Instructions to use krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools with Transformers:

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

pipe = pipeline("text-generation", model="krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools")
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("krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools")
model = AutoModelForCausalLM.from_pretrained("krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools", 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 krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools

SGLang

How to use krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools 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 "krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools" \
    --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": "krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools",
		"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 "krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools" \
        --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": "krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools with Docker Model Runner:
```
docker model run hf.co/krinetic1234/DeepSeek-R1-Distill-Llama-3B-tools
```

krinetic1234 commited on Mar 14, 2025

Commit

ad43cf0

verified ·

1 Parent(s): abd9948

End of training

Browse files

Files changed (4) hide show

README.md +1 -0
all_results.json +5 -0
config.json +1 -1
eval_results.json +7 -0

README.md CHANGED Viewed

@@ -4,6 +4,7 @@ library_name: transformers
 model_name: DeepSeek-R1-Distill-Llama-3B-tools
 tags:
 - generated_from_trainer
 - trl
 - sft
 licence: license

 model_name: DeepSeek-R1-Distill-Llama-3B-tools
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license

all_results.json CHANGED Viewed

@@ -1,4 +1,9 @@
 {
     "total_flos": 2216750733066240.0,
     "train_loss": 1.3457099199295044,
     "train_runtime": 12.531,

 {
+    "eval_loss": 1.656509280204773,
+    "eval_runtime": 0.4753,
+    "eval_samples": 1,
+    "eval_samples_per_second": 2.104,
+    "eval_steps_per_second": 2.104,
     "total_flos": 2216750733066240.0,
     "train_loss": 1.3457099199295044,
     "train_runtime": 12.531,

config.json CHANGED Viewed

@@ -33,6 +33,6 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
   "unsloth_fixed": true,
-  "use_cache": false,
   "vocab_size": 128256
 }

   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
   "unsloth_fixed": true,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+    "eval_loss": 1.656509280204773,
+    "eval_runtime": 0.4753,
+    "eval_samples": 1,
+    "eval_samples_per_second": 2.104,
+    "eval_steps_per_second": 2.104
+}