Text Generation
Transformers
Safetensors
PyTorch
gemma
Eval Results (legacy)
text-generation-inference
Instructions to use beomi/gemma-mling-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use beomi/gemma-mling-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="beomi/gemma-mling-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("beomi/gemma-mling-7b") model = AutoModelForCausalLM.from_pretrained("beomi/gemma-mling-7b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use beomi/gemma-mling-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "beomi/gemma-mling-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "beomi/gemma-mling-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/beomi/gemma-mling-7b
- SGLang
How to use beomi/gemma-mling-7b 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 "beomi/gemma-mling-7b" \ --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": "beomi/gemma-mling-7b", "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 "beomi/gemma-mling-7b" \ --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": "beomi/gemma-mling-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use beomi/gemma-mling-7b with Docker Model Runner:
docker model run hf.co/beomi/gemma-mling-7b
Update metric table
#2
by Taekyoon - opened
README.md
CHANGED
|
@@ -131,15 +131,15 @@ Model evaluation metrics and results.
|
|
| 131 |
|
| 132 |
### Benchmark Results
|
| 133 |
|
| 134 |
-
| Category | Metric | Shots |
|
| 135 |
|----------------------------------|----------------------|------------|--------|
|
| 136 |
| **Default Metric** | **ACC** | | |
|
| 137 |
| **Knowledge (5-shot)** | MMLU | | 61.76 |
|
| 138 |
-
| | KMMLU
|
| 139 |
| | CMLU | | 50.93 |
|
| 140 |
| | JMLU | | |
|
| 141 |
| | C-EVAL | | 50.07 |
|
| 142 |
-
| | HAERAE
|
| 143 |
| **KoBest (5-shot)** | BoolQ | | 85.47 |
|
| 144 |
| | COPA | | 83.5 |
|
| 145 |
| | Hellaswag (acc-norm) | | 63.2 |
|
|
@@ -154,8 +154,8 @@ Model evaluation metrics and results.
|
|
| 154 |
| **JP Eval Harness (Prompt ver 0.3)** | JcommonsenseQA | 3-shot | 85.97 |
|
| 155 |
| | JNLI | 3-shot | 39.11 |
|
| 156 |
| | Marc_ja | 3-shot | 96.48 |
|
| 157 |
-
| | JSquad
|
| 158 |
-
| | Jaqket
|
| 159 |
| | MGSM | 5-shot | 28.8 |
|
| 160 |
| **XWinograd (0-shot)** | EN | | 89.03 |
|
| 161 |
| | FR | | 72.29 |
|
|
|
|
| 131 |
|
| 132 |
### Benchmark Results
|
| 133 |
|
| 134 |
+
| Category | Metric | Shots | Score |
|
| 135 |
|----------------------------------|----------------------|------------|--------|
|
| 136 |
| **Default Metric** | **ACC** | | |
|
| 137 |
| **Knowledge (5-shot)** | MMLU | | 61.76 |
|
| 138 |
+
| | KMMLU (Exact Match) | | 42.75 |
|
| 139 |
| | CMLU | | 50.93 |
|
| 140 |
| | JMLU | | |
|
| 141 |
| | C-EVAL | | 50.07 |
|
| 142 |
+
| | HAERAE | 0-shot | 63.89 |
|
| 143 |
| **KoBest (5-shot)** | BoolQ | | 85.47 |
|
| 144 |
| | COPA | | 83.5 |
|
| 145 |
| | Hellaswag (acc-norm) | | 63.2 |
|
|
|
|
| 154 |
| **JP Eval Harness (Prompt ver 0.3)** | JcommonsenseQA | 3-shot | 85.97 |
|
| 155 |
| | JNLI | 3-shot | 39.11 |
|
| 156 |
| | Marc_ja | 3-shot | 96.48 |
|
| 157 |
+
| | JSquad (Exact Match) | 2-shot | 70.69 |
|
| 158 |
+
| | Jaqket (Exact Match) | 1-shot | 81.53 |
|
| 159 |
| | MGSM | 5-shot | 28.8 |
|
| 160 |
| **XWinograd (0-shot)** | EN | | 89.03 |
|
| 161 |
| | FR | | 72.29 |
|