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
Add DeepSWE-v1.1 leaderboard result (90.3%, 102/113)
Browse files- .eval_results/deep-swe.yaml +10 -0
.eval_results/deep-swe.yaml
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: datacurve/deep-swe
|
| 3 |
+
task_id: deep_swe
|
| 4 |
+
value: 90.3
|
| 5 |
+
date: "2026-11-02"
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/datasets/PCL-RSI-lab/DeepSWE-v1.1-Evaluation-Evidence
|
| 8 |
+
name: DeepSWE-v1.1 evaluation evidence (113 instances)
|
| 9 |
+
user: PCL-RSI-lab
|
| 10 |
+
notes: "Seshat/MetaEvo + GLM-5.3; DeepSWE-v1.1 (113), resolve rate 102/113=90.3%"
|