Plus Light
Light4Bear
AI & ML interests
None yet
Organizations
Light4Bear's activity
Join LMSYS Chatbot Arena?
1
#11 opened 6 months ago
by
Light4Bear
Can VLLM be used for loading?
6
#4 opened 7 months ago
by
wawoshashi
How many bits and what is the groupsize?
1
#3 opened 8 months ago
by
vitvit
How to load command r+ in text-generation-webui?
5
#1 opened 8 months ago
by
MLDataScientist
GPTQ/AWQ quant that is runable in vllm?
2
#4 opened 9 months ago
by
Light4Bear
Difference between v0.2 and v0.4?
1
#2 opened 9 months ago
by
Light4Bear
Tokenizer is incorrectly tokenizing '<|im_start|>' and '<|im_end|>' as strings
#5 opened 9 months ago
by
Light4Bear
Instruct sequences?
12
#2 opened 9 months ago
by
deleted
What is the context size of this model?
8
#1 opened 9 months ago
by
MarinaraSpaghetti
Suggestion: increase the weights of instruction-following models.
3
#6 opened 9 months ago
by
Light4Bear
Safetensor naming convention
10
#1 opened 9 months ago
by
dannysemi
vLLM output gibberish but text-generation-webui is fine
1
#2 opened 10 months ago
by
Light4Bear
GPTQ and AWQ quants
1
#1 opened 10 months ago
by
Light4Bear
Congratulations!
10
#1 opened 10 months ago
by
TomGrc
Difference between this and the non-"test" version?
16
#2 opened 10 months ago
by
samgreen
8.0bpw-h8-exl2 quant of this model
6
#1 opened 10 months ago
by
Light4Bear
fp16 version of the model
1
#6 opened over 1 year ago
by
Light4Bear