Is it possible to fine tune or use RAG on the CoreML version of Llama2?

202 views Asked by Mike Ike At 13 October 2023 at 16:11

score 1716 · Answer 2 · 2024-11-23 18:12:56

Compare two strings by meaning using LLMs

1.7k views Asked by root At 23 November 2024 at 18:12

score 307 · Answer 3 · 2024-11-22 20:16:53

Implementation (and working) differences between AutoModelForCausalLMWithValueHead vs AutoModelForCausalLM?

307 views Asked by Deshwal At 22 November 2024 at 20:16

score 103 · Answer 4 · 2023-10-18 07:09:33

How do I know the right data format for different LLMs finetuning？

103 views Asked by John At 18 October 2023 at 07:09

score 27 · Answer 5 · 2023-10-16 07:55:20

I am trying to make a product which will reformat the answer using the question and Sql_answer as data

27 views Asked by S_K At 16 October 2023 at 07:55

score 271 · Answer 6 · 2023-10-10 06:39:16

CUDA OutOfMemoryError but free memory is always half of required memory in error message

271 views Asked by olivarb At 10 October 2023 at 06:39

score 766 · Answer 7 · 2024-11-22 07:24:52

Query with my own data using langchain and pinecone

766 views Asked by javascript-wtf At 22 November 2024 at 07:24

score 362 · Answer 8 · 2024-11-25 09:12:16

Could not find a version that satisfies the requirement python-magic-bin

362 views Asked by Debrup Paul At 25 November 2024 at 09:12

score 543 · Answer 9 · 2023-10-14 21:28:49

Any possibility to increase performance of querying chromadb persisted locally

543 views Asked by mlee_jordan At 14 October 2023 at 21:28

score 39 · Answer 10 · 2024-11-23 11:02:17

Grid based decision making with Llama 2

39 views Asked by skvp At 23 November 2024 at 11:02

TechQA.

List Question

Is it possible to fine tune or use RAG on the CoreML version of Llama2?

Compare two strings by meaning using LLMs

Implementation (and working) differences between AutoModelForCausalLMWithValueHead vs AutoModelForCausalLM?

How do I know the right data format for different LLMs finetuning？

I am trying to make a product which will reformat the answer using the question and Sql_answer as data

CUDA OutOfMemoryError but free memory is always half of required memory in error message

Query with my own data using langchain and pinecone

Could not find a version that satisfies the requirement python-magic-bin

Any possibility to increase performance of querying chromadb persisted locally

Grid based decision making with Llama 2

Popular Questions

Popular Tags

Trending Questions