zai-org/GLM-4.7-Flash
Text Generation
•
31B
•
Updated
•
450k
•
•
1.24k
Ic Pro
icpro
AI & ML interests
None yet
Recent Activity
liked
a model
about 15 hours ago
zai-org/GLM-4.7-Flash
new activity
7 days ago
karpathy/nanochat-d32:Add Optimizer State
reacted
to
Parveshiiii's
post
with 👍
7 months ago
🧠 MathX-5M by XenArcAI — Scalable Math Reasoning for Smarter LLMs
Introducing MathX-5M, a high-quality, instruction-tuned dataset built to supercharge mathematical reasoning in large language models. With 5 million rigorously filtered examples, it spans everything from basic arithmetic to advanced calculus—curated from public sources and enhanced with synthetic data.
🔍 Key Highlights:
- Step-by-step reasoning with verified answers
- Covers algebra, geometry, calculus, logic, and more
- RL-validated correctness and multi-stage filtering
- Ideal for fine-tuning, benchmarking, and educational AI
📂 - https://huggingface.co/datasets/XenArcAI/MathX-5M
Organizations
liked
a
model
about 15 hours ago
Add Optimizer State
#9 opened 7 days ago
by
icpro
reacted to
Parveshiiii's
post with 👍
7 months ago
Post
2862
🧠 MathX-5M by XenArcAI — Scalable Math Reasoning for Smarter LLMs
Introducing MathX-5M, a high-quality, instruction-tuned dataset built to supercharge mathematical reasoning in large language models. With 5 million rigorously filtered examples, it spans everything from basic arithmetic to advanced calculus—curated from public sources and enhanced with synthetic data.
🔍 Key Highlights:
- Step-by-step reasoning with verified answers
- Covers algebra, geometry, calculus, logic, and more
- RL-validated correctness and multi-stage filtering
- Ideal for fine-tuning, benchmarking, and educational AI
📂 - https://huggingface.co/datasets/XenArcAI/MathX-5M
Introducing MathX-5M, a high-quality, instruction-tuned dataset built to supercharge mathematical reasoning in large language models. With 5 million rigorously filtered examples, it spans everything from basic arithmetic to advanced calculus—curated from public sources and enhanced with synthetic data.
🔍 Key Highlights:
- Step-by-step reasoning with verified answers
- Covers algebra, geometry, calculus, logic, and more
- RL-validated correctness and multi-stage filtering
- Ideal for fine-tuning, benchmarking, and educational AI
📂 - https://huggingface.co/datasets/XenArcAI/MathX-5M
- 1 reply
liked
2
models
10 months ago
liked
a
model
over 1 year ago
updated
2
models
over 1 year ago
upvoted
a
paper
over 1 year ago
reacted to
victor's
post with 🔥
over 1 year ago
Post
4357
The hype is real: a mysterious gpt2-chatbot model has appeared on the LLM Arena Leaderboard 👀.
It seems to be at least on par with the top performing models (closed and open).
To try it out: https://chat.lmsys.org/ -> then click on the Direct Chat tab and select gpt2-chatbot.
Take your bet, what do you think it is?
It seems to be at least on par with the top performing models (closed and open).
To try it out: https://chat.lmsys.org/ -> then click on the Direct Chat tab and select gpt2-chatbot.
Take your bet, what do you think it is?
- 4 replies
liked
5
models
over 1 year ago
MaziyarPanahi/Calme-7B-Instruct-v0.1
Text Generation
•
7B
•
Updated
•
106
•
5
AgentPublic/guillaumetell-7b
Text Generation
•
7B
•
Updated
•
39
•
30
bofenghuang/vigogne-2-7b-instruct
Text Generation
•
Updated
•
1.03k
•
25
almanach/camembert-large
0.3B
•
Updated
•
67.9k
•
20
mistralai/Mistral-7B-Instruct-v0.2
Text Generation
•
7B
•
Updated
•
2.1M
•
•
3.06k
liked
a
Space
almost 2 years ago
upvoted
an
article
almost 2 years ago
Article
Fine-tune Llama 3 with ORPO
•
241
reacted to
tomaarsen's
post with 🔥
almost 2 years ago
Post
3221
🚀 Sentence Transformers v2.7.0 is out! Featuring a new loss function, easier Matryoshka model inference & evaluation, CrossEncoder improvements & Intel Gaudi2 Accelerator support. Details:
1️⃣ A new loss function: CachedGISTEmbedLoss
This loss function is a combination of CachedMultipleNegativesRankingLoss and the GISTEmbedLoss, both of which are already excellent. The caching mechanism allows for much higher batch sizes with constant memory usage, which boosts training performance. The GIST part introduces a guide model to guide the in-batch negative sample selection. This prevents false negatives, resulting in a stronger training signal.
2️⃣ Automatic Matryoshka model truncation
Matryoshka models produce embeddings that are still useful after truncation. However, this truncation always had to be done manually, until now! We've added a
3️⃣ Additionally, you can now specify
4️⃣ CrossEncoder improvements
The CrossEncoder now supports 'push_to_hub' to upload trained reranker models to Hugging Face. Additionally, CrossEncoders now support
5️⃣ Inference on Intel Gaudi2
If you have an Intel Gaudi2 Accelerator, Sentence Transformers now uses it automatically for even faster inference. No changes are necessary to your code, the device is automatically detected!
Check out the release notes for all of the details: https://github.com/UKPLab/sentence-transformers/releases/tag/v2.7.0
I'm very excited for the upcoming releases: I'm making great progress with a notable v3 refactor that should heavily improve the training process for embedding models!
1️⃣ A new loss function: CachedGISTEmbedLoss
This loss function is a combination of CachedMultipleNegativesRankingLoss and the GISTEmbedLoss, both of which are already excellent. The caching mechanism allows for much higher batch sizes with constant memory usage, which boosts training performance. The GIST part introduces a guide model to guide the in-batch negative sample selection. This prevents false negatives, resulting in a stronger training signal.
2️⃣ Automatic Matryoshka model truncation
Matryoshka models produce embeddings that are still useful after truncation. However, this truncation always had to be done manually, until now! We've added a
truncate_dim option to the Sentence Transformer constructor. This also allows truncation when using HuggingFaceEmbeddings from LlamaIndex or LangChain.3️⃣ Additionally, you can now specify
truncate_dim in evaluators to get the performance after truncation. (Hint: it's surprisingly good, even for models not trained with MatryoshkaLoss, and it can speed up e.g. clustering, retrieval, etc.)4️⃣ CrossEncoder improvements
The CrossEncoder now supports 'push_to_hub' to upload trained reranker models to Hugging Face. Additionally, CrossEncoders now support
trust_remote_code to load models with custom modelling code.5️⃣ Inference on Intel Gaudi2
If you have an Intel Gaudi2 Accelerator, Sentence Transformers now uses it automatically for even faster inference. No changes are necessary to your code, the device is automatically detected!
Check out the release notes for all of the details: https://github.com/UKPLab/sentence-transformers/releases/tag/v2.7.0
I'm very excited for the upcoming releases: I'm making great progress with a notable v3 refactor that should heavily improve the training process for embedding models!
- 2 replies