I am now basing all future releases of the MFANN experiment using llama-3 as a base model, I may continue fine-tuning mistral-7b every other release
this model uses meta's llama-3 as its base, and benchmarks are pending
changed the model name to MFANNV0.6 due to a failed benchmark and the need to resubmit
edit: due to continuous benchmark fails I am renaming the model back to MFANNver0.6, the 3b model is also failing benchmarks for some reason despite the fact both models run fine on my machine :(
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.