Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
danielhanchen's submissions
login
1.
Train your own R1 reasoning model
(
unsloth.ai
)
11 points
by
danielhanchen
12 days ago
|
past
|
5 comments
2.
How to run 1.58bit DeepSeek R1 with Open WebUI
(
openwebui.com
)
37 points
by
danielhanchen
18 days ago
|
past
|
9 comments
3.
Phi-4 Bug Fixes
(
unsloth.ai
)
193 points
by
danielhanchen
39 days ago
|
past
|
68 comments
4.
My take on the Post Pretraining world
(
twitter.com/danielhanchen
)
1 point
by
danielhanchen
64 days ago
|
past
|
3 comments
5.
Dynamic 4bit Quantization
(
unsloth.ai
)
3 points
by
danielhanchen
76 days ago
|
past
|
5 comments
6.
Show HN: Finetune Llama 3.2 Vision in a Colab
(
colab.research.google.com
)
10 points
by
danielhanchen
89 days ago
|
past
7.
Python 3.11 is 1.25x faster than 3.10
(
python.org
)
3 points
by
danielhanchen
3 months ago
|
past
|
5 comments
8.
Fixing Gradient Accumulation
(
huggingface.co
)
2 points
by
danielhanchen
4 months ago
|
past
9.
Unit Economics of LLM APIs
(
lesswrong.com
)
5 points
by
danielhanchen
5 months ago
|
past
|
4 comments
10.
LoRA Learns Less and Forgets Less Updated
(
openreview.net
)
1 point
by
danielhanchen
5 months ago
|
past
|
1 comment
11.
VLLM automatic prefix / prompt caching
(
vllm.ai
)
2 points
by
danielhanchen
5 months ago
|
past
|
1 comment
12.
Higher Temperatures and Min_p Sampling
(
arxiv.org
)
1 point
by
danielhanchen
5 months ago
|
past
|
1 comment
13.
Show HN: Open-source fine-tuning in a Colab notebook
(
colab.research.google.com
)
5 points
by
danielhanchen
6 months ago
|
past
14.
Sahm rule signals start of recession
(
stlouisfed.org
)
4 points
by
danielhanchen
6 months ago
|
past
|
3 comments
15.
Low Level Technicals of LLMs [video]
(
youtube.com
)
1 point
by
danielhanchen
6 months ago
|
past
|
1 comment
16.
Gemma-2 2B beats GPT3.5 on Chatbot Arena
(
huggingface.co
)
5 points
by
danielhanchen
6 months ago
|
past
|
1 comment
17.
HuggingChat – Chat UI for Llama 3.1 405B
(
huggingface.co
)
5 points
by
danielhanchen
6 months ago
|
past
18.
Fine-Tune Llama 3.1 Ultra-Efficiently with Unsloth
(
huggingface.co
)
3 points
by
danielhanchen
6 months ago
|
past
19.
Yield Curve and Predicted GDP Growth
(
clevelandfed.org
)
2 points
by
danielhanchen
6 months ago
|
past
20.
Cloudflare DNS + Malware Blocking
(
one.one
)
3 points
by
danielhanchen
6 months ago
|
past
|
4 comments
21.
SIMD at Insomniac Games: How We Do the Shuffle
(
gdcvault.com
)
1 point
by
danielhanchen
6 months ago
|
past
22.
Some Machine Learning Notes
(
danielhanchen.github.io
)
3 points
by
danielhanchen
6 months ago
|
past
|
1 comment
23.
My Analysis of Llama 3.1
(
twitter.com/danielhanchen
)
2 points
by
danielhanchen
7 months ago
|
past
|
1 comment
24.
Show HN: Finetune Llama-3.1 2x faster in a Colab
(
colab.research.google.com
)
16 points
by
danielhanchen
7 months ago
|
past
|
2 comments
25.
Show HN: Mistral NeMo finetuning fits in Colab
(
colab.research.google.com
)
4 points
by
danielhanchen
7 months ago
|
past
26.
TextGrad – Backpropagation through text feedback
(
arxiv.org
)
2 points
by
danielhanchen
7 months ago
|
past
27.
Nemotron-4 340B open weights model
(
nvidia.com
)
18 points
by
danielhanchen
8 months ago
|
past
|
3 comments
28.
Show HN: Finetune Llama-3 2x faster in a Colab notebook
(
colab.research.google.com
)
45 points
by
danielhanchen
10 months ago
|
past
|
6 comments
29.
Try Llama-3 in a Colab Notebook
(
colab.research.google.com
)
5 points
by
danielhanchen
10 months ago
|
past
|
1 comment
30.
Fixing Gemma Bugs
(
unsloth.ai
)
166 points
by
danielhanchen
11 months ago
|
past
|
63 comments
More
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: