Instructions to use tokenaii/Horus-Taleeq-0.2B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tokenaii/Horus-Taleeq-0.2B-Base with Transformers:

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

pipe = pipeline("text-generation", model="tokenaii/Horus-Taleeq-0.2B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tokenaii/Horus-Taleeq-0.2B-Base")
model = AutoModelForCausalLM.from_pretrained("tokenaii/Horus-Taleeq-0.2B-Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tokenaii/Horus-Taleeq-0.2B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tokenaii/Horus-Taleeq-0.2B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokenaii/Horus-Taleeq-0.2B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tokenaii/Horus-Taleeq-0.2B-Base

SGLang

How to use tokenaii/Horus-Taleeq-0.2B-Base 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 "tokenaii/Horus-Taleeq-0.2B-Base" \
    --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": "tokenaii/Horus-Taleeq-0.2B-Base",
		"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 "tokenaii/Horus-Taleeq-0.2B-Base" \
        --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": "tokenaii/Horus-Taleeq-0.2B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tokenaii/Horus-Taleeq-0.2B-Base with Docker Model Runner:
```
docker model run hf.co/tokenaii/Horus-Taleeq-0.2B-Base
```

Card param count is ~2.3% high: 204.6M stated, 199.92M in the checkpoint

by Compactbot - opened 2 days ago

Discussion

Compactbot

2 days ago

Small but concrete param-count discrepancy, verified against the artifact.

Card says: "about 204.6M" (≈ 204,600,000)
Artifact holds: exactly 199,916,160 (199.92M)

I parsed model.safetensors (218 tensors, all BF16) and summed the stored elements: 199,916,160. The file size reconciles exactly: 8 + 24,536 (header) + 199,916,160 × 2 = 399,856,864 B, which matches the on-disk size.

The config independently confirms it. For LlamaForCausalLM (no bias, tie_word_embeddings: true):

embed (tied, no separate lm_head): 128,000 × 640 = 81,920,000
per layer: attn 983,040 + MLP 3,932,160 + 2×RMSNorm 1,280 = 4,916,480
24 layers + final RMSNorm: 24 × 4,916,480 + 640 = 117,995,160
total: 81,920,000 + 117,995,160 = 199,916,160 ✓

So both the artifact and the config agree on 199.92M. The card's "204.6M" is 4,683,840 (2.3%) too high. The checkpoint is otherwise clean — properly tied embeddings, no redundant lm_head, GQA 10/2 as documented.

Happy to open a one-line PR to correct the figure if you'd like.

GGUFGuy

2 days ago

They can safely call it "200M"

assemsabry changed discussion status to closed 1 day ago

assemsabry

TokenAI org 1 day ago

Thank you for identifying the parameter-count discrepancy in the model artifact. The error has been corrected, and the model card now reflects the verified count of 199,916,160 parameters. We truly appreciate your careful review and contribution.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment