Text Generation
Transformers
Safetensors
qwen2
superseded
archival
mixture-of-experts
Mixture of Experts
ternary
1-bit
qwen2.5
outlier
outlier-moe
research
overlay
sparse
local-llm
on-device
apple-silicon
mac
conversational
custom_code
text-generation-inference
Instructions to use Outlier-Ai/Outlier-10B-V3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Outlier-Ai/Outlier-10B-V3.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Outlier-Ai/Outlier-10B-V3.2", 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("Outlier-Ai/Outlier-10B-V3.2", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Outlier-Ai/Outlier-10B-V3.2", 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
- vLLM
How to use Outlier-Ai/Outlier-10B-V3.2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Outlier-Ai/Outlier-10B-V3.2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Outlier-Ai/Outlier-10B-V3.2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Outlier-Ai/Outlier-10B-V3.2
- SGLang
How to use Outlier-Ai/Outlier-10B-V3.2 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 "Outlier-Ai/Outlier-10B-V3.2" \ --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": "Outlier-Ai/Outlier-10B-V3.2", "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 "Outlier-Ai/Outlier-10B-V3.2" \ --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": "Outlier-Ai/Outlier-10B-V3.2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Outlier-Ai/Outlier-10B-V3.2 with Docker Model Runner:
docker model run hf.co/Outlier-Ai/Outlier-10B-V3.2
| { | |
| "layer_07_expert_00": 0.01969238929450512, | |
| "layer_07_expert_01": 0.01805144175887108, | |
| "layer_07_expert_02": 0.01898551732301712, | |
| "layer_07_expert_03": 0.020216668024659157, | |
| "layer_07_expert_04": 0.019787311553955078, | |
| "layer_07_expert_05": 0.019402215257287025, | |
| "layer_07_expert_06": 0.0193850789219141, | |
| "layer_07_expert_07": 0.02014368399977684, | |
| "layer_08_expert_00": 0.02600640431046486, | |
| "layer_08_expert_01": 0.022020943462848663, | |
| "layer_08_expert_02": 0.02276753820478916, | |
| "layer_08_expert_03": 0.026547007262706757, | |
| "layer_08_expert_04": 0.027177805081009865, | |
| "layer_08_expert_05": 0.02274380810558796, | |
| "layer_08_expert_06": 0.026304863393306732, | |
| "layer_08_expert_07": 0.02764948271214962, | |
| "layer_09_expert_00": 0.013534344732761383, | |
| "layer_09_expert_01": 0.0145828016102314, | |
| "layer_09_expert_02": 0.013892530463635921, | |
| "layer_09_expert_03": 0.013967453502118587, | |
| "layer_09_expert_04": 0.013249906711280346, | |
| "layer_09_expert_05": 0.01342932227998972, | |
| "layer_09_expert_06": 0.014618050307035446, | |
| "layer_09_expert_07": 0.01448456197977066, | |
| "layer_10_expert_00": 0.022231444716453552, | |
| "layer_10_expert_01": 0.019972696900367737, | |
| "layer_10_expert_02": 0.024050315842032433, | |
| "layer_10_expert_03": 0.021881794556975365, | |
| "layer_10_expert_04": 0.021667910739779472, | |
| "layer_10_expert_05": 0.020687896758317947, | |
| "layer_10_expert_06": 0.021906213834881783, | |
| "layer_10_expert_07": 0.021762344986200333, | |
| "layer_11_expert_00": 0.02834983915090561, | |
| "layer_11_expert_01": 0.028404127806425095, | |
| "layer_11_expert_02": 0.028010638430714607, | |
| "layer_11_expert_03": 0.029820352792739868, | |
| "layer_11_expert_04": 0.029144475236535072, | |
| "layer_11_expert_05": 0.031495511531829834, | |
| "layer_11_expert_06": 0.025821425020694733, | |
| "layer_11_expert_07": 0.02732662297785282, | |
