Instructions to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 with Transformers:

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

pipe = pipeline("text-generation", model="Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128")
model = AutoModelForCausalLM.from_pretrained("Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128")
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 Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128

SGLang

How to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 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 "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128" \
    --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": "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128",
		"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 "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128" \
        --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": "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 with Docker Model Runner:
```
docker model run hf.co/Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128
```

Hyun9junn commited on Apr 15

Commit

8fd2f5a

verified ·

1 Parent(s): b8ca432

Add files using upload-large-folder tool

Browse files

Files changed (6) hide show

config.json +1 -1
generation_config.json +1 -1
model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1
recipe.yaml +1 -4

config.json CHANGED Viewed

@@ -224,7 +224,7 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
   "topk_group": 1,
-  "transformers_version": "5.5.0",
   "use_cache": true,
   "vocab_size": 153600
 }

   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
   "topk_group": 1,
+  "transformers_version": "5.5.3",
   "use_cache": true,
   "vocab_size": 153600
 }

generation_config.json CHANGED Viewed

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 1.0,
   "top_p": 0.95,
-  "transformers_version": "5.5.0"
 }

   "pad_token_id": 0,
   "temperature": 1.0,
   "top_p": 0.95,
+  "transformers_version": "5.5.3"
 }

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9a20d31870eabcb1d2b964dd650ab3066a8ceb47febba502386b79d4bb9063
 size 49999847240

 version https://git-lfs.github.com/spec/v1
+oid sha256:46ea2df2017ceacabbf473948c1dede534686cb60d8882de32aaac3c4ec115ca
 size 49999847240

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4700439e571174e5255571b3ecfbf56af81f657e97370c1636c692184188c89b
 size 49999543336

 version https://git-lfs.github.com/spec/v1
+oid sha256:62134a3298a764d8c0abf913368494049f13067b7c91bfd3f720d830e094922e
 size 49999543336

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:653f1d34f9b987d245b84aa77a4eaa0b9d79696dc2e24a03278456939ff64d38
 size 24847289304

 version https://git-lfs.github.com/spec/v1
+oid sha256:4eed6b53a62c2c25af6fb5f2ef0d3d41ac634a4d0432e43815aded265492d627
 size 24847289304

recipe.yaml CHANGED Viewed

@@ -6,9 +6,6 @@ default_stage:
       scheme: W4A16
       bypass_divisibility_checks: false
       mappings:
-      - smooth_layer: re:.*v_proj$
-        balance_layers: ['re:.*o_proj$']
-        activation_hook_target: null
       - smooth_layer: model.layers.1.post_attention_layernorm
         balance_layers: ['re:model\.layers\.1\.mlp\.experts\.[0-9]+\.gate_proj$', 're:model\.layers\.1\.mlp\.experts\.[0-9]+\.up_proj$',
           model.layers.1.mlp.shared_experts.gate_proj, model.layers.1.mlp.shared_experts.up_proj]
@@ -203,4 +200,4 @@ default_stage:
       offload_device: !!python/object/apply:torch.device [cpu]
       duo_scaling: true
       n_grid: 20
-      cache_chunk_size_batches: 32

       scheme: W4A16
       bypass_divisibility_checks: false
       mappings:
       - smooth_layer: model.layers.1.post_attention_layernorm
         balance_layers: ['re:model\.layers\.1\.mlp\.experts\.[0-9]+\.gate_proj$', 're:model\.layers\.1\.mlp\.experts\.[0-9]+\.up_proj$',
           model.layers.1.mlp.shared_experts.gate_proj, model.layers.1.mlp.shared_experts.up_proj]
       offload_device: !!python/object/apply:torch.device [cpu]
       duo_scaling: true
       n_grid: 20
+      cache_chunk_size_batches: 16