Instructions to use Ma7ee7/Andgit-0.6B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ma7ee7/Andgit-0.6B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="Ma7ee7/Andgit-0.6B-SFT")
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("Ma7ee7/Andgit-0.6B-SFT")
model = AutoModelForCausalLM.from_pretrained("Ma7ee7/Andgit-0.6B-SFT", 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 Ma7ee7/Andgit-0.6B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ma7ee7/Andgit-0.6B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ma7ee7/Andgit-0.6B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ma7ee7/Andgit-0.6B-SFT

SGLang

How to use Ma7ee7/Andgit-0.6B-SFT 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 "Ma7ee7/Andgit-0.6B-SFT" \
    --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": "Ma7ee7/Andgit-0.6B-SFT",
		"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 "Ma7ee7/Andgit-0.6B-SFT" \
        --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": "Ma7ee7/Andgit-0.6B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ma7ee7/Andgit-0.6B-SFT with Docker Model Runner:
```
docker model run hf.co/Ma7ee7/Andgit-0.6B-SFT
```

Ma7ee7 commited on 3 days ago

Commit

00495db

verified ·

1 Parent(s): fb1758a

Update chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +39 -4

chat_template.jinja CHANGED Viewed

@@ -1,4 +1,39 @@
-{% for message in messages %}{{ '<|im_start|>' + message['role'] + '
-' + message['content'] + '<|im_end|>
-' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}

+{%- for message in messages %}
+    {%- set role = message['role'] %}
+    {%- if role not in ['system', 'user', 'assistant'] %}
+        {{- raise_exception('Noesis supports system, user, and assistant roles.') }}
+    {%- endif %}
+    {%- set content = message['content'] %}
+    {%- if content is not string %}
+        {%- if content is not sequence or content is mapping %}
+            {{- raise_exception('Message content must be text or a list of text blocks.') }}
+        {%- endif %}
+        {%- set text = namespace(value='') %}
+        {%- for part in content %}
+            {%- if part is not mapping or part['type'] != 'text' or part['text'] is not string %}
+                {{- raise_exception('Noesis only supports text content blocks.') }}
+            {%- endif %}
+            {%- set text.value = text.value + part['text'] %}
+        {%- endfor %}
+        {%- set content = text.value %}
+    {%- endif %}
+    {%- if role == 'assistant' %}
+        {%- set history = not loop.last or add_generation_prompt %}
+        {%- set trimmed = content.lstrip() %}
+        {%- set has_reasoning = trimmed.startswith('<think>') %}
+        {%- if history and has_reasoning and '</think>' in trimmed %}
+            {%- set content = trimmed.split('</think>', 1)[1].lstrip('\r\n') %}
+        {%- elif not history and not has_reasoning %}
+            {%- set reasoning = message.get('reasoning_content') %}
+            {%- if reasoning is string and reasoning.strip() %}
+                {%- set content = '<think>\n' + reasoning.strip() + '\n</think>\n\n' + content %}
+            {%- endif %}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_start|>' + role + '\n' + content + '<|im_end|>\n' }}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}