Comments (6)
pandora-s-git
commented on June 2, 2024
Hi, okay so it seems there was a misunderstanding on how the prompt works. The Chat Template you are using is supposed to work like this:
<s>[INST] My Instruction.... My Text.... Or other details... [/INST]
To better understand it, see it like this: [INST] => User: and [/INST] => Assistant:.
So its equivalent of this:
<s>User: My Instruction.... My Text.... Or other details... Assistant:
I hope this answers your doupts !
from mistral-src.
Related Issues (20)
- "evaluation pipeline" public?
- [Mistral 7B mistral-7b-instruct-v0.1.Q8_0.gguf] Wrong text "quoted" while presented as real HOT 3
- Friendly Reminder while Generating the output
- Evaluation Pipeline
- Mistral's tokenizer is not optimized
- [MISTRAL AI ERROR] Mistral AI responding with Unexpected role RoleEnum.tool error HOT 2
- CUDA EXTENSION NOT INSTALLED nvcr.io/nvidia/pytorch:22.12-py3 HOT 1
- Training code HOT 1
- Question about Mixtral MLP section HOT 3
- Missing the params.json HOT 2
- Fine Tuning Mistral 7b HOT 3
- I am unable to build the vLLM Container HOT 4
- Not completing answer
- Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 804: forward compatibility was attempted on non supported HW HOT 1
- JSON response format failing to retrieve clean JSON
- Q: Why rotary embedding applied only to queries and keys?
- Did Mistral-7B-Instruct-v0.2 use Sliding Window Attention (SWA)?
- AI generates responses or conversation without any human input
- PAD token missing ? HOT 2
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 mistral-src.