Instructions to use exnivo/tinybrain-100m-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use exnivo/tinybrain-100m-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="exnivo/tinybrain-100m-instruct")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("exnivo/tinybrain-100m-instruct") model = AutoModelForCausalLM.from_pretrained("exnivo/tinybrain-100m-instruct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use exnivo/tinybrain-100m-instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "exnivo/tinybrain-100m-instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "exnivo/tinybrain-100m-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/exnivo/tinybrain-100m-instruct
- SGLang
How to use exnivo/tinybrain-100m-instruct 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 "exnivo/tinybrain-100m-instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "exnivo/tinybrain-100m-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "exnivo/tinybrain-100m-instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "exnivo/tinybrain-100m-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use exnivo/tinybrain-100m-instruct with Docker Model Runner:
docker model run hf.co/exnivo/tinybrain-100m-instruct
Good news
wowwww thanks!
it looks great but maybe work on the ui an lil bit
it looks great but maybe work on the ui an lil bit
yeah, im not rlly good at ui and for the base i used gpt, gonna search online for some css stuff
Just use some frameworks and check out https://21st.dev/ for UI components there's some seriously cool stuff there
Just use some frameworks and check out https://21st.dev/ for UI components there's some seriously cool stuff there
looks great but idk how ill add it, maybe will keep it bare bones for now.
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
This has to be an bot 😭
This has to be an bot 😭
says u making ai ai models
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
i can run up to a 4000m param model on my phone, do you think my phone has 256mb ram or smth
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
i can run up to a 4000m param model on my phone, do you think my phone has 256mb ram or smth
if it can then its 900gb ram
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
i can run up to a 4000m param model on my phone, do you think my phone has 256mb ram or smth
if it can then its 900gb ram
then explain how your samsung phone with 8gb ram ran qwen 3.8 2.4T
This has to be an bot 😭
says u making ai ai models
100% is ragebait
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
I guess never heard of ggml-org/ggml
I am running a 3B model on my phone.

a 3b models its smaller than your average game.
im very sure you dont need a datacenter to run GTA 5
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
i can run up to a 4000m param model on my phone, do you think my phone has 256mb ram or smth
if it can then its 900gb ram
then explain how your samsung phone with 8gb ram ran qwen 3.8 2.4T
16gb ram*
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
I guess never heard of ggml-org/ggml
I am running a 3B model on my phone.
a 3b models its smaller than your average game.
im very sure you dont need a datacenter to run GTA 5
"your average game" isnt anywhere above 5gbs on mobile most are under 1gb
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
I guess never heard of ggml-org/ggml
I am running a 3B model on my phone.
a 3b models its smaller than your average game.
im very sure you dont need a datacenter to run GTA 5"your average game" isnt anywhere above 5gbs on mobile most are under 1gb
Conclusion: You are trolling and ragebaiting
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
I guess never heard of ggml-org/ggml
I am running a 3B model on my phone.
a 3b models its smaller than your average game.
im very sure you dont need a datacenter to run GTA 5"your average game" isnt anywhere above 5gbs on mobile most are under 1gb
Conclusion: You are trolling and ragebaiting
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
I guess never heard of ggml-org/ggml
I am running a 3B model on my phone.
a 3b models its smaller than your average game.
im very sure you dont need a datacenter to run GTA 5"your average game" isnt anywhere above 5gbs on mobile most are under 1gb
Conclusion: You are trolling and ragebaiting
OK, let's start, you are ragebaiting and trolling, and any avg mobile game, is atleast 300MB, but why compare a game to a LM? I suppose you just want to troll
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
I guess never heard of ggml-org/ggml
I am running a 3B model on my phone.
a 3b models its smaller than your average game.
im very sure you dont need a datacenter to run GTA 5"your average game" isnt anywhere above 5gbs on mobile most are under 1gb
Conclusion: You are trolling and ragebaiting
OK, let's start, you are ragebaiting and trolling, and any avg mobile game, is atleast 300MB, but why compare a game to a LM? I suppose you just want to troll
u compared game to lm first
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
I guess never heard of ggml-org/ggml
I am running a 3B model on my phone.
a 3b models its smaller than your average game.
im very sure you dont need a datacenter to run GTA 5"your average game" isnt anywhere above 5gbs on mobile most are under 1gb
Conclusion: You are trolling and ragebaiting
OK, let's start, you are ragebaiting and trolling, and any avg mobile game, is atleast 300MB, but why compare a game to a LM? I suppose you just want to troll
u compared game to lm first
Tbh, if you want to troll, just close the computer and touch some grass
"efficent" this isnt even a slm this is a llm u prob need datacenter to run this bullshit
You can run my 500m model on a router, phone, laptop, and etc. is bro ragebaiting 😭
??? 500m model cant run on any of those u dont know how param scaling works bro for a model to run on phone has to be 50m or under idiot
I guess never heard of ggml-org/ggml
I am running a 3B model on my phone.
a 3b models its smaller than your average game.
im very sure you dont need a datacenter to run GTA 5"your average game" isnt anywhere above 5gbs on mobile most are under 1gb
Conclusion: You are trolling and ragebaiting
OK, let's start, you are ragebaiting and trolling, and any avg mobile game, is atleast 300MB, but why compare a game to a LM? I suppose you just want to troll
u compared game to lm first
Tbh, if you want to troll, just close the computer and touch some grass
thats not trolling
posing then?
grammar please
grammar please
no u
*No, you.
*No, you.
no u*


