Instructions to use Kolyadual/MIXdevAI-llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kolyadual/MIXdevAI-llama with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kolyadual/MIXdevAI-llama")
model = AutoModelForCausalLM.from_pretrained("Kolyadual/MIXdevAI-llama")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kolyadual/MIXdevAI-llama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Kolyadual/MIXdevAI-llama

SGLang

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

Docker Model Runner
How to use Kolyadual/MIXdevAI-llama with Docker Model Runner:
```
docker model run hf.co/Kolyadual/MIXdevAI-llama
```

Kolyadual commited on Jan 9

Commit

46cfcb2

verified ·

1 Parent(s): 0b069e5

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -4

README.md CHANGED Viewed

@@ -1,14 +1,31 @@
 ---
-base_model: []
 library_name: transformers
 tags:
 - mergekit
 - merge
 ---
 # MIXdevAI-llama
-Нейронная сеть, на основе Llama 3, дообученная на датасете ChatGPT 5.2 и слита с нейросетью KingNish/Reasoning-Llama-1b-v0.1
 Модели, которые были слиты:
 * meta-llama/Llama-3.2-1B-Instruct
@@ -38,4 +55,4 @@ parameters:
 dtype: bfloat16
-```

 ---
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
 library_name: transformers
 tags:
 - mergekit
 - merge
+- NewtonBot
+- MIXdevAI
+- NewtonBotFamilyTree
+- chemistry
+- biology
+- code
+license: gpl-3.0
+datasets:
+- fka/awesome-chatgpt-prompts
+- TeichAI/claude-4.5-opus-high-reasoning-250x
+- KingNish/reasoning-base-20k
+language:
+- ru
+- en
+- ja
+- ro
+- fr
 ---
 # MIXdevAI-llama
+Легковестная ИИ, на основе Llama 3 из семейства Newton bot, созданная Kolyadual
 Модели, которые были слиты:
 * meta-llama/Llama-3.2-1B-Instruct
 dtype: bfloat16
+```