Instructions to use GeneZC/MiniMA-2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GeneZC/MiniMA-2-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GeneZC/MiniMA-2-1B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GeneZC/MiniMA-2-1B") model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniMA-2-1B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use GeneZC/MiniMA-2-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GeneZC/MiniMA-2-1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GeneZC/MiniMA-2-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GeneZC/MiniMA-2-1B
- SGLang
How to use GeneZC/MiniMA-2-1B 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 "GeneZC/MiniMA-2-1B" \ --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": "GeneZC/MiniMA-2-1B", "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 "GeneZC/MiniMA-2-1B" \ --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": "GeneZC/MiniMA-2-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GeneZC/MiniMA-2-1B with Docker Model Runner:
docker model run hf.co/GeneZC/MiniMA-2-1B
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,22 +21,25 @@ widget:
|
|
| 21 |
|
| 22 |
**Standard Benchmarks**
|
| 23 |
|
| 24 |
-
|
|
| 25 |
|--|--|--|--|--|--|--|--|
|
| 26 |
-
|
|
| 27 |
-
|
|
| 28 |
-
|
|
| 29 |
-
|
|
| 30 |
-
|
|
| 31 |
-
|
|
| 32 |
-
|
|
| 33 |
||
|
| 34 |
-
|MiniMA-3B|4.0E9|28.51|28.23|22.50|10.98|31.61|8.11|
|
| 35 |
-
|MiniChat-3B|4.0E9|38.40|36.48|22.58|18.29|31.36|29.72|
|
| 36 |
-
|MiniMA-2-1B|13.4E9|46.17|43.91|30.26|22.56|34.95|38.13|
|
| 37 |
|MiniMA-2-3B|13.4E9|40.14|44.65|23.10|14.63|31.43|8.87|
|
| 38 |
-
|
|
| 39 |
-
|MiniMix-2/4x3B|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
## Bibtex
|
| 42 |
|
|
|
|
| 21 |
|
| 22 |
**Standard Benchmarks**
|
| 23 |
|
| 24 |
+
||TFLOPs|MMLU (5-shot)|CEval (5-shot)|DROP (3-shot)|HumanEval (0-shot)|BBH (3-shot)|GSM8K (8-shot)|
|
| 25 |
|--|--|--|--|--|--|--|--|
|
| 26 |
+
|LLaMA-MoE-v1-3.5B-4_16|84.0+4.2E9|26.69|24.67|23.40|6.10|30.26|5.38|
|
| 27 |
+
|JetMoE-8B|16.5E9|48.24|36.03|30.63|24.39|33.86|40.71|
|
| 28 |
+
|DeepSeek-MoE-16B-base|33.6E9|44.64|39.90|29.74|26.83|31.95|17.06|
|
| 29 |
+
|MiniCPM-MoE-8x2B|14.4+24.0E9|55.38|54.01|31.39|47.56|37.15|54.81|
|
| 30 |
+
|Qwen1.5-MoE-A2.7B|23.8+35.7E9|59.56|79.27|32.87|33.54|39.12|65.13|
|
| 31 |
+
|Phixtral-2x2.8B|159.9E9|53.91|32.24|32.28|47.56|44.29|58.53|
|
| 32 |
+
|Mixtral-8x7B-v0.1|336.0E9|70.50|53.94|57.74|32.32|48.79|59.59|
|
| 33 |
||
|
|
|
|
|
|
|
|
|
|
| 34 |
|MiniMA-2-3B|13.4E9|40.14|44.65|23.10|14.63|31.43|8.87|
|
| 35 |
+
|MiniMix-2/4x3B-Kickoff|+0.1E9|34.30|33.51|21.34|10.37|30.35|6.60|
|
| 36 |
+
|MiniMix-2/4x3B-Biweek1|+2.0E9|41.17|41.75|27.24|15.85|32.17|14.25|
|
| 37 |
+
|MiniMix-2/4x3B-Biweek2|+4.0E9|41.35|40.79|28.62|18.90|31.66|13.34|
|
| 38 |
+
|MiniMix-2/4x3B-Biweek3|+6.0E9|41.58|44.21|30.68|17.68|32.91|16.07|
|
| 39 |
+
|MiniMix-2/4x3B-Biweek4|+8.0E9|43.14|44.21|31.33|18.29|32.61|16.98|
|
| 40 |
+
|MiniMix-2/4x3B-Biweek5|+10.0E9|43.75|45.10|32.47|18.29|33.71|21.99|
|
| 41 |
+
|MiniMix-2/4x3B-Biweek6|+12.0E9|44.57|45.39|33.35|20.12|33.43|22.52|
|
| 42 |
+
|MiniMix-2/4x3B-Release|+12.0E9|44.35|45.77|33.78|18.29|33.60|21.61|
|
| 43 |
|
| 44 |
## Bibtex
|
| 45 |
|