Text Generation
Transformers
ONNX
Safetensors
PyTorch
Russian
transformer
fill-mask
chat
russian
easyformer
custom_code
conversational
Eval Results (legacy)
Instructions to use OpenRussianAI/andrey with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenRussianAI/andrey with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenRussianAI/andrey", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelWithLMHead model = AutoModelWithLMHead.from_pretrained("OpenRussianAI/andrey", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OpenRussianAI/andrey with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenRussianAI/andrey" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRussianAI/andrey", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/OpenRussianAI/andrey
- SGLang
How to use OpenRussianAI/andrey 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 "OpenRussianAI/andrey" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRussianAI/andrey", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "OpenRussianAI/andrey" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRussianAI/andrey", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use OpenRussianAI/andrey with Docker Model Runner:
docker model run hf.co/OpenRussianAI/andrey
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
language:
|
| 4 |
- ru
|
|
@@ -18,6 +17,28 @@ datasets:
|
|
| 18 |
- custom
|
| 19 |
model_type: transformer
|
| 20 |
base_model: OpenRussianAI/andrey
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
---
|
| 22 |
|
| 23 |
# Andrey — EasyFormer 3.65M
|
|
@@ -46,18 +67,6 @@ Andrey — компактный русскоязычный чат-бот на с
|
|
| 46 |
| Токенизатор | BPE, vocab 1412 |
|
| 47 |
| Weight tying | lm_head ↔ tok_emb |
|
| 48 |
|
| 49 |
-
## Eval results
|
| 50 |
-
|
| 51 |
-
| Метрика | Значение |
|
| 52 |
-
|---|---|
|
| 53 |
-
| Train loss | 0.60 |
|
| 54 |
-
| Val loss | 0.98 |
|
| 55 |
-
| idk_acc | 95.6% |
|
| 56 |
-
| Perplexity (val) | 2.66 |
|
| 57 |
-
| Шагов | 8000 |
|
| 58 |
-
| Диалогов | 3895 |
|
| 59 |
-
|
| 60 |
-
idk_acc — точность на вопросах-ловушках, где правильный ответ — «не знаю».
|
| 61 |
|
| 62 |
## Быстрый старт
|
| 63 |
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- ru
|
|
|
|
| 17 |
- custom
|
| 18 |
model_type: transformer
|
| 19 |
base_model: OpenRussianAI/andrey
|
| 20 |
+
model-index:
|
| 21 |
+
- name: Andrey
|
| 22 |
+
results:
|
| 23 |
+
- task:
|
| 24 |
+
type: text-generation
|
| 25 |
+
name: Text Generation
|
| 26 |
+
dataset:
|
| 27 |
+
type: custom
|
| 28 |
+
name: Andrey-Dataset-v2
|
| 29 |
+
metrics:
|
| 30 |
+
- name: Train Loss
|
| 31 |
+
type: loss
|
| 32 |
+
value: 0.60
|
| 33 |
+
- name: Val Loss
|
| 34 |
+
type: loss
|
| 35 |
+
value: 0.98
|
| 36 |
+
- name: Perplexity
|
| 37 |
+
type: perplexity
|
| 38 |
+
value: 2.66
|
| 39 |
+
- name: IDK Accuracy
|
| 40 |
+
type: accuracy
|
| 41 |
+
value: 95.6
|
| 42 |
---
|
| 43 |
|
| 44 |
# Andrey — EasyFormer 3.65M
|
|
|
|
| 67 |
| Токенизатор | BPE, vocab 1412 |
|
| 68 |
| Weight tying | lm_head ↔ tok_emb |
|
| 69 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
## Быстрый старт
|
| 72 |
|