Text Generation
Transformers
agent
rsi
recursive-self-improvement
self-evolving
metaevo
meta-knowledge
swe-bench
swe-bench-pro
deepswe
code-agent
kimi
Eval Results
Instructions to use PCL-RSI-lab/Seshat-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PCL-RSI-lab/Seshat-agent with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="PCL-RSI-lab/Seshat-agent")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("PCL-RSI-lab/Seshat-agent", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use PCL-RSI-lab/Seshat-agent with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "PCL-RSI-lab/Seshat-agent" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "PCL-RSI-lab/Seshat-agent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/PCL-RSI-lab/Seshat-agent
- SGLang
How to use PCL-RSI-lab/Seshat-agent 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 "PCL-RSI-lab/Seshat-agent" \ --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": "PCL-RSI-lab/Seshat-agent", "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 "PCL-RSI-lab/Seshat-agent" \ --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": "PCL-RSI-lab/Seshat-agent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use PCL-RSI-lab/Seshat-agent with Docker Model Runner:
docker model run hf.co/PCL-RSI-lab/Seshat-agent
Is it benchmaxxing
#1
by ArushCodes - opened
Hello @PCL-RSI-Lab ... The model looked Promising at first but Question is why are you post training a model on SWE Questions? You can use human made questions or vibe coding tasks that usually people use
Thank you for your interest in Seshat!
Just to clarify, Seshat is an agent-level self-improvement framework, not a post-trained or fine-tuned language model. We do not perform any post-training or modify the underlying model weights.
We appreciate your feedback!