Instructions to use Eugleo/climbmix-d26-10tpp-noright with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Eugleo/climbmix-d26-10tpp-noright with Transformers:

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

pipe = pipeline("text-generation", model="Eugleo/climbmix-d26-10tpp-noright", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Eugleo/climbmix-d26-10tpp-noright", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Eugleo/climbmix-d26-10tpp-noright with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Eugleo/climbmix-d26-10tpp-noright"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Eugleo/climbmix-d26-10tpp-noright",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Eugleo/climbmix-d26-10tpp-noright

SGLang

How to use Eugleo/climbmix-d26-10tpp-noright 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 "Eugleo/climbmix-d26-10tpp-noright" \
    --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": "Eugleo/climbmix-d26-10tpp-noright",
		"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 "Eugleo/climbmix-d26-10tpp-noright" \
        --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": "Eugleo/climbmix-d26-10tpp-noright",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Eugleo/climbmix-d26-10tpp-noright with Docker Model Runner:
```
docker model run hf.co/Eugleo/climbmix-d26-10tpp-noright
```

climbmix-d26-10tpp-noright / tokenizer_config.json

Eugleo

exp-088 noright: d26 10-TPP base model on ClimbMix with the noright filter (arm d26-r10-a737eac7df78)

970f21f verified 20 days ago

Raw History Blame Contribute Delete

370 Bytes

	{
	"backend": "tokenizers",
	"bos_token": "<\|bos\|>",
	"eos_token": "<\|bos\|>",
	"extra_special_tokens": [
	"<\|user_start\|>",
	"<\|user_end\|>",
	"<\|assistant_start\|>",
	"<\|assistant_end\|>",
	"<\|python_start\|>",
	"<\|python_end\|>",
	"<\|output_start\|>",
	"<\|output_end\|>"
	],
	"model_max_length": 2048,
	"tokenizer_class": "TokenizersBackend"
	}

	{
	"backend": "tokenizers",
	"bos_token": "<\|bos\|>",
	"eos_token": "<\|bos\|>",
	"extra_special_tokens": [
	"<\|user_start\|>",
	"<\|user_end\|>",
	"<\|assistant_start\|>",
	"<\|assistant_end\|>",
	"<\|python_start\|>",
	"<\|python_end\|>",
	"<\|output_start\|>",
	"<\|output_end\|>"
	],
	"model_max_length": 2048,
	"tokenizer_class": "TokenizersBackend"
	}