Instructions to use techdotus/Tokle-SPAB-3M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use techdotus/Tokle-SPAB-3M with Transformers:

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

pipe = pipeline("text-generation", model="techdotus/Tokle-SPAB-3M", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("techdotus/Tokle-SPAB-3M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use techdotus/Tokle-SPAB-3M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "techdotus/Tokle-SPAB-3M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "techdotus/Tokle-SPAB-3M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/techdotus/Tokle-SPAB-3M

SGLang

How to use techdotus/Tokle-SPAB-3M 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 "techdotus/Tokle-SPAB-3M" \
    --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": "techdotus/Tokle-SPAB-3M",
		"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 "techdotus/Tokle-SPAB-3M" \
        --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": "techdotus/Tokle-SPAB-3M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use techdotus/Tokle-SPAB-3M with Docker Model Runner:
```
docker model run hf.co/techdotus/Tokle-SPAB-3M
```

anandselvadurai-techus commited on 27 days ago

Commit

c8aac5a

verified ·

1 Parent(s): 4bbdc93

Updated Tags

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -8,7 +8,6 @@ tags:
 - text-generation
 - causal-lm
 - custom-architecture
-- custom_code
 - slm
 - small-language-model
 - spab
@@ -87,7 +86,7 @@ the best result in each column.
 ## Training Data Details
-We trained on a curated mixture with a strict cleaning pipeline that also
 removed topics not useful for a model of this size.
 | Source | Percentage |
@@ -131,4 +130,4 @@ Model weights and code: MIT.
   publisher    = {Hugging Face},
   howpublished = {\url{https://huggingface.co/techdotus/Tokle-3M}}
 }
-```

 - text-generation
 - causal-lm
 - custom-architecture
 - slm
 - small-language-model
 - spab
 ## Training Data Details
+We trained on a curated mixture with a strict cleaning pipeline that also
 removed topics not useful for a model of this size.
 | Source | Percentage |
   publisher    = {Hugging Face},
   howpublished = {\url{https://huggingface.co/techdotus/Tokle-3M}}
 }
+```