ISTA-DASLab
/

Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16

Commit History

Update tokenizer_config.json

6ece93b
verified

BlackSamorez commited on May 13

Update tokenizer_config.json (#2)

eb41f2a
verified

BlackSamorez commited on May 6

Update README.md

ffdffd6
verified

SpiridonSunRotator commited on May 3

Update README.md

7bdd700
verified

SpiridonSunRotator commited on May 2

Updated metrics for improved version of the model

f2991f9
verified

SpiridonSunRotator commited on May 2

Uploaded improved version of quantized model

c688054
verified

SpiridonSunRotator commited on May 2

Added more evaluations

90f515b
verified

SpiridonSunRotator commited on Apr 22

Added evaluation metrics

7d8c61e
verified

SpiridonSunRotator commited on Apr 22

Create README.md

4c3d1a4
verified

SpiridonSunRotator commited on Apr 21

Uploaded Meta-Llama-3-8B-Instruct with AQLM 1x16 quantization

2c4df03
verified

SpiridonSunRotator commited on Apr 21

initial commit

ce10727
verified

SpiridonSunRotator commited on Apr 21