Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
pantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
pantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8-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
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8 - GGUF
Model creator:
https://huggingface.co/pantelis-ninja/
Original model:
https://huggingface.co/pantelis-ninja/unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8/
Name
Quant method
Size
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q2_K.gguf
Q2_K
1.19GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.IQ3_XS.gguf
IQ3_XS
1.3GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.IQ3_S.gguf
IQ3_S
1.36GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q3_K_S.gguf
Q3_K_S
1.35GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.IQ3_M.gguf
IQ3_M
1.39GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q3_K.gguf
Q3_K
1.48GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q3_K_M.gguf
Q3_K_M
1.48GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q3_K_L.gguf
Q3_K_L
1.59GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.IQ4_XS.gguf
IQ4_XS
1.63GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q4_0.gguf
Q4_0
1.7GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.IQ4_NL.gguf
IQ4_NL
1.71GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q4_K_S.gguf
Q4_K_S
1.71GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q4_K.gguf
Q4_K
1.8GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q4_K_M.gguf
Q4_K_M
1.8GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q4_1.gguf
Q4_1
1.86GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q5_0.gguf
Q5_0
2.02GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q5_K_S.gguf
Q5_K_S
2.02GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q5_K.gguf
Q5_K
2.07GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q5_K_M.gguf
Q5_K_M
2.07GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q5_1.gguf
Q5_1
2.18GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q6_K.gguf
Q6_K
2.36GB
unsloth-Qwen2.5-3B-Instruct-18_r-8_lr-0.0005_ms-75_gas-2_batch-size-8.Q8_0.gguf
Q8_0
3.06GB
Original model description:
base_model: unsloth/qwen2.5-3b-instruct-bnb-4bit tags:
text-generation-inference
transformers
unsloth
qwen2
trl
sft license: apache-2.0 language:
en
Uploaded model
Developed by:
pantelis-ninja
License:
apache-2.0
Finetuned from model :
unsloth/qwen2.5-3b-instruct-bnb-4bit
This qwen2 model was trained 2x faster with
Unsloth
and Huggingface's TRL library.
