Text Generation
PEFT
Safetensors
dia
carbon-footprint
energy-efficiency
sustainability
conversational
Instructions to use DIA-MVP/tinyllama-lora-cpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use DIA-MVP/tinyllama-lora-cpu with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0") model = PeftModel.from_pretrained(base_model, "DIA-MVP/tinyllama-lora-cpu") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,6 +1,36 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags: []
|
| 4 |
+
dia_version: '0.1'
|
| 5 |
+
dia_report:
|
| 6 |
+
scope: incremental
|
| 7 |
+
lineage:
|
| 8 |
+
- model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 9 |
+
relation: lora
|
| 10 |
+
compute:
|
| 11 |
+
hardware:
|
| 12 |
+
gpu: cpu-80core
|
| 13 |
+
count: 1
|
| 14 |
+
duration_gpu_hours: 1.0613
|
| 15 |
+
footprint:
|
| 16 |
+
energy_kwh:
|
| 17 |
+
value: 0.0515
|
| 18 |
+
quality: measured
|
| 19 |
+
carbon_kgco2eq:
|
| 20 |
+
value: 0.0033
|
| 21 |
+
quality: measured
|
| 22 |
+
water_liters:
|
| 23 |
+
value:
|
| 24 |
+
- 0.093
|
| 25 |
+
- 0.206
|
| 26 |
+
quality: estimated-from-default-wue
|
| 27 |
+
context:
|
| 28 |
+
region: ca-on
|
| 29 |
+
carbon_intensity: 0.03
|
| 30 |
+
wue_l_per_kwh:
|
| 31 |
+
- 1.8
|
| 32 |
+
- 4.0
|
| 33 |
+
tool: codecarbon
|
| 34 |
---
|
| 35 |
|
| 36 |
# Model Card for Model ID
|