teknium/OpenHermes-2.5
Viewer • Updated • 1M • 22.1k • 832
How to use cahya/TestLM with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="cahya/TestLM", trust_remote_code=True) # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("cahya/TestLM", trust_remote_code=True, dtype="auto")How to use cahya/TestLM with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cahya/TestLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "cahya/TestLM",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/cahya/TestLM
How to use cahya/TestLM with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "cahya/TestLM" \
--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": "cahya/TestLM",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "cahya/TestLM" \
--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": "cahya/TestLM",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use cahya/TestLM with Docker Model Runner:
docker model run hf.co/cahya/TestLM
This is just a place holder to test the tokenizer.
The chat format is identical to the default HuggingFace format, EXCEPT that we replace the <|im_start|> and <|im_end|> special tokens with the unused ASCII codes "\x16" and "\x17" respectively. This was done to ensure complete compatibility withe standard RWKV World tokenizer.
An example interaction:
\x16user
Write a poem about the beauty of mathematics in the style of Emily Dickinson.\x17
\x16assistant
In the heart of Numbers, so precise,
A Beauty dwells - both cool and nice.
An elegance that sings in sums,
And dances to algebraic drums.
Addition's grace, subtraction's might,
Multiplication's sheer delight,
Division's firm yet gentle hand,
All part of this enchanted land.
Infinity, a lover bold,
To whom the stars their secrets told,
While Zero, cloaked in mystery,
Unlocks each mathematical decree.
Fractals bloom like flowers wild,
Geometry, Nature's favored child,
Calculus, with steady gaze,
Maps out life's intricate maze.
Pi, an endless serenade,
In circles' arms forever laid,
And prime numbers,
standing lone,
Make the universe their own.
Each equation, theorem scribed,
In
parchment old or computer imbibed,
Is but a whisper from the skies,
A cosmic truth in disguise.\x17
In the above, newlines are printed without escaping, while ASCII codes are escaped for readability.