Reinforcement Learning
Transformers
Safetensors
qwen2
text-generation
code-generation
software-engineering
long-context
quantized
awq
4-bit precision
72b
swe-bench
lmdeploy
text-generation-inference
Instructions to use twhitworth/KAT-Dev-72B-Exp-AWQ-INT4-noct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use twhitworth/KAT-Dev-72B-Exp-AWQ-INT4-noct with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("twhitworth/KAT-Dev-72B-Exp-AWQ-INT4-noct") model = AutoModelForCausalLM.from_pretrained("twhitworth/KAT-Dev-72B-Exp-AWQ-INT4-noct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
#2 opened 12 months ago
by
twhitworth