HyperCLOVAX-SEED-Think-14B

Instructions to use FriendliAI/HyperCLOVAX-SEED-Think-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FriendliAI/HyperCLOVAX-SEED-Think-14B with Transformers:

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

pipe = pipeline("text-generation", model="FriendliAI/HyperCLOVAX-SEED-Think-14B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FriendliAI/HyperCLOVAX-SEED-Think-14B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("FriendliAI/HyperCLOVAX-SEED-Think-14B", trust_remote_code=True)
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 FriendliAI/HyperCLOVAX-SEED-Think-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FriendliAI/HyperCLOVAX-SEED-Think-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FriendliAI/HyperCLOVAX-SEED-Think-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FriendliAI/HyperCLOVAX-SEED-Think-14B

SGLang

How to use FriendliAI/HyperCLOVAX-SEED-Think-14B 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 "FriendliAI/HyperCLOVAX-SEED-Think-14B" \
    --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": "FriendliAI/HyperCLOVAX-SEED-Think-14B",
		"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 "FriendliAI/HyperCLOVAX-SEED-Think-14B" \
        --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": "FriendliAI/HyperCLOVAX-SEED-Think-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FriendliAI/HyperCLOVAX-SEED-Think-14B with Docker Model Runner:
```
docker model run hf.co/FriendliAI/HyperCLOVAX-SEED-Think-14B
```

seungahdev commited on May 26

Commit

c526be0

verified ·

1 Parent(s): 0404851

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

chat_template.jinja +11 -9
spec_model.safetensors +3 -0
version.txt +1 -0

chat_template.jinja CHANGED Viewed

@@ -37,13 +37,15 @@
     {%- if message.content is string %}
         {%- set content = message.content %}
     {%- else %}
         {%- set content = '' %}
     {%- endif %}
     {%- set reasoning_content = '' %}
     {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
-        {%- set reasoning_content = message.reasoning_content %}
     {%- endif %}
     {%- if message.role == "assistant" %}
         {%- if loop.index0 > ns.last_query_index %}
@@ -90,11 +92,11 @@
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
-  {%- if (force_reasoning is defined and force_reasoning) or (enable_thinking is defined and enable_thinking) %}
-      {{- '<|im_start|>assistant/think\n' }}
-  {%- elif (skip_reasoning is defined and skip_reasoning) or (enable_thinking is defined and enable_thinking is false) %}
-      {{- '<|im_start|>assistant\n' }}
-  {%- else %}
-      {{- '<|im_start|>assistant' }}
-  {%- endif %}
-{%- endif %}

     {%- if message.content is string %}
         {%- set content = message.content %}
+    {%- elif message.content is iterable %}
+        {%- set content = message.content | map(attribute='text') | join %}
     {%- else %}
         {%- set content = '' %}
     {%- endif %}
     {%- set reasoning_content = '' %}
     {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+        {%- set reasoning_content = message.reasoning_content %}
     {%- endif %}
     {%- if message.role == "assistant" %}
         {%- if loop.index0 > ns.last_query_index %}
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
+    {%- if (force_reasoning is defined and force_reasoning) or (enable_thinking is defined and enable_thinking) %}
+        {{- '<|im_start|>assistant/think\n' }}
+    {%- elif (skip_reasoning is defined and skip_reasoning) or (enable_thinking is defined and enable_thinking is false) %}
+        {{- '<|im_start|>assistant\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant' }}
+    {%- endif %}
+{%- endif %}

spec_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:73744872fb4fc26da957b7e90b33cfe0b614104f500c9cfc176006d5cc196144
+size 1358954615

version.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ 1.0.0