All Questions
Tagged with large-language-model ollama
35
questions
0
votes
0
answers
22
views
Fine-tune LLM on custom schema to be used in sqlcoder, an ollama based llm
I am working on a POC to convert Natural language to SQL. I have used phi3 and now planning to use sqlcoder as part of the llm. All this are set up via ollama which I am running on docker.
The one ...
0
votes
0
answers
50
views
How should I use Llama-3 properly?
I downloaded the Meta-Llama-3-70B-Instruct model using the download.sh and the url provided by Meta email, and this is all the files in the folder.
enter image description here
And when I tried to use ...
0
votes
0
answers
97
views
The relationship between chunk_size, context length and embedding length in a Langchain RAG Framework
everyone. Currently I am working on a Langchain RAG framework using Ollama. I have a question towards the chunk size in the Document Splitter.
Now I decide to use qwen2:72b model as both embedding ...
1
vote
0
answers
202
views
LLamaIndex-ReACT agent talking to itself and hallucinating
I'm new to creating a custom ReACT agent to query my data using the RAG technique.
It turns out that my locally running LLama2 7B model(Using Ollama) does fine with questions about my data(I added the ...
-2
votes
0
answers
524
views
system Requirements for the DeepSeek-Coder-V2-Instruct
I want to know the Windows system requirements of the below versions of DeepSeek Coder V2 (236 TB and 21B AP). https://github.com/deepseek-ai/DeepSeek-Coder-V2/tree/main. I am using the system with ...
1
vote
0
answers
97
views
Error in Ollama Functions js (Error(Failed to parse a function call from ${this.llm.model} output: ${chatGenerationContent}))
Can you help me please with this , i try to use ollama to make a chat that can call tools in order to answer to the the user question, I use the same documentation in langachain langchain openai call ...
1
vote
1
answer
49
views
Mistral7b response starts with an extra leading space when streamed with Ollama
When I stream the response of mistral7b LLM with Ollama, it has an extra space to the left on the very first streamed chunk. Below is my code:
import ollama
stream = ollama.chat(
model='mistral',
...
0
votes
2
answers
106
views
ImportError: cannot import name 'Ollama' from 'llama_index.llms' (unknown location) - installing dependencies does not solve the problem
I want to learn LLMs. I run Ollama with the following Docker Compose file - it's running:
services:
ollama:
image: ollama/ollama:latest
ports:
- 11434:11434
volumes:
- ...
0
votes
1
answer
110
views
How to use Llama3?
I'm using Ollama and llama 3 to build a ChatBot. However, right now, it can't remember chat history. For example, if my first query is "tell me about the theory of relativity," and if my ...
2
votes
1
answer
1k
views
Client error '404 Not Found' for url 'http://localhost:11434/api/chat' while using ReActAgent of llama_index.core.agent
I am following this tutorial, https://youtu.be/JLmI0GJuGlY?si=eeffNvHjaRHVV6r7&t=1915, and trying to build a simple LLM agent.
I am on WSL2, Windows 11, and I am coding in VSC. I use Ollama to ...
0
votes
0
answers
77
views
How to save fine tuning LLM model?
I am doing fine-tuning of a model and then I want to save this model to convert it to the GGUF format to use in Ollama. However, when converting to the GGUF format, I get the following error: ...
0
votes
0
answers
37
views
Is there a standard pipeline to RAG workflow on LangChain?
Before going straight to the issue, I'm a begginer at using LangChain, so I wanted to incorporate it in small problems on my daily-basis so I could get the hang of it. One of them, for example, is the ...
1
vote
1
answer
320
views
How to load web articles into RAG LLM for embedding
I watched this tutorial (https://youtu.be/2TJxpyO3ei4) on setting up RAG (retrieval augmented generation) using LLMs (I used a local embedding model and a local model for queries). I want to be able ...
0
votes
1
answer
75
views
Not able to access llama3 using python
I am testing llama3 here using this simple code below
import ollama
message = "What is football"
# connect to Llama3 model
try:
response_stream = ollama.chat(
model="llama3&...
0
votes
1
answer
190
views
Using Llama_index with Mistral Model
I'm new to the field of large language models (LLMs), so I apologize if my explanation isn't clear.
I have a Mistral model running in a private cloud, and I have both the URL and the model name.
URL = ...