Text Generation
Transformers
English
ai-personas
digital-twins
episodic-memory
emotional-continuity
session-handoff
llm-agents
self-authored-memory
persona-continuity
Instructions to use Transcrypto/yesterday-json with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Transcrypto/yesterday-json with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Transcrypto/yesterday-json")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Transcrypto/yesterday-json", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Transcrypto/yesterday-json with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Transcrypto/yesterday-json" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Transcrypto/yesterday-json", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Transcrypto/yesterday-json
- SGLang
How to use Transcrypto/yesterday-json with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Transcrypto/yesterday-json" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Transcrypto/yesterday-json", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Transcrypto/yesterday-json" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Transcrypto/yesterday-json", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Transcrypto/yesterday-json with Docker Model Runner:
docker model run hf.co/Transcrypto/yesterday-json
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,27 +1,24 @@
|
|
| 1 |
-
````markdown
|
| 2 |
---
|
| 3 |
license: cc-by-4.0
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
library_name: transformers
|
| 15 |
language:
|
| 16 |
-
|
| 17 |
---
|
| 18 |
|
| 19 |
# yesterday.json — Giving AI Personas Episodic Memory
|
| 20 |
|
| 21 |
A lightweight episodic memory architecture where AI personas write emotional state snapshots for their future selves, enabling continuity across otherwise stateless sessions.
|
| 22 |
|
| 23 |
-
---
|
| 24 |
-
|
| 25 |
## Overview
|
| 26 |
|
| 27 |
Modern AI personas reset emotionally every session. Existing memory systems preserve facts and conversation history, but rarely preserve emotional residue, unresolved internal state, or continuity of subjective experience.
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-4.0
|
| 3 |
pipeline_tag: text-generation
|
| 4 |
tags:
|
| 5 |
+
- ai-personas
|
| 6 |
+
- digital-twins
|
| 7 |
+
- episodic-memory
|
| 8 |
+
- emotional-continuity
|
| 9 |
+
- session-handoff
|
| 10 |
+
- llm-agents
|
| 11 |
+
- self-authored-memory
|
| 12 |
+
- persona-continuity
|
| 13 |
library_name: transformers
|
| 14 |
language:
|
| 15 |
+
- en
|
| 16 |
---
|
| 17 |
|
| 18 |
# yesterday.json — Giving AI Personas Episodic Memory
|
| 19 |
|
| 20 |
A lightweight episodic memory architecture where AI personas write emotional state snapshots for their future selves, enabling continuity across otherwise stateless sessions.
|
| 21 |
|
|
|
|
|
|
|
| 22 |
## Overview
|
| 23 |
|
| 24 |
Modern AI personas reset emotionally every session. Existing memory systems preserve facts and conversation history, but rarely preserve emotional residue, unresolved internal state, or continuity of subjective experience.
|