Instructions to use SupraLabs/Supra2-Medium-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra2-Medium-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/Supra2-Medium-Instruct")
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("SupraLabs/Supra2-Medium-Instruct")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra2-Medium-Instruct", 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 SupraLabs/Supra2-Medium-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra2-Medium-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra2-Medium-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra2-Medium-Instruct

SGLang

How to use SupraLabs/Supra2-Medium-Instruct 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 "SupraLabs/Supra2-Medium-Instruct" \
    --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": "SupraLabs/Supra2-Medium-Instruct",
		"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 "SupraLabs/Supra2-Medium-Instruct" \
        --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": "SupraLabs/Supra2-Medium-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SupraLabs/Supra2-Medium-Instruct with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra2-Medium-Instruct
```

Unfilled configs

by PashkovD - opened Sep 1

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+23

-8

Files changed (4) hide show

chat_template.jinja +10 -2
config.json +2 -2
generation_config.json +9 -2
tokenizer_config.json +2 -2

chat_template.jinja CHANGED Viewed

@@ -1,4 +1,12 @@
-{% for m in messages %}<|im_start|>{{ m['role'] }}
 {{ m['content'] }}<|im_end|>
-{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
 {% endif %}

+{% for m in messages %}
+<|im_start|>{{ m['role'] }}
+{% if m['role'] == 'assistant' %}
+{% generation %}{{ m['content'] }}<|im_end|>{% endgeneration %}
+{% else %}
 {{ m['content'] }}<|im_end|>
+{% endif %}
+{% endfor %}
+{% if add_generation_prompt %}
+<|im_start|>assistant
 {% endif %}

config.json CHANGED Viewed

@@ -4,9 +4,9 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
   "dtype": "float32",
-  "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 512,

   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token_id": 16384,
   "dtype": "float32",
+  "eos_token_id": 16385,
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 512,

generation_config.json CHANGED Viewed

@@ -1,7 +1,14 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
   "output_attentions": false,
   "output_hidden_states": false,
   "pad_token_id": 0,

 {
   "_from_model_config": true,
+  "bos_token_id": 16384,
+  "eos_token_id": [
+    16385
+  ],
+  "do_sample": true,
+  "temperature": 0.2,
+  "top_p": 0.85,
+  "top_k": 25,
+  "no_repeat_ngram_size": 3,
   "output_attentions": false,
   "output_hidden_states": false,
   "pad_token_id": 0,

tokenizer_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "backend": "tokenizers",
-  "bos_token": "<s>",
-  "eos_token": "</s>",
   "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>",

 {
   "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
   "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>",