Instructions to use bobber/lex-interviewer-nemotron-4b-grpo-v12 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bobber/lex-interviewer-nemotron-4b-grpo-v12 with Transformers:

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

pipe = pipeline("text-generation", model="bobber/lex-interviewer-nemotron-4b-grpo-v12", 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("bobber/lex-interviewer-nemotron-4b-grpo-v12", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("bobber/lex-interviewer-nemotron-4b-grpo-v12", 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 bobber/lex-interviewer-nemotron-4b-grpo-v12 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bobber/lex-interviewer-nemotron-4b-grpo-v12"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bobber/lex-interviewer-nemotron-4b-grpo-v12",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bobber/lex-interviewer-nemotron-4b-grpo-v12

SGLang

How to use bobber/lex-interviewer-nemotron-4b-grpo-v12 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 "bobber/lex-interviewer-nemotron-4b-grpo-v12" \
    --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": "bobber/lex-interviewer-nemotron-4b-grpo-v12",
		"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 "bobber/lex-interviewer-nemotron-4b-grpo-v12" \
        --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": "bobber/lex-interviewer-nemotron-4b-grpo-v12",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bobber/lex-interviewer-nemotron-4b-grpo-v12 with Docker Model Runner:
```
docker model run hf.co/bobber/lex-interviewer-nemotron-4b-grpo-v12
```

bobber commited on Mar 31

Commit

8f74872

verified ·

1 Parent(s): 93531f5

Fix model_q4.onnx: proper sharded format (in-place byte patch)

Browse files

Files changed (4) hide show

.gitattributes +2 -0
onnx/model_q4.onnx +2 -2
onnx/model_q4.onnx_data +3 -0
onnx/model_q4.onnx_data_1 +3 -0

.gitattributes CHANGED Viewed

@@ -453,3 +453,5 @@ onnx/model_layers_9_mamba_in_proj_MatMul_weight_zp filter=lfs diff=lfs merge=lfs
 onnx/model_layers_9_mamba_out_proj_MatMul_weight_quant filter=lfs diff=lfs merge=lfs -text
 onnx/model_layers_9_mamba_out_proj_MatMul_weight_scales filter=lfs diff=lfs merge=lfs -text
 onnx/model_layers_9_mamba_out_proj_MatMul_weight_zp filter=lfs diff=lfs merge=lfs -text

 onnx/model_layers_9_mamba_out_proj_MatMul_weight_quant filter=lfs diff=lfs merge=lfs -text
 onnx/model_layers_9_mamba_out_proj_MatMul_weight_scales filter=lfs diff=lfs merge=lfs -text
 onnx/model_layers_9_mamba_out_proj_MatMul_weight_zp filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx_data_1 filter=lfs diff=lfs merge=lfs -text

onnx/model_q4.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcd4348def063d7bf3d2844759fd36bcdf38d0e62a5b7de6760a6c344615b66
-size 1384199

 version https://git-lfs.github.com/spec/v1
+oid sha256:a36fa995d2c2480a327b83fadb1c671ae3413f325a1818a08cd2581636dfce32
+size 1375895

onnx/model_q4.onnx_data ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d88446cb2a2fe4045e18e3a2fe68a619381dfee7f10d3455a4972dd1c67b23b7
+size 2089224480

onnx/model_q4.onnx_data_1 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d6037fbaae94cceda7ab7b662ed262c4a64101f0490c61df4d0fc778c14d8cd0
+size 465316544