Instructions to use AIAT/EXP-mindblow with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AIAT/EXP-mindblow with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AIAT/EXP-mindblow")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AIAT/EXP-mindblow") model = AutoModelForCausalLM.from_pretrained("AIAT/EXP-mindblow", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AIAT/EXP-mindblow with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AIAT/EXP-mindblow" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AIAT/EXP-mindblow", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AIAT/EXP-mindblow
- SGLang
How to use AIAT/EXP-mindblow 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 "AIAT/EXP-mindblow" \ --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": "AIAT/EXP-mindblow", "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 "AIAT/EXP-mindblow" \ --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": "AIAT/EXP-mindblow", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AIAT/EXP-mindblow with Docker Model Runner:
docker model run hf.co/AIAT/EXP-mindblow
added EXP icon
Browse files
README.md
CHANGED
|
@@ -10,9 +10,14 @@ tags:
|
|
| 10 |
---
|
| 11 |
# 🇹🇭 EXP-mindblow 13b 1.0.0
|
| 12 |
|
|
|
|
| 13 |

|
|
|
|
|
|
|
|
|
|
| 14 |
This model is fine-tuned version of openthaigpt/openthaigpt-1.0.0-13b-chat on text-2-sql datasets to generate SQL query.
|
| 15 |
|
| 16 |
-
Recommendation :
|
|
|
|
| 17 |
This model should be used with other LLMs to summarize or synthesize response as the model fine-tuned heavily on SQL may cause
|
| 18 |
some hallucinations when it comes to generating thai and eng texts
|
|
|
|
| 10 |
---
|
| 11 |
# 🇹🇭 EXP-mindblow 13b 1.0.0
|
| 12 |
|
| 13 |
+

|
| 14 |

|
| 15 |
+
|
| 16 |
+
# Overview :
|
| 17 |
+
|
| 18 |
This model is fine-tuned version of openthaigpt/openthaigpt-1.0.0-13b-chat on text-2-sql datasets to generate SQL query.
|
| 19 |
|
| 20 |
+
# Recommendation :
|
| 21 |
+
|
| 22 |
This model should be used with other LLMs to summarize or synthesize response as the model fine-tuned heavily on SQL may cause
|
| 23 |
some hallucinations when it comes to generating thai and eng texts
|