Instructions to use Technoculture/MT7Bi-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Technoculture/MT7Bi-dpo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Technoculture/MT7Bi-dpo")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Technoculture/MT7Bi-dpo") model = AutoModelForCausalLM.from_pretrained("Technoculture/MT7Bi-dpo") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Technoculture/MT7Bi-dpo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Technoculture/MT7Bi-dpo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Technoculture/MT7Bi-dpo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Technoculture/MT7Bi-dpo
- SGLang
How to use Technoculture/MT7Bi-dpo 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 "Technoculture/MT7Bi-dpo" \ --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": "Technoculture/MT7Bi-dpo", "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 "Technoculture/MT7Bi-dpo" \ --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": "Technoculture/MT7Bi-dpo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Technoculture/MT7Bi-dpo with Docker Model Runner:
docker model run hf.co/Technoculture/MT7Bi-dpo
Update README.md
#1
by satyamt - opened
README.md
CHANGED
|
@@ -7,4 +7,13 @@ base_model: Technoculture/MT7Bi-sft
|
|
| 7 |
|
| 8 |
# MT7Bi-dpo
|
| 9 |
|
| 10 |
-
[Technoculture/MT7Bi-sft (base)](https://huggingface.co/Technoculture/MT7Bi-sft) + [Technoculture/MT7Bi-alpha-dpo-v0.2 (adapter)](https://huggingface.co/Technoculture/MT7Bi-alpha-dpo-v0.2)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
# MT7Bi-dpo
|
| 9 |
|
| 10 |
+
[Technoculture/MT7Bi-sft (base)](https://huggingface.co/Technoculture/MT7Bi-sft) + [Technoculture/MT7Bi-alpha-dpo-v0.2 (adapter)](https://huggingface.co/Technoculture/MT7Bi-alpha-dpo-v0.2)
|
| 11 |
+
|
| 12 |
+
# Open LLM Leaderboard
|
| 13 |
+
|
| 14 |
+
| Model Name | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
| 15 |
+
| ------------------ | -------- | --------- | ---- | ---------- | ---------- | -------- |
|
| 16 |
+
| Orca-2-7b | **78.4** | 76.1 | 53.7 | **52.4** | **74.2** | **47.2** |
|
| 17 |
+
| LLAMA-2-7b | 43.2 | **77.1** | 44.4 | 38.7 | 69.5 | 16 |
|
| 18 |
+
| MT7Bi-sft | 54.1 | 75.11 | - | 43.08 | 72.14 | 15.54 |
|
| 19 |
+
| MT7bi-dpo | 54.69 | 75.89 | 52.82 | 45.48 | 71.58 | 25.93 |
|