| "layer_12_expert_00": 0.030554262921214104, | |
| "layer_12_expert_01": 0.030468732118606567, | |
| "layer_12_expert_02": 0.030987773090600967, | |
| "layer_12_expert_03": 0.028986576944589615, | |
| "layer_12_expert_04": 0.03083137981593609, | |
| "layer_12_expert_05": 0.02847979962825775, | |
| "layer_12_expert_06": 0.029302263632416725, | |
| "layer_12_expert_07": 0.02996886521577835, | |
| "layer_13_expert_00": 0.03826427087187767, | |
| "layer_13_expert_01": 0.03209064528346062, | |
| "layer_13_expert_02": 0.034369178116321564, | |
| "layer_13_expert_03": 0.030629923567175865, | |
| "layer_13_expert_04": 0.033462297171354294, | |
| "layer_13_expert_05": 0.033646147698163986, | |
| "layer_13_expert_06": 0.031612180173397064, | |
| "layer_13_expert_07": 0.03360999748110771, | |
| "layer_14_expert_00": 0.03800996392965317, | |
| "layer_14_expert_01": 0.035479817539453506, | |
| "layer_14_expert_02": 0.035590216517448425, | |
| "layer_14_expert_03": 0.03698544576764107, | |
| "layer_14_expert_04": 0.036537885665893555, | |
| "layer_14_expert_05": 0.03591139242053032, | |
| "layer_14_expert_06": 0.0347776859998703, | |
| "layer_14_expert_07": 0.035771314054727554, | |
| "layer_15_expert_00": 0.037486180663108826, | |
| "layer_15_expert_01": 0.03183320537209511, | |
| "layer_15_expert_02": 0.033597372472286224, | |
| "layer_15_expert_03": 0.034959577023983, | |
| "layer_15_expert_04": 0.033746231347322464, | |
| "layer_15_expert_05": 0.03387705609202385, | |
| "layer_15_expert_06": 0.036250147968530655, | |
| "layer_15_expert_07": 0.03742583096027374, | |
| "layer_16_expert_00": 0.03308767080307007, | |
| "layer_16_expert_01": 0.03283284604549408, | |
| "layer_16_expert_02": 0.03292208909988403, | |
| "layer_16_expert_03": 0.032567355781793594, | |
| "layer_16_expert_04": 0.0328839085996151, | |
| "layer_16_expert_05": 0.03387352451682091, | |
| "layer_16_expert_06": 0.032794974744319916, | |
| "layer_16_expert_07": 0.031062856316566467, | |
| "layer_17_expert_00": 0.03392287716269493, | |
| "layer_17_expert_01": 0.030720185488462448, | |
| "layer_17_expert_02": 0.03290826454758644, | |
| "layer_17_expert_03": 0.03276655077934265, | |
| "layer_17_expert_04": 0.031194286420941353, | |
| "layer_17_expert_05": 0.0328129306435585, | |
| "layer_17_expert_06": 0.03219807893037796, | |
| "layer_17_expert_07": 0.03303227201104164, | |
| "layer_18_expert_00": 0.032916367053985596, | |
| "layer_18_expert_01": 0.03964288905262947, | |
| "layer_18_expert_02": 0.039214037358760834, | |
| "layer_18_expert_03": 0.03236524388194084, | |
| "layer_18_expert_04": 0.03989103063941002, | |
| "layer_18_expert_05": 0.03882138058543205, | |
| "layer_18_expert_06": 0.032691407948732376, | |
| "layer_18_expert_07": 0.03731442242860794, | |
| "layer_19_expert_00": 0.02582397684454918, | |
| "layer_19_expert_01": 0.026262322440743446, | |
| "layer_19_expert_02": 0.026067685335874557, | |
| "layer_19_expert_03": 0.025103550404310226, | |
| "layer_19_expert_04": 0.026913922280073166, | |
| "layer_19_expert_05": 0.02546408213675022, | |
| "layer_19_expert_06": 0.025271881371736526, | |
| "layer_19_expert_07": 0.026326699182391167, | |
| "layer_20_expert_00": 0.037034712731838226, | |
| "layer_20_expert_01": 0.02768402174115181, | |
| "layer_20_expert_02": 0.026117460802197456, | |
| "layer_20_expert_03": 0.03588447719812393, | |
| "layer_20_expert_04": 0.03711237385869026, | |
| "layer_20_expert_05": 0.025986790657043457, | |
| "layer_20_expert_06": 0.026828493922948837, | |
| "layer_20_expert_07": 0.036583513021469116 | |
| } |