Ronan McGovern PRO
RonanMcGovern
AI & ML interests
Open source LLMs. Fine-tuning. Summarisation. Patents.
Organizations
Clarification on Recent Changes to Loss and Gradient Accumulation
👍
2
1
#15 opened about 2 months ago
by
jiosephlee
Fine tuning of Model
2
#22 opened about 2 months ago
by
amritansh
Data norm issue during evaluation/inference
1
#8 opened 2 months ago
by
RonanMcGovern

Amazon Chronos T5 Small Forecasting Google Colab Notebook
👍
1
2
#4 opened about 1 year ago
by
JamesBentley
Ollama with GGUF
2
#6 opened 5 months ago
by
smaram
SGLang very slow ~6 toks with 1 concurrency on H100SXM
1
#3 opened 4 months ago
by
RonanMcGovern

Low inference throughput?
3
#2 opened 5 months ago
by
RonanMcGovern

Model Produces no Outputs
3
#16 opened 6 months ago
by
RonanMcGovern

[BUG] {'use_reentrant': True} results in "Gradients will be None"
2
#74 opened 7 months ago
by
RonanMcGovern

Model does not follow or acknowledge system prompts?
2
#3 opened 7 months ago
by
RonanMcGovern

Transformers 3.0 can't find files
8
#5 opened 11 months ago
by
r0-0rd
Unable to load finetuned model after saving
3
#57 opened 8 months ago
by
Charlington
Set base_model & tags metadata
1
#1 opened 8 months ago
by
tomaarsen

Finetuning for pointing, object detection task
3
#48 opened 8 months ago
by
yaneivan

Can I apply a LoRA?
2
#1 opened 9 months ago
by
RonanMcGovern

Is vLLM support planned?
3
#10 opened 10 months ago
by
RonanMcGovern

Mac Support: RuntimeError: Placeholder storage has not been allocated on MPS device!
1
#30 opened 10 months ago
by
RonanMcGovern

Is there any difference between this and https://huggingface.co/openai/whisper-large-v3-turbo
2
#2 opened 11 months ago
by
RonanMcGovern

GGUF versions
14
#1 opened over 1 year ago
by
christianweyer
