Instructions to use kiel2/Kiel-2.2-Sol with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kiel2/Kiel-2.2-Sol with Transformers:

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

pipe = pipeline("text-generation", model="kiel2/Kiel-2.2-Sol")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kiel2/Kiel-2.2-Sol")
model = AutoModelForCausalLM.from_pretrained("kiel2/Kiel-2.2-Sol", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kiel2/Kiel-2.2-Sol with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kiel2/Kiel-2.2-Sol"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kiel2/Kiel-2.2-Sol",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kiel2/Kiel-2.2-Sol

SGLang

How to use kiel2/Kiel-2.2-Sol 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 "kiel2/Kiel-2.2-Sol" \
    --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": "kiel2/Kiel-2.2-Sol",
		"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 "kiel2/Kiel-2.2-Sol" \
        --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": "kiel2/Kiel-2.2-Sol",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kiel2/Kiel-2.2-Sol with Docker Model Runner:
```
docker model run hf.co/kiel2/Kiel-2.2-Sol
```

kiel2 commited on 29 days ago

Commit

c7f9d45

verified ·

1 Parent(s): 551ec6e

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-base_model: kiel2/KielMind-Lite
 library_name: transformers
 pipeline_tag: text-generation
 tags:
@@ -12,7 +12,7 @@ tags:
 - qwen
 ---
-# KielMind-Lite-Flash
 **KielMind-Lite-Flash** is a high-performance multi-domain instruction model. It is engineered to excel in complex logical reasoning, advanced coding patterns (such as asynchronous Python workflows), and multi-domain problem solving. As part of the **Kiel AI** ecosystem, it serves as the core text intelligence engine powering responsive chat interfaces and backend generative pipelines.
@@ -20,15 +20,15 @@ tags:
 ## Model Details
-- **Developed by:** Kiel AI Team
 - **Model Type:** Causal Language Model (Fully Merged Standalone Weights)
-- **Finetuned from model:** `kiel2/KielMind-Lite`
 - **Language(s) (NLP):** English
 - **Format:** Safetensors (FP16 optimized for high-throughput cloud serving)
 ### Model Sources
-- **Repository:** [kiel2/KielMind-Lite-Flash](https://huggingface.co/kiel2/KielMind-Lite-Flash)
 - **Ecosystem:** Kiel AI Suite (Integrated with KielForge and KielStream-Luna)
 ---
@@ -53,9 +53,9 @@ Because **KielMind-Lite-Flash** is provided as a fully merged standalone model (
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-MODEL_ID = "kiel2/KielMind-Lite-Flash"
-print("Loading KielMind-Lite-Flash tokenizer and model...")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 if tokenizer.pad_token is None:
     tokenizer.pad_token = tokenizer.eos_token
@@ -70,7 +70,7 @@ model.eval()
 # Test prompt
 prompt = (
-    "System: You are KielMind-Lite-Flash, an advanced multi-domain AI assistant.\n"
     "User: Write a robust Python function using asyncio and aiohttp to concurrently fetch JSON payloads."
 )
@@ -102,11 +102,11 @@ Capabilities: Validated on complex programming prompts, successfully synthesizin
 Citation
 Code snippet
-@misc{kielmind-lite-flash-2026,
-  author = {Kiel AI},
-  title = {KielMind-Lite-Flash: High-Performance Multi-Domain Language Model},
   year = {2026},
   publisher = {Hugging Face},
   journal = {Hugging Face Repository},
-  howpublished = {\url{[https://huggingface.co/kiel2/KielMind-Lite-Flash](https://huggingface.co/kiel2/KielMind-Lite-Flash)}}
 }

 ---
+base_model: kiel2/Kiel-2-Echo
 library_name: transformers
 pipeline_tag: text-generation
 tags:
 - qwen
 ---
+# kiel2/Kiel-2.1-Echo
 **KielMind-Lite-Flash** is a high-performance multi-domain instruction model. It is engineered to excel in complex logical reasoning, advanced coding patterns (such as asynchronous Python workflows), and multi-domain problem solving. As part of the **Kiel AI** ecosystem, it serves as the core text intelligence engine powering responsive chat interfaces and backend generative pipelines.
 ## Model Details
+- **Developed by:** KielTech
 - **Model Type:** Causal Language Model (Fully Merged Standalone Weights)
+- **Finetuned from model:** `kiel2/Kiel-2-Echo`
 - **Language(s) (NLP):** English
 - **Format:** Safetensors (FP16 optimized for high-throughput cloud serving)
 ### Model Sources
+- **Repository:** [kiel2/kiel2/Kiel-2.1-Echo](https://huggingface.co/kiel2/kiel2/Kiel-2.1-Echo)
 - **Ecosystem:** Kiel AI Suite (Integrated with KielForge and KielStream-Luna)
 ---
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+MODEL_ID = "kiel2/Kiel-2.1-Echo"
+print("Loading kiel2/Kiel-2.1-Echo tokenizer and model...")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 if tokenizer.pad_token is None:
     tokenizer.pad_token = tokenizer.eos_token
 # Test prompt
 prompt = (
+    "System: You are kiel2/Kiel-2.1-Echo, an advanced multi-domain AI assistant.\n"
     "User: Write a robust Python function using asyncio and aiohttp to concurrently fetch JSON payloads."
 )
 Citation
 Code snippet
+@misc{kiel2/Kiel-2.1-Echo-2026,
+  author = {KielTech},
+  title = {kiel2/Kiel-2.1-Echo: High-Performance Multi-Domain Language Model},
   year = {2026},
   publisher = {Hugging Face},
   journal = {Hugging Face Repository},
+  howpublished = {\url{[https://huggingface.co/kiel2/Kiel-2.1-Echo](https://kiel2/Kiel-2.1-Echo)}}
 }