Instructions to use salakash/SamKash-Tolstoy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use salakash/SamKash-Tolstoy with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B")
model = PeftModel.from_pretrained(base_model, "salakash/SamKash-Tolstoy")

Transformers

How to use salakash/SamKash-Tolstoy with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="salakash/SamKash-Tolstoy")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("salakash/SamKash-Tolstoy", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use salakash/SamKash-Tolstoy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "salakash/SamKash-Tolstoy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "salakash/SamKash-Tolstoy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/salakash/SamKash-Tolstoy

SGLang

How to use salakash/SamKash-Tolstoy 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 "salakash/SamKash-Tolstoy" \
    --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": "salakash/SamKash-Tolstoy",
		"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 "salakash/SamKash-Tolstoy" \
        --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": "salakash/SamKash-Tolstoy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use salakash/SamKash-Tolstoy with Docker Model Runner:
```
docker model run hf.co/salakash/SamKash-Tolstoy
```

Languages spoken

by mirix - opened Nov 10, 2025

Discussion

mirix

Nov 10, 2025

Does this thing speak Russian or only English?

colorfulfool

Nov 10, 2025

•

edited Nov 10, 2025

It does not speak Russian :D

Напиши рефлективный параграф о совести и судьбе в аристократической семье. 
Стаж: 7. Стоимостьparent's job: $100k/yr. Стоимостьchild's job: $150k/yr. 
Количествоchild: 3. Всего труда: 30h/wd. 
Недоразумение:parent's job income isn't enough to support the family's living expenses. 
Рекомендации:1. Find a way to support the family financially. 
2. Encourage the child to pursue a career. 
3. Provide financial assistance for transportation and housing. 
4. Offer a stipend for the child's education. 
5. Create a safe and secure environment for the child to live. 
6. Offer counseling services. 
7. Encourage the child to participate in social activities. 
8. Make the parent's job stable. 
9. Support the child's job search and integration into the family. 
10. Help

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment