Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Mistral-7B-v0.1-sharded – AI Model by kkboy1 | AlphaNeural AI
You can deploy this model and start earning money today!
kkboy1
/
Mistral-7B-v0.1-sharded
like
0
transformers
pytorch
mistral
text-generation
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Just a version of
https://huggingface.co/mistralai/Mistral-7B-v0.1
which is sharded to 2GB as to reduce the ram required when loading.
original_base_model: MistralForCausalLM = AutoModelForCausalLM.from_pretrained( pretrained_model_name_or_path="mistralai/Mistral-7B-v0.1", device_map="auto", torch_dtype=torch.float16, offload_folder="offload", trust_remote_code=True, low_cpu_mem_usage=True )
original_base_model.save_pretrained( save_directory="kkboy1/Mistral-7B-v0.1-sharded", max_shard_size="2GB", push_to_hub=True )
