Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
HuggingFaceTB
/
SmolLM2-1.7B-Instruct
like
382
Follow
Hugging Face TB Research
522
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
18
Train
Deploy
Use this model
main
SmolLM2-1.7B-Instruct
/
onnx
8 contributors
History:
3 commits
Xenova
HF staff
Fix q8 weights (use uint8 for q8; int8 produces poor results) (
#18
)
b75eb65
verified
1 day ago
model.onnx
179 kB
LFS
Upload optimized ONNX weights (deduplicated) (#17)
2 days ago
model.onnx_data
6.85 GB
LFS
Upload optimized ONNX weights (deduplicated) (#17)
2 days ago
model_bnb4.onnx
1.31 GB
LFS
Upload optimized ONNX weights (deduplicated) (#17)
2 days ago
model_fp16.onnx
1.33 GB
LFS
Upload optimized ONNX weights (deduplicated) (#17)
2 days ago
model_fp16.onnx_data
2.1 GB
LFS
Upload ONNX weights (#1)
27 days ago
model_int8.onnx
1.71 GB
LFS
Upload optimized ONNX weights (deduplicated) (#17)
2 days ago
model_q4.onnx
1.41 GB
LFS
Upload optimized ONNX weights (deduplicated) (#17)
2 days ago
model_q4f16.onnx
1.11 GB
LFS
Upload optimized ONNX weights (deduplicated) (#17)
2 days ago
model_quantized.onnx
1.71 GB
LFS
Fix q8 weights (use uint8 for q8; int8 produces poor results) (#18)
1 day ago
model_uint8.onnx
1.71 GB
LFS
Upload optimized ONNX weights (deduplicated) (#17)
2 days ago
