Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
HuggingFaceTB
/
SmolLM2-1.7B-Instruct
like
459
Follow
Hugging Face TB Research
821
Text Generation
Transformers
TensorBoard
ONNX
Safetensors
Transformers.js
English
llama
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
21
Train
Deploy
Use this model
Fix q8 weights (use uint8 for q8; int8 produces poor results)
#18
by
Xenova
HF staff
- opened
Nov 26, 2024
base:
refs/heads/main
←
from:
refs/pr/18
Discussion
Files changed
+2
-2
Upload fixed q8 ONNX models (reduce_range=True, per_channel=True)
06633a3e
Xenova
Hugging Face TB Research org
Nov 26, 2024
•
edited Nov 26, 2024
Slightly better, but not great. Will play around with other settings
👀
1
1
+
Upload folder using huggingface_hub
0919b6ca
Fix q8 weights (use uint8 for q8; int8 produces poor results)
4f13109a
Xenova
changed pull request title from
Upload fixed q8 ONNX models (reduce_range=True, per_channel=True)
to
Fix q8 weights (use uint8 for q8; int8 produces poor results)
Nov 26, 2024
Xenova
changed pull request status to
merged
Nov 26, 2024
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Comment
·
Sign up
or
log in
to comment
