Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text
β’
Updated
β’
2.11M
β’
β’
796
Ic Pro
icpro
Β·
AI & ML interests
None yet
Recent Activity
liked
a model
19 days ago
Qwen/Qwen2.5-VL-7B-Instruct
liked
a model
20 days ago
ds4sd/SmolDocling-256M-preview
liked
a model
7 months ago
black-forest-labs/FLUX.1-dev
Organizations
icpro's activity
liked
a
model
19 days ago
liked
a
model
20 days ago
liked
a
model
7 months ago
updated
2
models
10 months ago
Mistral-7b pre-trained on French
#123 opened 11 months ago
by
icpro
upvoted
a
paper
11 months ago
reacted to
victor's
post with π₯
11 months ago
Post
4316
The hype is real: a mysterious gpt2-chatbot model has appeared on the LLM Arena Leaderboard π.
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
11 months ago
MaziyarPanahi/Calme-7B-Instruct-v0.1
Text Generation
β’
Updated
β’
33
β’
5
AgentPublic/guillaumetell-7b
Text Generation
β’
Updated
β’
74
β’
30
bofenghuang/vigogne-2-7b-instruct
Text Generation
β’
Updated
β’
1.42k
β’
26
almanach/camembert-large
Updated
β’
15.9k
β’
19
mistralai/Mistral-7B-Instruct-v0.2
Text Generation
β’
Updated
β’
2.86M
β’
β’
2.7k
liked
a
Space
12 months ago
reacted to
tomaarsen's
post with π₯
12 months ago
Post
3189
π Sentence Transformers v2.7.0 is out! Featuring a new loss function, easier Matryoshka model inference & evaluation, CrossEncoder improvements & Intel Gaudi2 Accelerator support. Details:
1οΈβ£ 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.
2οΈβ£ 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
3οΈβ£ Additionally, you can now specify
4οΈβ£ CrossEncoder improvements
The CrossEncoder now supports 'push_to_hub' to upload trained reranker models to Hugging Face. Additionally, CrossEncoders now support
5οΈβ£ 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!
1οΈβ£ 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.
2οΈβ£ 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.3οΈβ£ 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.)4οΈβ£ 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.5οΈβ£ 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
How to format custom dataset to finetune Mixtral with TRL SFT script?
#132 opened about 1 year ago
by
icpro