Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
sonthenguyen_-_zephyr-sft-bnb-4bit-DPO-mtbc-213steps-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
sonthenguyen_-_zephyr-sft-bnb-4bit-DPO-mtbc-213steps-gguf
like
0
conversational
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
zephyr-sft-bnb-4bit-DPO-mtbc-213steps - GGUF
Model creator:
https://huggingface.co/sonthenguyen/
Original model:
https://huggingface.co/sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbc-213steps/
Name
Quant method
Size
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q2_K.gguf
Q2_K
2.53GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.IQ3_XS.gguf
IQ3_XS
2.81GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.IQ3_S.gguf
IQ3_S
2.96GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q3_K_S.gguf
Q3_K_S
2.95GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.IQ3_M.gguf
IQ3_M
3.06GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q3_K.gguf
Q3_K
3.28GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q3_K_M.gguf
Q3_K_M
3.28GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q3_K_L.gguf
Q3_K_L
3.56GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.IQ4_XS.gguf
IQ4_XS
3.67GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q4_0.gguf
Q4_0
3.83GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.IQ4_NL.gguf
IQ4_NL
3.87GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q4_K_S.gguf
Q4_K_S
3.86GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q4_K.gguf
Q4_K
4.07GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q4_K_M.gguf
Q4_K_M
4.07GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q4_1.gguf
Q4_1
4.24GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q5_0.gguf
Q5_0
4.65GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q5_K_S.gguf
Q5_K_S
4.65GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q5_K.gguf
Q5_K
4.78GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q5_K_M.gguf
Q5_K_M
4.78GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q5_1.gguf
Q5_1
5.07GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q6_K.gguf
Q6_K
5.53GB
zephyr-sft-bnb-4bit-DPO-mtbc-213steps.Q8_0.gguf
Q8_0
7.17GB
Original model description:
license: apache-2.0 pipeline_tag: text-generation library_name: transformers
TrainOutput(global_step=213, training_loss=0.09253080396371667, metrics={'train_runtime': 1906.7032, 'train_samples_per_second': 1.791, 'train_steps_per_second': 0.112, 'total_flos': 0.0, 'train_loss': 0.09253080396371667, 'epoch': 0.4991212653778559})
base_model: unsloth/zephyr-sft-bnb-4bit language:
en license: apache-2.0 tags:
text-generation-inference
transformers
unsloth
mistral
trl
dpo
Uploaded model
Developed by:
sonthenguyen
License:
apache-2.0
Finetuned from model :
unsloth/zephyr-sft-bnb-4bit
This mistral model was trained 2x faster with
Unsloth
and Huggingface's TRL library.
