Instructions to use Nehc/AGIRussia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nehc/AGIRussia with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Nehc/AGIRussia")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Nehc/AGIRussia") model = AutoModelForCausalLM.from_pretrained("Nehc/AGIRussia", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Nehc/AGIRussia with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Nehc/AGIRussia" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Nehc/AGIRussia", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Nehc/AGIRussia
- SGLang
How to use Nehc/AGIRussia 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 "Nehc/AGIRussia" \ --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": "Nehc/AGIRussia", "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 "Nehc/AGIRussia" \ --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": "Nehc/AGIRussia", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Nehc/AGIRussia with Docker Model Runner:
docker model run hf.co/Nehc/AGIRussia
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,15 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- ru
|
| 4 |
+
widget:
|
| 5 |
+
- text: "<IN>Как нам все-таки сделать AGI?\n<OUT>"
|
| 6 |
+
metrics:
|
| 7 |
+
- loss: 3.3
|
| 8 |
+
- perplexity: 25.7528
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
Start from sberbank-ai/rugpt3medium_based_on_gpt2 and finetuning on AGIRussia chats (russian).
|
| 12 |
+
|
| 13 |
+
On this moment - only 3 epoch (perplexity falls reasons)
|
| 14 |
+
|
| 15 |
+
on progress...
|