cognitivecomputations/Dolphin3.0-Llama3.1-8B
Updated
•
2.26k
•
160
Cognitive Computations
community
AI & ML interests
Supervised Fine Tuning, DPO, and unalignment
Recent Activity
View all activity
cognitivecomputations's activity
LLuke777
updated
a
model
about 12 hours ago
why tokenizer_config.json changed for AWQ model.
2
#7 opened 2 days ago
by
rockcat-miao
Does FlashMLA support kv cache fp8 dtype and how to enable FlashMLA ?
9
#6 opened 10 days ago
by
CharlesLincoln
How to Resolve "GLIBC_2.32 Not Found" Error When Deploying vLLM Environment?
8
#32 opened 19 days ago
by
lastsummerLi
v2ray
updated
3
models
17 days ago
Can the 4090 device run this model?
3
#3 opened 19 days ago
by
jinzhongwei
vllm crach with a slightly longer prompt
1
#4 opened 19 days ago
by
rockcat-miao
可以添加一下LICENSE文件吗？
2
#2 opened 20 days ago
by
adol-ch
Are there any updates to the recommended commands?
5
#27 opened 27 days ago
by
NaiveYan
ehartford
updated
a
model
20 days ago
ehartford
published
a
model
20 days ago
Why hasn't the MTP layer of the 61st layer been quantized?
1
#30 opened 20 days ago
by
yang001002
Is there any testing on the support for running on other memory capacities
1
#29 opened 21 days ago
by
HRan2004
Any one can run this model with SGlang framework？
5
#13 opened about 2 months ago
by
muziyongshixin
DeepSeek-R1-AWQ quantized model missing one layer of experts
4
#28 opened 26 days ago
by
virilo
Post
4200
There seems to multiple paid apps shared here that are based on models on hf, but some ppl sell their wrappers as "products" and promote them here. For a long time, hf was the best and only platform to do oss model stuff but with the recent AI website builders anyone can create a product (really crappy ones btw) and try to sell it with no contribution to oss stuff. Please dont do this, or try finetuning the models you use...
Sorry for filling yall feed with this bs but yk...
Sorry for filling yall feed with this bs but yk...
- 6 replies