Instructions to use flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat with Transformers:

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

pipe = pipeline("text-generation", model="flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat")
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("flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat")
model = AutoModelForCausalLM.from_pretrained("flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat", 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 flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat

SGLang

How to use flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat 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 "flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat" \
    --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": "flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat",
		"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 "flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat" \
        --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": "flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat with Docker Model Runner:
```
docker model run hf.co/flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat
```

flypg commited on Feb 10, 2025

Commit

f4e7264

verified ·

1 Parent(s): 4a9f55e

Upload model

Browse files

Files changed (2) hide show

adapter_config.json +4 -4
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -19,12 +19,12 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "cyberagent/DeepSeek-R1-Distill-Qwen-14B-Japanese",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d812c82c5424a0cfd6214c20f2e4db7429a0d51b5bc36c74989886eb5b2940b7
-size 50383600

 version https://git-lfs.github.com/spec/v1
+oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
+size 40