Instructions to use AhiskaAI/AhiskaAI-308m-Instruct-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AhiskaAI/AhiskaAI-308m-Instruct-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="AhiskaAI/AhiskaAI-308m-Instruct-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AhiskaAI/AhiskaAI-308m-Instruct-v0.2")
model = AutoModelForCausalLM.from_pretrained("AhiskaAI/AhiskaAI-308m-Instruct-v0.2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AhiskaAI/AhiskaAI-308m-Instruct-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AhiskaAI/AhiskaAI-308m-Instruct-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AhiskaAI/AhiskaAI-308m-Instruct-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AhiskaAI/AhiskaAI-308m-Instruct-v0.2

SGLang

How to use AhiskaAI/AhiskaAI-308m-Instruct-v0.2 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 "AhiskaAI/AhiskaAI-308m-Instruct-v0.2" \
    --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": "AhiskaAI/AhiskaAI-308m-Instruct-v0.2",
		"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 "AhiskaAI/AhiskaAI-308m-Instruct-v0.2" \
        --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": "AhiskaAI/AhiskaAI-308m-Instruct-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AhiskaAI/AhiskaAI-308m-Instruct-v0.2 with Docker Model Runner:
```
docker model run hf.co/AhiskaAI/AhiskaAI-308m-Instruct-v0.2
```

YunusEmreSaidoglu commited on 8 days ago

Commit

1ecf116

verified ·

1 Parent(s): 83677bc

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -8

README.md CHANGED Viewed

@@ -4,19 +4,18 @@ language:
 - tr
 pipeline_tag: text-generation
 tags:
 - slm
-- base-model
-- causal-lm
-- pre-trained
 - tr-llm
-- Ahıska
-- AhiskaTurks
-- MeskhetianTurks
-- AhıskaTürkleri
 library_name: transformers
 ---
 # AhiskaAI-308m-IT-v0.2
 AhiskaAI-308m-IT-v0.2 is the instruction-tuned version of our 308M parameter Small Language Model. Fine-tuned on 16,000+ curated Turkish instruction-response pairs, it is designed to provide stronger conversational ability and improved instruction following while remaining efficient enough to run on consumer hardware.

 - tr
 pipeline_tag: text-generation
 tags:
+- instruct
+- chat
+- conversational
+- fine-tuned
 - slm
+- llama
 - tr-llm
+- Ahiska
 library_name: transformers
 ---
 # AhiskaAI-308m-IT-v0.2
 AhiskaAI-308m-IT-v0.2 is the instruction-tuned version of our 308M parameter Small Language Model. Fine-tuned on 16,000+ curated Turkish instruction-response pairs, it is designed to provide stronger conversational ability and improved instruction following while remaining efficient enough to run on consumer hardware.