Instructions to use roskosmos19/Orca-2-4B-Coding-max with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roskosmos19/Orca-2-4B-Coding-max with Transformers:

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

pipe = pipeline("text-generation", model="roskosmos19/Orca-2-4B-Coding-max")
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("roskosmos19/Orca-2-4B-Coding-max")
model = AutoModelForCausalLM.from_pretrained("roskosmos19/Orca-2-4B-Coding-max", 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 roskosmos19/Orca-2-4B-Coding-max with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roskosmos19/Orca-2-4B-Coding-max"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roskosmos19/Orca-2-4B-Coding-max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/roskosmos19/Orca-2-4B-Coding-max

SGLang

How to use roskosmos19/Orca-2-4B-Coding-max 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 "roskosmos19/Orca-2-4B-Coding-max" \
    --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": "roskosmos19/Orca-2-4B-Coding-max",
		"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 "roskosmos19/Orca-2-4B-Coding-max" \
        --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": "roskosmos19/Orca-2-4B-Coding-max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use roskosmos19/Orca-2-4B-Coding-max with Docker Model Runner:
```
docker model run hf.co/roskosmos19/Orca-2-4B-Coding-max
```

roskosmos19 commited on Jun 18

Commit

9d360d3

verified ·

1 Parent(s): dd7cb08

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -10

README.md CHANGED Viewed

@@ -54,19 +54,19 @@ uv pip install transformers torch accelerate
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
-model = AutoModelForCausalLM.from_pretrained("Aquiles-ai/Athenea-4B-Coding",
         dtype=torch.bfloat16,
         trust_remote_code=True,
         device_map="auto",
         attn_implementation="flash_attention_2") # Requires flash-attn
 # Without flash-attn:
-# model = AutoModelForCausalLM.from_pretrained("Aquiles-ai/Athenea-4B-Coding",
 #     dtype="auto",
 #     device_map="auto"
 # )
-tokenizer = AutoTokenizer.from_pretrained("Aquiles-ai/Athenea-4B-Coding", trust_remote_code=True)
 messages = [
     {"role": "user", "content": "Hey, write a Python function that calculates the factorial of a number recursively."}
@@ -147,7 +147,7 @@ for chunk in streamer:
 **Start server:**
 ```bash
-vllm serve Aquiles-ai/Athenea-4B-Coding \
   --host 0.0.0.0 \
   --port 8000 \
   --api-key dummyapikey \
@@ -162,7 +162,7 @@ vllm serve Aquiles-ai/Athenea-4B-Coding \
 from openai import OpenAI
 client = OpenAI(api_key="dummyapikey", base_url="http://127.0.0.1:8000/v1")
 stream = client.chat.completions.create(
-    model="Aquiles-ai/Athenea-4B-Coding",
     messages=[{
         "role": "user",
         "content": "Hey, write a Python function that determines if a string is a palindrome, ignoring case, spaces, and punctuation."
@@ -179,11 +179,6 @@ for chunk in stream:
-### Aquiles-playground
-In addition to code usage, you can also try our models locally through an [open-source playground on GitHub](https://github.com/Aquiles-ai/aquiles-playground).
 <p align="center">
   Roskosmos19
 </p>

 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding",
         dtype=torch.bfloat16,
         trust_remote_code=True,
         device_map="auto",
         attn_implementation="flash_attention_2") # Requires flash-attn
 # Without flash-attn:
+# model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding",
 #     dtype="auto",
 #     device_map="auto"
 # )
+tokenizer = AutoTokenizer.from_pretrained("Roskosmos19/Rhea-4B-Coding", trust_remote_code=True)
 messages = [
     {"role": "user", "content": "Hey, write a Python function that calculates the factorial of a number recursively."}
 **Start server:**
 ```bash
+vllm serve Roskosmos19/Rhea-4B-Coding \
   --host 0.0.0.0 \
   --port 8000 \
   --api-key dummyapikey \
 from openai import OpenAI
 client = OpenAI(api_key="dummyapikey", base_url="http://127.0.0.1:8000/v1")
 stream = client.chat.completions.create(
+    model="roskosmos19/Rhea-4B-Coding",
     messages=[{
         "role": "user",
         "content": "Hey, write a Python function that determines if a string is a palindrome, ignoring case, spaces, and punctuation."
 <p align="center">
   Roskosmos19
 </p>