Ben Li

bash99's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Qwen/Qwen3.6-27B 3 days ago

Anyone noticed the diffrence of sampling parameters between 27B and 35B-A3B (both 3.6)

👍 1

1

#10 opened 3 days ago by

bash99

New activity in mratsim/MiniMax-M2.1-FP8-INT4-AWQ 3 months ago

Should I tuned for this warning?

1

#4 opened 3 months ago by

bash99

New activity in RedHatAI/Qwen3-32B-FP8-dynamic 12 months ago

How can I repeat the eval results?

3

#2 opened 12 months ago by

bash99

What is the difference between Qwen/Qwen3-32B-FP8 and this quatinized model？

4

#1 opened 12 months ago by

traphix

New activity in rhymes-ai/Aria over 1 year ago

llama.cpp support

🔥👍 11

9

#1 opened over 1 year ago by

ayyylol

New activity in Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4 over 1 year ago

Any one can use VLLM or any other engine support dynamic batch to run this with more than 1 GPU?

1

#1 opened over 1 year ago by

bash99

New activity in Alibaba-NLP/gte-multilingual-base over 1 year ago

某些特殊情况匹配排序会有错）

2

#5 opened over 1 year ago by

bash99

New activity in jondurbin/airoboros-13b-gpt4-1.4 almost 3 years ago

4 bit GPTQ

2

#1 opened almost 3 years ago by

flashvenom

New activity in coyude/Nous-Hermes-13b-Chinese-plus-GPTQ almost 3 years ago

请问这个带Plus的版本和不带的有什么区别？

2

#1 opened almost 3 years ago by

bash99

New activity in TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ almost 3 years ago

Gibberish on 'latest', with recent qwopqwop GPTQ/triton and ooba?

👍 4

7

#2 opened almost 3 years ago by

andysalerno

New activity in thatname/Ziya-LLaMA-13B-v1-ggml almost 3 years ago

convert ziya to ggml shell

👍 1

4

#1 opened almost 3 years ago by

jiangyong007

New activity in anon8231489123/vicuna-13b-GPTQ-4bit-128g about 3 years ago

Vram usage

11

#3 opened about 3 years ago by

Juuuuu