Hugging Face's logo
xldistance's picture
22 15

xldistance

xldistance

AI & ML interests

None yet

Recent Activity

New activity 3 days ago
LoneStriker/Qwen2.5-72B-Instruct-2.25bpw-h6-exl2:How to reduce the problem of 2.25bpw quantitative models often responding haphazardly
New activity 11 days ago
rombodawg/Rombos-Coder-V2.5-Qwen-32b:Your trained model calls the ollama api frequently unresponsive, you need to restart ollama to reply again.
New activity 11 days ago
rombodawg/Rombos-Coder-V2.5-Qwen-32b:The most powerful open source code large model！！！
View all activity

Organizations

None yet

xldistance's activity

New activity in LoneStriker/Qwen2.5-72B-Instruct-2.25bpw-h6-exl2 3 days ago

How to reduce the problem of 2.25bpw quantitative models often responding haphazardly

1
#2 opened 3 days ago by xldistance
New activity in rombodawg/Rombos-Coder-V2.5-Qwen-32b 11 days ago

Your trained model calls the ollama api frequently unresponsive, you need to restart ollama to reply again.

1
#3 opened 11 days ago by xldistance

The most powerful open source code large model！！！

3
#1 opened 14 days ago by xldistance
New activity in mradermacher/Llama3.1-70B-Chinese-Chat-GGUF 4 months ago

gguf model not loading properly in ollama

3
#1 opened 4 months ago by xldistance
New activity in THUDM/glm-4-9b-chat-1m 6 months ago

Can you quantify this model in exl2?

1
#7 opened 6 months ago by xldistance
New activity in saltlux/luxia-21.4b-alignment-v1.0 9 months ago

Can you provide the EXL2 quantitative model?

1
#1 opened 9 months ago by xldistance
New activity in mixtao/MixTAO-7Bx2-MoE-v8.1 9 months ago

Create GGUF for this please

8
#2 opened 9 months ago by ishanparihar
New activity in cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 9 months ago

Can you produce a 2.4bpw exl2 quantisation of this model?

1
#2 opened 9 months ago by xldistance
New activity in abacusai/Smaug-34B-v0.1 10 months ago

Can you quantify the model?

5
#1 opened 10 months ago by xldistance
New activity in cloudyu/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE 10 months ago

Can you make a 2.4bpw exl2 quantisation for this model?

4
#1 opened 10 months ago by xldistance
New activity in TomGrc/FusionNet_34Bx2_MoE 10 months ago

Can you make a fusionnet 34b moe model, 24gb of video memory is too much of a strain to run a 34BX2 model

1
#1 opened 10 months ago by xldistance
New activity in yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 10 months ago

GGUF Version?

20
#1 opened 10 months ago by johnnnna
New activity in JackCloudman/MoMo-70B-lora-1.8.6-DPO-exl2-3.4bpw 10 months ago

Can you quantize this model to 2.4 bpw?
#2 opened 10 months ago by xldistance
New activity in moreh/MoMo-72B-lora-1.8.6-DPO 10 months ago

Can you do a 2.0bpw quantization model?
#4 opened 10 months ago by xldistance

maximum context length

2
#3 opened 10 months ago by MaziyarPanahi
New activity in LoneStriker/Mixtral_34Bx2_MoE_60B-3.0bpw-h6-exl2 11 months ago

Can you make a 2.4bpw quantization?

5
#1 opened 11 months ago by xldistance
New activity in one-man-army/UNA-34Beagles-32K-bf16-v1 11 months ago

Can you quantify this model?

5
#1 opened 11 months ago by xldistance
New activity in LoneStriker/Mixtral_34Bx2_MoE_60B-2.4bpw-h6-exl2 11 months ago

2.4bpw quantitative modeling can have broken or non-responsive responses
#1 opened 11 months ago by xldistance
New activity in LoneStriker/Mixtral_34Bx2_MoE_60B-2.65bpw-h6-exl2 11 months ago

Can you make a 2.4bpw quantization?

1
#1 opened 11 months ago by xldistance
New activity in keyfan/Qwen-72B-Chat-2bit 11 months ago

Is there a big performance difference between 2bit quantization and 4bit quantization conversations?

1
#2 opened 11 months ago by xldistance