Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
fzzhang_-_Marcoroni-neural-chat-7B-v2_gsm8k_merged-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
fzzhang_-_Marcoroni-neural-chat-7B-v2_gsm8k_merged-gguf
like
0
endpoints_compatible
gguf
template
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
Marcoroni-neural-chat-7B-v2_gsm8k_merged - GGUF
Model creator:
https://huggingface.co/fzzhang/
Original model:
https://huggingface.co/fzzhang/Marcoroni-neural-chat-7B-v2_gsm8k_merged/
Name
Quant method
Size
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q2_K.gguf
Q2_K
2.53GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.IQ3_XS.gguf
IQ3_XS
2.81GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.IQ3_S.gguf
IQ3_S
2.96GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q3_K_S.gguf
Q3_K_S
2.95GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.IQ3_M.gguf
IQ3_M
3.06GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q3_K.gguf
Q3_K
3.28GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q3_K_M.gguf
Q3_K_M
3.28GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q3_K_L.gguf
Q3_K_L
3.56GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.IQ4_XS.gguf
IQ4_XS
3.67GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q4_0.gguf
Q4_0
3.83GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.IQ4_NL.gguf
IQ4_NL
3.87GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q4_K_S.gguf
Q4_K_S
3.86GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q4_K.gguf
Q4_K
4.07GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q4_K_M.gguf
Q4_K_M
4.07GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q4_1.gguf
Q4_1
4.24GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q5_0.gguf
Q5_0
4.65GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q5_K_S.gguf
Q5_K_S
4.65GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q5_K.gguf
Q5_K
4.78GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q5_K_M.gguf
Q5_K_M
4.78GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q5_1.gguf
Q5_1
5.07GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q6_K.gguf
Q6_K
5.53GB
Marcoroni-neural-chat-7B-v2_gsm8k_merged.Q8_0.gguf
Q8_0
7.17GB
Original model description:
license: apache-2.0 datasets:
gsm8k language:
en
Marcoroni-neural-chat-7B-v2_gsm8k
This model is a fine-tuned version of
Toten5/Marcoroni-neural-chat-7B-v2
on the GSM8K dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 8
seed: 0
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
Training results
Framework versions
PEFT 0.7.2.dev0
Transformers 4.36.2
Pytorch 2.1.2
Datasets 2.16.1
Tokenizers 0.15.1
