Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
terry69_-_qwen_1.8_feedback_dirty-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
terry69_-_qwen_1.8_feedback_dirty-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
qwen_1.8_feedback_dirty - GGUF
Model creator:
https://huggingface.co/terry69/
Original model:
https://huggingface.co/terry69/qwen_1.8_feedback_dirty/
Name
Quant method
Size
qwen_1.8_feedback_dirty.Q2_K.gguf
Q2_K
0.79GB
qwen_1.8_feedback_dirty.IQ3_XS.gguf
IQ3_XS
0.86GB
qwen_1.8_feedback_dirty.IQ3_S.gguf
IQ3_S
0.89GB
qwen_1.8_feedback_dirty.Q3_K_S.gguf
Q3_K_S
0.89GB
qwen_1.8_feedback_dirty.IQ3_M.gguf
IQ3_M
0.92GB
qwen_1.8_feedback_dirty.Q3_K.gguf
Q3_K
0.95GB
qwen_1.8_feedback_dirty.Q3_K_M.gguf
Q3_K_M
0.95GB
qwen_1.8_feedback_dirty.Q3_K_L.gguf
Q3_K_L
0.98GB
qwen_1.8_feedback_dirty.IQ4_XS.gguf
IQ4_XS
1.01GB
qwen_1.8_feedback_dirty.Q4_0.gguf
Q4_0
1.04GB
qwen_1.8_feedback_dirty.IQ4_NL.gguf
IQ4_NL
1.05GB
qwen_1.8_feedback_dirty.Q4_K_S.gguf
Q4_K_S
1.08GB
qwen_1.8_feedback_dirty.Q4_K.gguf
Q4_K
1.13GB
qwen_1.8_feedback_dirty.Q4_K_M.gguf
Q4_K_M
1.13GB
qwen_1.8_feedback_dirty.Q4_1.gguf
Q4_1
1.13GB
qwen_1.8_feedback_dirty.Q5_0.gguf
Q5_0
1.22GB
qwen_1.8_feedback_dirty.Q5_K_S.gguf
Q5_K_S
1.24GB
qwen_1.8_feedback_dirty.Q5_K.gguf
Q5_K
1.28GB
qwen_1.8_feedback_dirty.Q5_K_M.gguf
Q5_K_M
1.28GB
qwen_1.8_feedback_dirty.Q5_1.gguf
Q5_1
1.31GB
qwen_1.8_feedback_dirty.Q6_K.gguf
Q6_K
1.47GB
qwen_1.8_feedback_dirty.Q8_0.gguf
Q8_0
1.82GB
Original model description:
library_name: transformers license: other base_model: Qwen/Qwen1.5-1.8B-Chat tags:
alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
preference-data model-index:
name: qwen_1.8_feedback_dirty results: []
qwen_1.8_feedback_dirty
This model is a fine-tuned version of
Qwen/Qwen1.5-1.8B-Chat
on the preference-data 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: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 16
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
Training results
Framework versions
Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0
