15 lines
286 B
Markdown
15 lines
286 B
Markdown
|
---
|
||
|
|
base_model: state-spaces/mamba-2.8b-hf
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
model_creator: state-spaces
|
||
|
|
model_name: mamba-2.8b
|
||
|
|
model_type: MambaForCausalLM
|
||
|
|
inference: false
|
||
|
|
---
|
||
|
|
|
||
|
|
# mamba-2.8b-GGUF
|
||
|
|
|
||
|
|
Quantized mamba-2.8b models using recent versions of llama.cpp.
|
||
|
|
|