Use this tag for questions about large language models (LLM), trained deep-learning artificial intelligence algorithms that interpret and generate natural language text.
Questions tagged [large-language-model]
118 questions
0
votes
0 answers
Getting inconsistent response when using pandas_dataframe_agent and taking too much time for execution
def create_pandas_dataframe_agent(
llm:llm,
df:df,
#callback_manager: Optional[BaseCallbackManager] = None,
prefix: str=PREFIX,
suffix: str= SUFFIX,
input_variables:str= None,
verbose:bool=False,
…
0
votes
1 answer
How to compile the llm library with nix
I tried to install the llm library with nix.
You just have to do that:
git clone https://github.com/rustformers/llm.git
nix build
Unfortunately it fails:
error: builder…
Pierre-olivier Gendraud
- 1,545
- 1
- 8
- 33
0
votes
0 answers
How fix 'type=value_error' when loading a wizard-vicuna model to PrivateGPT?
I'm following a tutorial to install PrivateGPT and be able to query with a LLM about my local documents.
I'm using a wizard-vicuna-13B.ggmlv3.q4_1.bin model, and as per the README.md adjusted the example.env file settings to a new .env…
pol0
- 33
- 5
0
votes
0 answers
GPU out of memory in Jupyter
My OS specs are 8GB dedicated GPU and 24GB shared GPU, I am trying to fine tune a model and I am facing CUDA out of memory errors . I am not able to use Shared memory. Is there any way to use it when my dedicated memory was full.
Code Snippet for…
Sai Ganesh
- 1
- 1
0
votes
0 answers
How to deal with "This model's maximum context length is 4097 tokens." issue in Scikit-LLM
I am trying the Scikit-LLM on a StackOverflow question dataset comprising around 7k rows. Below is the code where I train and test a Zero Shot Classifier.
X_train, X_test, y_train, y_test =
train_test_split(_soQuestions['Body'],…
renakre
- 8,001
- 5
- 46
- 99
0
votes
0 answers
Best Large Language Model for abstractive Summarization
Browsing through Huggingfaces I am not able to find any abstractive summarization model for longer texts like newsarticle, with a size of around 5000 characters.
I compared different models but none of them really worked. Mostly they are restricted…
Ollowain
- 55
- 6
0
votes
0 answers
Langchain MRKL Agent not giving useful Final Answer
Here is the code I'm using for initializing a Zero Shot ReAct Agent with some tools for fetching relevant documents from a vector database:
chat_model = ChatOpenAI(
model_name="gpt-3.5-turbo",
temperature="0",
…
0
votes
1 answer
How are LLMs assigned tasks in Python code?
I'm following Nicholas' Renotte's tutorials on VSCode, LangChain, and OpenAI using Python.
These are the codeblocks I've seen from the aforementioned tutorials, and I don't see any other lines of code that tell the AI what to do.
title_template =…
pol0
- 33
- 5
0
votes
0 answers
How do LLMs manage grammatical generation like "is a" or "is an"?
LLMs are forward generating models, generating the next word based on the previous context without having known the future words. This being the case the model shouldn't be able to know the difference between is a and is an grammatically as this…
KaranJ
- 48
- 1
- 10
0
votes
0 answers
Can I load the weight parameter on DRAM permanently and use it whenever it's needed?
I'm using HuggingFace and debugging NLLB-MoE with the VSCode debugger.
But the model parameters are so big and take so long time for a single execution.
Can I just make parameter be loaded on the CPU DRAM and use it whenever needed?
The code is…
Ryan
- 73
- 7
0
votes
1 answer
Error while installing lmql[hf] using pip: "No matching distribution found for lmql[hf]
I am trying to install lmql[hf] using the pip package manager in order to set up a local LMQL playground. Following the documentation, I ran the command pip install lmql[hf].
However, I encountered the following error:
ERROR: Ignored the following…
Pavel
- 1
- 2
0
votes
1 answer
Getting TypeError in Snowpark
Currently I am trying write vectorized UDF function in snowpark
import pandas as pd
from snowflake.snowpark.functions import pandas_udf
from snowflake.snowpark.types import StringType
@pandas_udf(
…
Sam777
- 15
- 6
0
votes
0 answers
Issue with langchain llm and huggingface. The SSL issue
I an getting an SSL when using huggingface hub when using langchain LLM. Below is the error. I tried options input my username and password and did not work.. please help
HTTPSConnectionPool(host='api-inference.huggingface.co', port=443): Max…
Nick
- 1
0
votes
1 answer
Faster initialization with config.init_device
I am running these codes
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
There is a message on the console stating...
You are using config.init_device='cpu', but…
zoomraider
- 117
- 1
- 9
0
votes
1 answer
Unsupervised fine-tuning on custom documents after the supervised fine tuning on general question-answers dataset. Will it be useful for GPT-2 model?
I know the formal way of training a GPT2 model on custom documents is to first do semi-supervised fine tuning on the text of the documents followed by supervised fine-tuning on question answers from the same documents.
But the sole purpose of…
