Comments (7)
If you're willing to manually retype the conversation history, then you can get your question answered, like so:
from alpaca.cpp.
If you're willing to manually retype the conversation history, then you can get your question answered, like so:
Thanks! I guess that'll do for now.
Hoping that it is integrated within the program itself... I don't think the original llama.cpp repo has this issue.
from alpaca.cpp.
After playing around with it some more, I'm somewhat more confused -- but I no longer think that the model doesn't have 'conversational memory'.
Also, the chat.cpp file is identical in this repo vs the one it was forked from, so that suggests that the chat logic is the same
Yet even if it can sometimes 'remember previous conversation', it does so only very intermittently, so imo your original report is basically correct, there is a lot of engineering work we can do here to improve the model's conversational memory
from alpaca.cpp.
I am working on a version that more explicitly conveys the idea to Llama that there is a single-threaded conversation and its job is only to respond to the user. Curious whether anybody else has made any kind of significant progress with this.
from alpaca.cpp.
I have also seen a few cases of indisputable conversational memory across 2 or 3 separate questions, but it's been very rare. No time to work on this myself, unfortunately, but I look forward to seeing what folks come up with to make it a properly conversational tool.
from alpaca.cpp.
I guess the biggest problem will be - the "emulated" conversational memory, i.e. when you add the whole (or just summary of) your previous conversation as a part of your prompt, will quickly hit the limit of number of tokens this model can take as an input.
This video explains it quite nicely - https://www.youtube.com/watch?v=VW5LBavIfY4&feature=youtu.be
from alpaca.cpp.
I am working on a version that more explicitly conveys the idea to Llama that there is a single-threaded conversation and its job is only to respond to the user. Curious whether anybody else has made any kind of significant progress with this.
https://github.com/deep-diver/Alpaca-LoRA-Serve
Implements a functional context system and has a demo running on a cloud instance which shows promise. My local testing shows that alpaca.cpp looks like it doesn't remember history, which makes me confused about the -c and --ctx_size params for alpaca.cpp because they clearly don't work.
Their(LoRA-Serve) implementation is targeted towards CPUs with the VRAM capacity to run these models, unlike the CPU based alpaca.cpp. Seeing it refactored for CPU applications would be nice.
from alpaca.cpp.
Related Issues (20)
- windows 10, fails to get to chat prompt HOT 8
- Issues with Monte Carlo Tree Search on alpaca.cpp
- CUDA support? HOT 3
- Input Handling HOT 1
- Segmentation Fault with 7b on Raspberry Pi 3 HOT 5
- ### Instruction: ### Response: HOT 3
- Random seed not working correctly, "too many inputs", chinese symbols?
- How to use with python HOT 1
- Can i use it on linux with nvidia gpu HOT 4
- minimum specs
- Does not perceive other languages HOT 5
- Are there any plans to add support for 13B and beyond? HOT 7
- Running very slow HOT 7
- Redpajama dataset?
- using ggml-alpaca-13b-q4.bin HOT 1
- Archive Repository HOT 1
- main: failed to load model from 'ggml-alpaca-7b-q4.bin' HOT 4
- llama_model_load: failed to open 'ggml-alpaca-7b-native-q4.bin' HOT 1
- HuggingFaceH4/starchat-alpha Cpp LLM
- Adding risc-v architecture support HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from alpaca.cpp.