1,747 questions
0
votes
0
answers
11
views
LangGraph course_title and course_description mismatch
over the past few days I've been working with LangGraph, and I'm still new to it. While learning, I created a LangGraph agent that generates a course based on the user_thought and targeted_audience. ...
- 1
-1
votes
0
answers
17
views
How to preserve context across multiple messages using Google Genkit with Gemini 1.5 Flash?
I'm building a portfolio website with a chatbot assistant using the following stack:
Framework: Next.js 15 (App Router)
Language: TypeScript
AI: Google Genkit with Gemini 1.5 Flash via API
Email ...
-1
votes
0
answers
27
views
How to adapt domain of a VLM? [closed]
What I want to do is to adapt one of the models (Qwen/Qwen2.5-VL-3B-Instruct or Qwen/Qwen2.5-VL-7B-Instruct) to food domain. I may be wring in choosing the model, correct me in that case, but those ...
- 131
2
votes
1
answer
46
views
Running a Flask python Function give me : 'str' object has no attribute 'copy'
I'm working with a LLM project where i have a PDF file that is being processed with LamaIndexParse , when i upload the file the api for parsing works fine then the server print the error :
INFO:...
- 21
0
votes
0
answers
19
views
Assistant `content` format when hyper tuning an LLM with structured output
I'm saving data that I can then use to hyper tune a model with the OpenAI API. In the documentation they say they want the expected output to have the "assistant" role. That is fine but they ...
- 5,674
0
votes
1
answer
44
views
AWS SageMaker - Custom Inference With HuggingFace Model
For context, I'm currently working in a JupyterLab space in SageMaker studio.
My goal is to deploy a HuggingFace Llama model for batch transform inference. The data I will be passing in to the LLM is ...
- 27
-2
votes
0
answers
22
views
Did GPT-3 utilize both causal and locally banded attention masks simultaneously? [closed]
Did GPT-3 utilize both causal and locally banded attention masks simultaneously?
I have seen the paper from OpenAI which titled with "Language Models are Few-Shot Learners"
One page 8 in the ...
0
votes
0
answers
22
views
Custom NER to extract header, request and response from API document
I'm trying to extract API integration parameters like Authorization headers, query params, and request body fields from API documentation. This is essentially a custom NER task.
I’ve experimented with ...
- 1
-2
votes
0
answers
45
views
How to make a fast and accurate relevant data extraction for a chatbot? [closed]
I'm working on a property management assistant that needs to search through a database containing information about apartments, amenities, services, contact info, etc., but I'm struggling with ...
- 35
-1
votes
1
answer
33
views
Fine tuning with LoRA: q_proj/k_proj/v_proj/o_proj [closed]
Recently, I've been fine-tuning a large language model (LLM) using LoRA.
I'm wondering what the term target_modules refers to.
What are the differences between q_proj, k_proj, v_proj, and o_proj?
...
- 3
0
votes
2
answers
125
views
Two strings are spelled exactly the same, but are not equal
I have a PDF where I'm trying to extract a table. I'm using the Camelot package, but the package is not able to properly extract the foreign text.
Table from PDF
So I'm using Camelot to extract ...
1
vote
1
answer
62
views
Trained Huggingface EncoderDecoderModel.generate() produces only bos-tokens
I am working on a Huggingface transformers EncoderDecoderModel consisting of a frozen BERT-Encoder (answerdotai-ModernBERT-base) and a trainable GPT2-Decoder. Due to the different architectures for ...
- 119
-1
votes
0
answers
44
views
How to increase context size of nomic embed text model? [closed]
I'm using ollama to run a nomic-embed-text-v1.5 for generate embeddins.
As I know, nomic-embed-text can support up 8192 tokens context size.
And the num_ctx is set to 8192 when download the model by ...
- 111
-2
votes
0
answers
44
views
How to fine-tune a good lightweight Vision models [closed]
I want to fine-tune Vision models mainly one's from the huggingface or through APIs. I want to fine-tune pre-trained models based on my dataset which can give Image results to Text inputs.
I tried ...
-7
votes
0
answers
73
views
How to import bitsandbytes in google colab [closed]
I import the latest version of bitesandbytes but it is having some conflicts
!pip install bitsandbytes==0.41.2, this is the command that I ran, but isn't working. Sometimes some other package is not ...
