Instructions to use BananaMind/TernaryBananaMind-10M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BananaMind/TernaryBananaMind-10M with Transformers:

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

pipe = pipeline("text-generation", model="BananaMind/TernaryBananaMind-10M", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("BananaMind/TernaryBananaMind-10M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BananaMind/TernaryBananaMind-10M with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BananaMind/TernaryBananaMind-10M

SGLang

How to use BananaMind/TernaryBananaMind-10M 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 "BananaMind/TernaryBananaMind-10M" \
    --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": "BananaMind/TernaryBananaMind-10M",
		"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 "BananaMind/TernaryBananaMind-10M" \
        --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": "BananaMind/TernaryBananaMind-10M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BananaMind/TernaryBananaMind-10M with Docker Model Runner:
```
docker model run hf.co/BananaMind/TernaryBananaMind-10M
```

Banaxi-Tech commited on 4 days ago

Commit

b7cc374

verified ·

1 Parent(s): 603f5fe

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -1

README.md CHANGED Viewed

@@ -54,6 +54,9 @@ The model has **8,428,032 logical weights**, a **4,096-token context window**, a
 | HF architecture | `BananaAllForCausalLM` |
 | HF model type | `bananaall` |
 The packed weights are decoded to temporary tensors for matrix multiplication. **2.07 bits per weight describes checkpoint storage, not arithmetic precision or peak inference memory.** Packed weights are registered as buffers, so `sum(p.numel() for p in model.parameters())` reports only the 6,656 trainable normalization parameters. Use the logical weight count above for model-size comparisons.
 ## Tokenizer
@@ -69,7 +72,7 @@ The custom 2k byte-level BPE tokenizer isolates digits during pre-tokenization.
 ## Training
-The model was trained on **2 billion tokens of FineWeb-Edu** with the **BananaAll training framework**. The included `training_args.bin` records the settings below. Its maximum-step value is a configured limit, not a separately verified final step count.
 | Setting | Recorded value |
 |---|---:|
@@ -87,10 +90,17 @@ The model was trained on **2 billion tokens of FineWeb-Edu** with the **BananaAl
 | PyTorch compile | Enabled |
 | Seed | 37 |
 ## Evaluation
 The `lm_eval` and BananaMind Base Bench 1.1 scores below were supplied for the **current packed checkpoint**. Harness version, dtype, and runtime settings can affect results.
 ### Standard benchmarks (`lm_eval`)
 | Benchmark | Acc | Acc norm | Samples |

 | HF architecture | `BananaAllForCausalLM` |
 | HF model type | `bananaall` |
+We have trained TernaryBananaMind-10M on our BananaAll training framework. See it at https://github.com/BananaMind/BananaAll/ to train your own model simply.
 The packed weights are decoded to temporary tensors for matrix multiplication. **2.07 bits per weight describes checkpoint storage, not arithmetic precision or peak inference memory.** Packed weights are registered as buffers, so `sum(p.numel() for p in model.parameters())` reports only the 6,656 trainable normalization parameters. Use the logical weight count above for model-size comparisons.
 ## Tokenizer
 ## Training
+The model was trained on **2 billion tokens of FineWeb-Edu** with the **BananaAll training framework**. It was trained on a RTX Pro 6000 by Molab and the script was exported as a notebook. The included `training_args.bin` records the settings below. Its maximum-step value is a configured limit, not a separately verified final step count.
 | Setting | Recorded value |
 |---|---:|
 | PyTorch compile | Enabled |
 | Seed | 37 |
+Training took 2 hours.
 ## Evaluation
 The `lm_eval` and BananaMind Base Bench 1.1 scores below were supplied for the **current packed checkpoint**. Harness version, dtype, and runtime settings can affect results.
+These scores have been evaluated via our BananaAll framework.
 ### Standard benchmarks (`lm_eval`)
 | Benchmark | Acc | Acc norm | Samples |