Instructions to use bineric/lynx-instruct-30b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bineric/lynx-instruct-30b with Transformers:

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

pipe = pipeline("text-generation", model="bineric/lynx-instruct-30b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bineric/lynx-instruct-30b")
model = AutoModelForCausalLM.from_pretrained("bineric/lynx-instruct-30b")
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 bineric/lynx-instruct-30b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bineric/lynx-instruct-30b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bineric/lynx-instruct-30b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bineric/lynx-instruct-30b

SGLang

How to use bineric/lynx-instruct-30b 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 "bineric/lynx-instruct-30b" \
    --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": "bineric/lynx-instruct-30b",
		"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 "bineric/lynx-instruct-30b" \
        --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": "bineric/lynx-instruct-30b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bineric/lynx-instruct-30b with Docker Model Runner:
```
docker model run hf.co/bineric/lynx-instruct-30b
```

Umair Imam commited on Mar 26

Commit

fae5cb1

1 Parent(s): 395587c

Update config to match original: 262K context, rope_theta 10M

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -14,7 +14,7 @@
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 6144,
-  "max_position_embeddings": 40960,
   "max_window_layers": 48,
   "mlp_only_layers": [],
   "model_type": "qwen3_moe",
@@ -28,7 +28,7 @@
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,

   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
   "max_window_layers": 48,
   "mlp_only_layers": [],
   "model_type": "qwen3_moe",
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
+  "rope_theta": 10000000,
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,