ko
mirek190
AI & ML interests
None yet
Organizations
None yet
mirek190's activity
Hi - are you going add new llama 70b version as well?
4
#1 opened 9 days ago
by
mirek190
OK llama 3 8b model is INSANE. Is almost as good as wizard 2 8x22b!
52
#5 opened 21 days ago
by
mirek190
template for llamacpp
1
#4 opened 21 days ago
by
mirek190
Template for llama3 using llamacpp
5
#7 opened 21 days ago
by
mirek190
That wizardlm 8x22b is very advanced.!
16
#8 opened 24 days ago
by
mirek190
llama-cpp failed
9
#3 opened 3 months ago
by
gptwin
Code LLaMA 70b run locally on my pc .... is bad.
13
#2 opened 3 months ago
by
mirek190
WOW - best opensource llm I ever seen !
60
#1 opened 5 months ago
by
mirek190
GPTQ model is available
6
#1 opened 4 months ago
by
MaziyarPanahi
New Leader!
6
#2 opened 4 months ago
by
DKRacingFan
WOW ..just wow
19
#1 opened 4 months ago
by
mirek190
gguf weight ?
5
#2 opened 4 months ago
by
wukongai
Update or delete
3
#48 opened 5 months ago
by
rombodawg
Reasoning this model id worse that original mixtral-8x7b-instruct model.
2
#4 opened 5 months ago
by
mirek190
Do not even try to download lower that 8 bit ;P
4
#2 opened 5 months ago
by
mirek190
How many tokens per second?
12
#9 opened 5 months ago
by
Hoioi
Wait? 4x13b model?
1
#1 opened 5 months ago
by
mirek190
Why is the response slower than the 70B model?
7
#9 opened 5 months ago
by
shalene
How do you get the reported Arc score of 85.8?
4
#3 opened 5 months ago
by
Phil337
chatbot giving weird responses
20
#6 opened 5 months ago
by
hammad93
Great model
2
#1 opened 5 months ago
by
dranger003
Issue with Mixtral-8x7B-Instruct-v0.1-GGUF Model: 'blk.0.ffn_gate.weight' Tensor Not Found
3
#2 opened 5 months ago
by
littleworth
Hello - prompt template ?
1
#1 opened 5 months ago
by
mirek190
MoE mixtral verion? ..That is fast ;)
#1 opened 5 months ago
by
mirek190
Issue with Mixtral-8x7B-Instruct-v0.1-GGUF Model: 'blk.0.ffn_gate.weight' Tensor Not Found
4
#4 opened 5 months ago
by
littleworth
[FLAG] TigerResearch/tigerbot-70b-chat-v4-4k
23
#438 opened 5 months ago
by
fblgit
YOU ARE FAST!
2
#1 opened 5 months ago
by
ajv009
Hi Bloke add una-cybertron-7b-v2-bf16 please ;)
#1 opened 5 months ago
by
mirek190
Bloke add una-cybertron-7b-v2 model please
#3 opened 5 months ago
by
mirek190
Really impressive!
15
#1 opened 6 months ago
by
Thireus
What's the prompt format for v1.2?
1
#3 opened 7 months ago
by
gotzmann
Free and ready to use openchat_3.5-GGUF model as OpenAI API compatible endpoint
1
#4 opened 6 months ago
by
limcheekin
Free and ready to use zephyr-7B-beta-GGUF model as OpenAI API compatible endpoint
12
#2 opened 6 months ago
by
limcheekin
llamacpp main: build = 1426 (ad93962) error
1
#2 opened 7 months ago
by
mirek190
dolphin-2.1-mistral-7B is even better than openorca-mistral-7b unbelievable
5
#1 opened 7 months ago
by
mirek190
HumanEval(pass@1) 75.5 ..........hmmmmm that's more than even GPT-4
#1 opened 7 months ago
by
mirek190
What is the context length of this model?
4
#4 opened 7 months ago
by
denrykhlov
Hey bloke you should make new version of that model
3
#1 opened 7 months ago
by
mirek190
Can’t get to work in inference endpoints
2
#3 opened 7 months ago
by
joeofportland
I made some test that 7B model. - I am impressed
2
#1 opened 7 months ago
by
mirek190
hardware requirements
2
#4 opened 8 months ago
by
wildheart25c
Your model is at the top of leaderboard any way to play with it
1
#4 opened 8 months ago
by
MarxistLeninist
Brilliant!
15
#1 opened 8 months ago
by
shafiqalibhai
how to use 128k context?
8
#1 opened 8 months ago
by
mirek190
Those score benchmarks look insane ...
9
#2 opened 8 months ago
by
mirek190
This modes is the top 1 ....
#3 opened 8 months ago
by
mirek190
Are the weights updated?
3
#1 opened 8 months ago
by
krao
This model looks insanely good for coding ( 73.2 for humanEval )!
18
#1 opened 9 months ago
by
mirek190