Lucas Atkins PRO
Crystalcareai
AI & ML interests
MoE Models & Dataset Curation
Organizations
Crystalcareai's activity
Great model
2
#1 opened 3 days ago
by
smchapman54
Congrats!
11
#1 opened 2 days ago
by
aaronday3
phi-3 small has been released and it is a game changer
1
#2 opened 6 days ago
by
sebastienbo
So this is like Lora adapters, but for the GPU rich?
3
#1 opened 7 days ago
by
fieryTransition
Best model i've tried (sometimes?)
7
#1 opened 13 days ago
by
saishf
duplicated output.weight tensor
1
#2 opened 13 days ago
by
mradermacher
Update README.md
1
#3 opened 13 days ago
by
saishf
rope theta?
1
#1 opened 13 days ago
by
bdambrosio
You're mentioning Meta's license on a qwen model
1
#1 opened 16 days ago
by
xalkoi
Is this "dolphin" uncensored?
2
#2 opened 20 days ago
by
scubadrv
GGUF Models struggle with ChatML format in LMStudio for me
3
#3 opened 19 days ago
by
tculler91
large context Dolphin Llama70b?
2
#6 opened 22 days ago
by
Alias1964
Thank you very much for the model I have a question
1
#1 opened 23 days ago
by
NickyNicky
Anyone else getting random Javascript keywords and errors?
7
#18 opened 24 days ago
by
danthegoodman1
Oh Come on
14
#1 opened about 1 month ago
by
supercharge19
Has anyone tried this gguf with agentic framework?
3
#6 opened about 1 month ago
by
BigDeeper
How do you calc the relevance score?
1
#2 opened about 1 month ago
by
raincandy-u
Is this really an uncensored model?
4
#5 opened about 1 month ago
by
sumant4ssm
This is not uncensored
1
#4 opened about 1 month ago
by
sumant4ssm
LoRA cancels pre-review
3
#20 opened about 1 month ago
by
WbjuSrceu
Does the custom System Prompt does not work with the llama 3 models?
3
#14 opened about 1 month ago
by
ishanparihar
Please delete, I made a mistake
#1 opened about 1 month ago
by
QuamtumX
validation loss
1
#3 opened about 1 month ago
by
jacek2024
Why does this one perform substantially worse in some tests?
5
#2 opened about 1 month ago
by
QuamtumX
add axolotl tag
#12 opened about 1 month ago
by
winglian
Failed to uncensor?
3
#4 opened about 1 month ago
by
BlueNipples
Fix Incorrect Prompt Template defined in tokenizer_config.json
#3 opened about 1 month ago
by
Mikael110
No gemmoe branch in github
2
#7 opened about 1 month ago
by
rabimba
Librarian Bot: Add language metadata for dataset
#2 opened about 1 month ago
by
librarian-bot
Update README.md
#3 opened 2 months ago
by
Crystalcareai
Delete model.safetensors
#1 opened 2 months ago
by
Crystalcareai
Delete model.safetensors
#2 opened 2 months ago
by
Crystalcareai
Delete model.safetensors
1
#3 opened 2 months ago
by
Crystalcareai
Minimal inference code
5
#1 opened 2 months ago
by
thomaskalnik
Upload 7 files
#4 opened 2 months ago
by
Crystalcareai
Add custom modeling_files
1
#3 opened 2 months ago
by
Crystalcareai
What is the reason why gguf cannot be quantized?
5
#3 opened 2 months ago
by
huggingfacess
flash_attn requirement prevents loading on macos
2
#6 opened 2 months ago
by
ptx0
from_pretrained() extremely slow
2
#5 opened 2 months ago
by
jmjzz
Question about the modeling_code
2
#7 opened 3 months ago
by
damerajee
Can't convert to safetensors
1
#6 opened 3 months ago
by
bartowski
Someone please make GGUF versions (-)
2
#5 opened 3 months ago
by
huggingfacess
Memory requirement
3
#4 opened 3 months ago
by
jmjzz
Mergekit source
4
#2 opened 3 months ago
by
Locutusque
Questions
1
#1 opened 3 months ago
by
sl33pyC01E
Librarian Bot: Add language metadata for dataset
#2 opened 3 months ago
by
librarian-bot
Datasets used
2
#2 opened 3 months ago
by
Locutusque
Is the training code details released
2
#4 opened 3 months ago
by
Milo11
Interesting dataset, what criteria did you have to select the data?
1
#1 opened 3 months ago
by
NickyNicky
Evaluation result?
3
#1 opened 3 months ago
by
yixinsong
Any positive/negative prompts for merging?
3
#2 opened 3 months ago
by
adi-kmt