Instructions to use CausalLM/miniG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CausalLM/miniG with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CausalLM/miniG", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CausalLM/miniG", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CausalLM/miniG with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CausalLM/miniG" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CausalLM/miniG", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CausalLM/miniG
- SGLang
How to use CausalLM/miniG 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 "CausalLM/miniG" \ --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": "CausalLM/miniG", "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 "CausalLM/miniG" \ --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": "CausalLM/miniG", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CausalLM/miniG with Docker Model Runner:
docker model run hf.co/CausalLM/miniG
Commit ·
050089e
1
Parent(s): 0b93b1e
Update README.md
Browse files
README.md
CHANGED
|
@@ -55,7 +55,7 @@ Despite the absence of thorough alignment with human preferences, the model is u
|
|
| 55 |
|
| 56 |
**Regarding [Benchmark Scores](https://huggingface.co/spaces/JosephusCheung/Goodharts-Law-on-Benchmarks-a-Page-for-miniG):** Generally, you shouldn't worry too much about them, as people can always train specifically to achieve good results. We mainly use them as a smoke test, a quick check to ensure no major regressions have occurred. In fact, if you actually read through the benchmark questions themselves, you'll often find yourself chuckling at how inane, low-quality, or even downright silly they are.
|
| 57 |
|
| 58 |
-
**Regarding training:** The final released version was trained using a merge of multiple candidate models in an attempt to improve performance. However, we were unable to conclusively determine whether this was effective. Excluding candidate versions, an efficient
|
| 59 |
|
| 60 |
**Disclaimer:** Please note that the model was trained on unfiltered internet data. Since we do not have the capacity to vet all of it, there may be a substantial amount of objectionable content, pornography, violence, and offensive language present that we are unable to remove. Therefore, you will still need to complete your own checks on the model's safety and filter keywords in the output. Due to computational resource constraints, we are presently unable to implement RLHF for the model's ethics and safety, nor training on SFT samples that refuse to answer certain questions for restrictive fine-tuning.
|
| 61 |
|
|
|
|
| 55 |
|
| 56 |
**Regarding [Benchmark Scores](https://huggingface.co/spaces/JosephusCheung/Goodharts-Law-on-Benchmarks-a-Page-for-miniG):** Generally, you shouldn't worry too much about them, as people can always train specifically to achieve good results. We mainly use them as a smoke test, a quick check to ensure no major regressions have occurred. In fact, if you actually read through the benchmark questions themselves, you'll often find yourself chuckling at how inane, low-quality, or even downright silly they are.
|
| 57 |
|
| 58 |
+
**Regarding training:** The final released version was trained using a merge of multiple candidate models in an attempt to improve performance. However, we were unable to conclusively determine whether this was effective. Excluding candidate versions, an efficient naïve fine-tuning should be achievable within one day on 16 nodes of 8*A100-80G. Based on this, we estimate the carbon emissions to be 700 kg CO2 eq.
|
| 59 |
|
| 60 |
**Disclaimer:** Please note that the model was trained on unfiltered internet data. Since we do not have the capacity to vet all of it, there may be a substantial amount of objectionable content, pornography, violence, and offensive language present that we are unable to remove. Therefore, you will still need to complete your own checks on the model's safety and filter keywords in the output. Due to computational resource constraints, we are presently unable to implement RLHF for the model's ethics and safety, nor training on SFT samples that refuse to answer certain questions for restrictive fine-tuning.
|
| 61 |
|