Hugging Face's logo
kas's picture
14 8 10

kas

shing3232
AkiraChisaka's profile picture jiting's profile picture hjije's profile picture
·

AI & ML interests

None yet

Organizations

None yet

shing3232's activity

New activity in SakuraLLM/Sakura-14B-Qwen2beta-v0.9.2-GGUF about 2 months ago

CUDA运行不了BF16模型？

2
#1 opened about 2 months ago by NeuronAstate
New activity in Qwen/Qwen1.5-7B-Chat-GGUF about 2 months ago

Please post f16 quantization.

8
#1 opened about 2 months ago by ZeroWw
New activity in Qwen/CodeQwen1.5-7B-Chat 3 months ago

What are the diffences of this with Qwen/CodeQwen1.5-7B

6
#5 opened 3 months ago by Kalemnor
New activity in Qwen/Qwen1.5-MoE-A2.7B-Chat 3 months ago

请问这个版本GPU内存消耗28G与14B对比如何?

7
#7 opened 4 months ago by william0014
New activity in Qwen/qwen1.5-MoE-A2.7B-Chat-demo 4 months ago

How is the inference so fast in this free hardware space?

2
#1 opened 4 months ago by mahiatlinux
New activity in ai21labs/Jamba-v0.1 4 months ago

Would there a chance Jamba to be train in 1.58bit weight?

1
#22 opened 4 months ago by shing3232
commented a paper 4 months ago
New activity in shing3232/dataset_imatrix 4 months ago

这个矩阵用于常规中文模型量化效果会好吗？

1
#2 opened 4 months ago by DesperateZero
New activity in ShenSheiBot/Sakura-1B8-Qwen2beta-v0.9-GGUF 4 months ago

Upload sakura0.9_1.8B_IQ4NL.gguf

1
#1 opened 5 months ago by shing3232
New activity in OrionStarAI/Orion-14B-Chat 5 months ago

add GPTQ, AWQ, and GGUFF formats

4
#11 opened 6 months ago by nonetrix
New activity in ikawrakow/various-2bit-sota-gguf 6 months ago

mixtral-instruct-8x7b for Q2KS as well
#7 opened 6 months ago by shing3232

Could We combine AWQ and Importance Matrix calculation together to further improve perplexity.

3
#4 opened 6 months ago by shing3232
New activity in ikawrakow/various-2bit-sota-gguf 7 months ago

Please 3b model rocket 2bit?

17
#1 opened 7 months ago by Shqmil
New activity in TheBloke/Qwen-14B-Chat-AWQ 7 months ago

Which calibration set is chose?

4
#4 opened 7 months ago by frankxyy