Instructions to use websystemspl/Bielik-11B-v3.0-Instruct-128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use websystemspl/Bielik-11B-v3.0-Instruct-128k with Transformers:

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

pipe = pipeline("text-generation", model="websystemspl/Bielik-11B-v3.0-Instruct-128k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("websystemspl/Bielik-11B-v3.0-Instruct-128k")
model = AutoModelForCausalLM.from_pretrained("websystemspl/Bielik-11B-v3.0-Instruct-128k", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use websystemspl/Bielik-11B-v3.0-Instruct-128k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "websystemspl/Bielik-11B-v3.0-Instruct-128k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "websystemspl/Bielik-11B-v3.0-Instruct-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/websystemspl/Bielik-11B-v3.0-Instruct-128k

SGLang

How to use websystemspl/Bielik-11B-v3.0-Instruct-128k 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 "websystemspl/Bielik-11B-v3.0-Instruct-128k" \
    --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": "websystemspl/Bielik-11B-v3.0-Instruct-128k",
		"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 "websystemspl/Bielik-11B-v3.0-Instruct-128k" \
        --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": "websystemspl/Bielik-11B-v3.0-Instruct-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use websystemspl/Bielik-11B-v3.0-Instruct-128k with Docker Model Runner:
```
docker model run hf.co/websystemspl/Bielik-11B-v3.0-Instruct-128k
```

websystemspl commited on Mar 31

Commit

8ccbdb7

verified ·

1 Parent(s): 6832a36

Copy added_tokens.json from speakleash/Bielik-11B-v3.0-Instruct

Browse files

Files changed (1) hide show

added_tokens.json +130 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,130 @@

+{
+  "<|im_start|>": 32000,
+  "<|im_end|>": 32001,
+  "<|function_list|>": 32002,
+  "<|function_output|>": 32003,
+  "<|function_call|>": 32004,
+  "<tool_call>": 32005,
+  "</tool_call>": 32006,
+  "<think>": 32007,
+  "</think>": 32008,
+  "<|control_100|>": 32099,
+  "<|control_101|>": 32100,
+  "<|control_102|>": 32101,
+  "<|control_103|>": 32102,
+  "<|control_104|>": 32103,
+  "<|control_105|>": 32104,
+  "<|control_106|>": 32105,
+  "<|control_107|>": 32106,
+  "<|control_108|>": 32107,
+  "<|control_109|>": 32108,
+  "<|control_10|>": 32009,
+  "<|control_110|>": 32109,
+  "<|control_111|>": 32110,
+  "<|control_112|>": 32111,
+  "<|control_113|>": 32112,
+  "<|control_114|>": 32113,
+  "<|control_115|>": 32114,
+  "<|control_116|>": 32115,
+  "<|control_117|>": 32116,
+  "<|control_118|>": 32117,
+  "<|control_119|>": 32118,
+  "<|control_11|>": 32010,
+  "<|control_120|>": 32119,
+  "<|control_121|>": 32120,
+  "<|control_122|>": 32121,
+  "<|control_123|>": 32122,
+  "<|control_124|>": 32123,
+  "<|control_125|>": 32124,
+  "<|control_126|>": 32125,
+  "<|control_127|>": 32126,
+  "<|control_128|>": 32127,
+  "<|control_12|>": 32011,
+  "<|control_13|>": 32012,
+  "<|control_14|>": 32013,
+  "<|control_15|>": 32014,
+  "<|control_16|>": 32015,
+  "<|control_17|>": 32016,
+  "<|control_18|>": 32017,
+  "<|control_19|>": 32018,
+  "<|control_20|>": 32019,
+  "<|control_21|>": 32020,
+  "<|control_22|>": 32021,
+  "<|control_23|>": 32022,
+  "<|control_24|>": 32023,
+  "<|control_25|>": 32024,
+  "<|control_26|>": 32025,
+  "<|control_27|>": 32026,
+  "<|control_28|>": 32027,
+  "<|control_29|>": 32028,
+  "<|control_30|>": 32029,
+  "<|control_31|>": 32030,
+  "<|control_32|>": 32031,
+  "<|control_33|>": 32032,
+  "<|control_34|>": 32033,
+  "<|control_35|>": 32034,
+  "<|control_36|>": 32035,
+  "<|control_37|>": 32036,
+  "<|control_38|>": 32037,
+  "<|control_39|>": 32038,
+  "<|control_40|>": 32039,
+  "<|control_41|>": 32040,
+  "<|control_42|>": 32041,
+  "<|control_43|>": 32042,
+  "<|control_44|>": 32043,
+  "<|control_45|>": 32044,
+  "<|control_46|>": 32045,
+  "<|control_47|>": 32046,
+  "<|control_48|>": 32047,
+  "<|control_49|>": 32048,
+  "<|control_50|>": 32049,
+  "<|control_51|>": 32050,
+  "<|control_52|>": 32051,
+  "<|control_53|>": 32052,
+  "<|control_54|>": 32053,
+  "<|control_55|>": 32054,
+  "<|control_56|>": 32055,
+  "<|control_57|>": 32056,
+  "<|control_58|>": 32057,
+  "<|control_59|>": 32058,
+  "<|control_60|>": 32059,
+  "<|control_61|>": 32060,
+  "<|control_62|>": 32061,
+  "<|control_63|>": 32062,
+  "<|control_64|>": 32063,
+  "<|control_65|>": 32064,
+  "<|control_66|>": 32065,
+  "<|control_67|>": 32066,
+  "<|control_68|>": 32067,
+  "<|control_69|>": 32068,
+  "<|control_70|>": 32069,
+  "<|control_71|>": 32070,
+  "<|control_72|>": 32071,
+  "<|control_73|>": 32072,
+  "<|control_74|>": 32073,
+  "<|control_75|>": 32074,
+  "<|control_76|>": 32075,
+  "<|control_77|>": 32076,
+  "<|control_78|>": 32077,
+  "<|control_79|>": 32078,
+  "<|control_80|>": 32079,
+  "<|control_81|>": 32080,
+  "<|control_82|>": 32081,
+  "<|control_83|>": 32082,
+  "<|control_84|>": 32083,
+  "<|control_85|>": 32084,
+  "<|control_86|>": 32085,
+  "<|control_87|>": 32086,
+  "<|control_88|>": 32087,
+  "<|control_89|>": 32088,
+  "<|control_90|>": 32089,
+  "<|control_91|>": 32090,
+  "<|control_92|>": 32091,
+  "<|control_93|>": 32092,
+  "<|control_94|>": 32093,
+  "<|control_95|>": 32094,
+  "<|control_96|>": 32095,
+  "<|control_97|>": 32096,
+  "<|control_98|>": 32097,
+  "<|control_99|>": 32098
+}