Joseph
Joseph717171
AI & ML interests
None yet
Organizations
None yet
Joseph717171's activity
Update README.md
2
#1 opened 9 days ago
by
Joseph717171
Bigstral-12B-v0.3-32k?
#1 opened 9 days ago
by
Joseph717171
Smaug-LLaMa-3-8B-Instruct in the works?
3
#3 opened 14 days ago
by
Joseph717171
Can you please include the mergkit.yaml
1
#1 opened 14 days ago
by
Joseph717171
Idea for a truly uncensored LLaMa-3-8B
9
#3 opened about 1 month ago
by
Joseph717171
[NEW] Internet access for Assistants
65
#385 opened 3 months ago
by
nsarrazin
Sorry to say this but...
2
#4 opened about 1 month ago
by
Nitral-AI
Modl showing up as Llama instead of phi3 in LMstudio
11
#1 opened about 1 month ago
by
Tirin
I have a few questions for the quantized model quality.
8
#5 opened about 1 month ago
by
HannahKim
Request: Make a Based LLaMa-3-8B and LLaMa-3-70B
3
#1 opened about 1 month ago
by
Joseph717171
Template?
1
#1 opened about 1 month ago
by
grey8
Just have to say - this is the best LLM model I have used to date!
12
#2 opened about 1 month ago
by
billsecond
Thanks Guys!
5
#1 opened about 1 month ago
by
Joseph717171
Please post the imatrix that was used to quantize
1
#1 opened about 1 month ago
by
Joseph717171
Please post the imatrix
#2 opened about 1 month ago
by
Joseph717171
Thank you for providing the imatrix
#1 opened about 1 month ago
by
Joseph717171
I'm struggling making the Q2 version work on my M1 Max machine.
4
#2 opened about 1 month ago
by
LucaColonnello
LLaMa-3-8B mmproj?
4
#2 opened about 1 month ago
by
Joseph717171
What does the abbreviation MFANN stand for?
3
#1 opened about 1 month ago
by
Joseph717171
LM Studio and Bartowski for the clutch and the win!
#2 opened about 1 month ago
by
Joseph717171
It's like Christmas without December! 🌲🎁🤖
#15 opened about 1 month ago
by
Joseph717171
Can you please post your computed imatrices to your repo?
#2 opened about 2 months ago
by
Joseph717171
is this a single expert of all the experts merged?
2
#5 opened about 2 months ago
by
rombodawg
merge method
1
#3 opened about 2 months ago
by
ehartford
I can't load this model on L4 GPU
2
#5 opened about 2 months ago
by
albusdd
PR #5796 is merged
1
#1 opened about 2 months ago
by
Joseph717171
Update added_tokens.json
#1 opened about 2 months ago
by
Joseph717171
My favorite model right now
1
#1 opened about 2 months ago
by
Joseph717171
Mistral 0.2 Base Is Censored, But Not the 0.1 Base.
30
#9 opened 2 months ago
by
Phil337
would you explain more in detail?
2
#2 opened 3 months ago
by
KnutJaegersberg
Update README.md
#3 opened about 2 months ago
by
Joseph717171
Train Mistral 7B 0.2
9
#2 opened 5 months ago
by
mosama
Train OpenChat on Mistral-10.7B-v0.2
#12 opened about 2 months ago
by
Joseph717171
Question about continued training.
5
#14 opened 2 months ago
by
neverdoubt
Fine-Tune Joseph717171/Hermes-2-Pro-Mistral-10.7B on IKM/ ANIMA-Phi-Neptune
#1 opened 2 months ago
by
Joseph717171
Further Fine-Tune Joseph717171/Mistral-10.7B-v0.2 on IKM and ANIMA-Phi-Neptune
2
#1 opened 2 months ago
by
Joseph717171
Update README.md
#1 opened 2 months ago
by
Joseph717171
Thanks for the paper!!!
#13 opened 2 months ago
by
Joseph717171
Further Fine-Tune Joseph717171/ANIMA-Phi-Neptune-Mistral-10.7B
2
#4 opened 2 months ago
by
Joseph717171
Thanks for posting this to your repo! 😁
1
#2 opened 2 months ago
by
Joseph717171
Submit model to the OpenLLM Leaderboard for Benchmarking
#1 opened 2 months ago
by
Joseph717171
Submit model to the OpenLLM Leaderboard for Benchmarking
#1 opened 2 months ago
by
Joseph717171
Please do 2B model
1
#2 opened 3 months ago
by
theodotus
Unquantized Files for this Massive Model
2
#1 opened 4 months ago
by
Joseph717171
Where's the Sauce?
3
#1 opened 2 months ago
by
Joseph717171
How do I use the chat template in oobabooga/sillytavern/koboldcpp?
2
#2 opened 2 months ago
by
siddhesh22
Fine-Tune Request: Bagel-dpo using AetherResearch/Cerebrum-1.0-7b
#3 opened 2 months ago
by
Joseph717171
Submit Mistral-Evolved-11b-v0.1 to the HuggingFaceH4 Open LLM LeaderBoard
3
#4 opened 2 months ago
by
Joseph717171
Spelling mistake in your quantize example
1
#3 opened 2 months ago
by
Joseph717171
Can't convert to GGUF
2
#1 opened 2 months ago
by
Joseph717171
Fine-Tune With Unsloth using the Free Tier
1
#2 opened 2 months ago
by
Joseph717171
I made the next gen mistral model. Id love to see you train it in the same way!
2
#4 opened 2 months ago
by
rombodawg
Can't work with Ollama
4
#1 opened 3 months ago
by
dboyplus
WestLake-7B-v2_wikitext-2-raw.imatrix
#17 opened 3 months ago
by
Joseph717171
Train NousResearch/Hermes-2-Pro-Mistral-7B on the Internal Knowledge Map dataset
3
#4 opened 3 months ago
by
Joseph717171