Comments (6)
I'm not able to reproduce this using llama2
and mistral
with setting seed
and temperature
through both the API and the Modelfile.
What version of ollama (ollama -v
) are you using? Can you also provide your Modelfile?
from ollama.
I'm not able to reproduce this using
llama2
andmistral
with settingseed
andtemperature
through both the API and the Modelfile.What version of ollama (
ollama -v
) are you using? Can you also provide your Modelfile?
ollama -v
ollama version is 0.1.20
cat Modelfile
FROM ./q4_0.bin
TEMPLATE """{{ if .First }}{{ .System }}{{ end }}{{ .Prompt }} [/INST]{{ .Response }} </s><s>[INST] """
SYSTEM "[INST] "
PARAMETER stop "[INST]"
PARAMETER stop "[/INST]"
PARAMETER stop "<<SYS>>"
PARAMETER stop "<</SYS>>"
PARAMETER temperature 0
PARAMETER seed 37
PARAMETER num_ctx 4096
from ollama.
Hi @mxyng, could you please take a look at the Modelfile config I provided when you get a chance?
Thanks!
from ollama.
@Fei-Wang what kind of model is q4_0.bin
? The template may be incorrect. It should probably be something like this:
[INST] {{ .System }} {{ .Prompt }} [/INST]
<s>
and </s>
shouldn't be necessary and {{ .Response }}
is (currently) ignored.
from ollama.
Hey @mxyng,
I'm working with q4_0.bin
, a finetuned llama2 model, and I've hit two snags:
-
I'm using
<s>
and</s>
as per the guide on Hugging Face (https://huggingface.co/blog/codellama#conversational-instructions). Did I get something wrong? -
Changing the ModelFile to
llama2
hasn't fixed inconsistent outputs. See the screenshot below.
Any ideas?
![Screenshot 2024-01-23 at 2 03 40 PM](https://private-user-images.githubusercontent.com/11441526/298824274-e5cd6da1-7481-46de-add0-ac70bc1f8362.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTQ4NjE0MDIsIm5iZiI6MTcxNDg2MTEwMiwicGF0aCI6Ii8xMTQ0MTUyNi8yOTg4MjQyNzQtZTVjZDZkYTEtNzQ4MS00NmRlLWFkZDAtYWM3MGJjMWY4MzYyLnBuZz9YLUFtei1BbGdvcml0aG09QVdTNC1ITUFDLVNIQTI1NiZYLUFtei1DcmVkZW50aWFsPUFLSUFWQ09EWUxTQTUzUFFLNFpBJTJGMjAyNDA1MDQlMkZ1cy1lYXN0LTElMkZzMyUyRmF3czRfcmVxdWVzdCZYLUFtei1EYXRlPTIwMjQwNTA0VDIyMTgyMlomWC1BbXotRXhwaXJlcz0zMDAmWC1BbXotU2lnbmF0dXJlPWY3NGFjNTIxMDJiMzU1NzgwN2Q1OTQ3ODA0NmY5OGIzYmI0Njk0ODcxMTFmNmVhY2E2NWY1YWMwNzFlOTc0ZTImWC1BbXotU2lnbmVkSGVhZGVycz1ob3N0JmFjdG9yX2lkPTAma2V5X2lkPTAmcmVwb19pZD0wIn0.06l1xGY1OJ2Pyk38sEf5LDS87KyiI27Z2H9q88LhFrk)
from ollama.
Closing this as a dupe of #1749
from ollama.
Related Issues (20)
- HTTPStatusError: Client error '404 Not Found' for url 'http://127.0.0.1:11434/api/chat' HOT 2
- Some Ollama models apparently affected by llama.cpp BPE pretokenization issue HOT 11
- Add LLAVA++ model HOT 1
- Normalization of output from embedding model
- Docker Build is failing because libcurl-httpd24 .so.4 cannot be loaded HOT 2
- Error "timed out waiting for llama runner to start: " on larger models. HOT 1
- model run command not rendered on mobile HOT 5
- "which/max" command line options to help with sizing.
- WithSecure quarantined ollama_llama_server.exe as harmful file / Malware HOT 2
- [Feature] Rapid Modelfile Updates HOT 1
- Support for HyperGAI/HPT1_5-Air-Llama-3-8B-Instruct-multimodal
- only 1 GPU found -- regression 1.32 -> 1.33 HOT 8
- Original 2gb and 4gb Jetson Nano Developer Kits (Not Orin Version) - GPU Possible?
- More Quants for command-r-plus Please? HOT 1
- starting the docker container stucks at "CPU has AVX2" HOT 2
- Importing a Mistral finetune into Ollama fails with `invalid file magic`
- Supports the computing power of NPUs and GPUs provided by Intel Ultra processors HOT 4
- mixtral:8x22b causes intermittent system freezes on Mac, runs very slow
- v0.1.33 can't load gemma:7b-instruct-v1.1-fp16 due to failed to create context with model HOT 4
- Add option in the install scripts to auto set OLLAMA_HOST environment variable
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 ollama.