Text Generation
Transformers
Safetensors
English
Generated from Trainer
axolotl
mistral
instruct
finetune
chatml
gpt4
synthetic data
distillation
Instructions to use maxrovalio/helloboi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maxrovalio/helloboi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="maxrovalio/helloboi")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("maxrovalio/helloboi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use maxrovalio/helloboi with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "maxrovalio/helloboi" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "maxrovalio/helloboi", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/maxrovalio/helloboi
- SGLang
How to use maxrovalio/helloboi 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 "maxrovalio/helloboi" \ --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": "maxrovalio/helloboi", "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 "maxrovalio/helloboi" \ --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": "maxrovalio/helloboi", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use maxrovalio/helloboi with Docker Model Runner:
docker model run hf.co/maxrovalio/helloboi
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,6 +41,25 @@ as its base model, finetuned on only half of the layers using laserQLoRA. The pr
|
|
| 41 |
|
| 42 |
## Evaluation data
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
🏆 Evaluation
|
| 45 |
|
| 46 |
| Task |Version| Metric |Value| |Stderr|
|
|
|
|
| 41 |
|
| 42 |
## Evaluation data
|
| 43 |
|
| 44 |
+
Task Version Metric Value StdErr
|
| 45 |
+
---------------------------------------------------------------------
|
| 46 |
+
agieval_aqua_rat 0 acc 28.35% 2.83%
|
| 47 |
+
agieval_aqua_rat 0 acc_norm 26.38% 2.77%
|
| 48 |
+
agieval_logiqa_en 0 acc 38.25% 1.91%
|
| 49 |
+
agieval_logiqa_en 0 acc_norm 38.10% 1.90%
|
| 50 |
+
agieval_lsat_ar 0 acc 23.91% 2.82%
|
| 51 |
+
agieval_lsat_ar 0 acc_norm 23.48% 2.80%
|
| 52 |
+
agieval_lsat_lr 0 acc 52.75% 2.21%
|
| 53 |
+
agieval_lsat_lr 0 acc_norm 53.92% 2.21%
|
| 54 |
+
agieval_lsat_rc 0 acc 66.91% 2.87%
|
| 55 |
+
agieval_lsat_rc 0 acc_norm 67.29% 2.87%
|
| 56 |
+
agieval_sat_en 0 acc 78.64% 2.86%
|
| 57 |
+
agieval_sat_en 0 acc_norm 78.64% 2.86%
|
| 58 |
+
agieval_sat_en_without_passage 0 acc 45.15% 3.48%
|
| 59 |
+
agieval_sat_en_without_passage 0 acc_norm 44.17% 3.47%
|
| 60 |
+
agieval_sat_math 0 acc 33.18% 3.18%
|
| 61 |
+
agieval_sat_math 0 acc_norm 31.36% 3.14%
|
| 62 |
+
|
| 63 |
🏆 Evaluation
|
| 64 |
|
| 65 |
| Task |Version| Metric |Value| |Stderr|
|