ArthurGprog/Codestral-22B-v0.1-FIM-Fix-GPTQ
Text Generation • 22B • Updated • 27 • 5
Arthur Galas
ArthurGprog
·
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
ArthurGprog/Codestral-22B-v0.1-FIM-Fix-GPTQ new activity over 1 year ago
mistralai/Magistral-Small-2506:Mistral reasoning parser fails on startup with ValueError new activity over 1 year ago
mistralai/Magistral-Small-2506:output issueOrganizations
None yet
liked a
model 3 days ago
Mistral reasoning parser fails on startup with ValueError
👍 1
3
#27 opened over 1 year ago
by ArthurGprog
output issue
3
#14 opened over 1 year ago
by 
dnum-ia-unistra
updated 4
models over 1 year ago
neuralmind/bert-base-portuguese-cased
Fill-Mask • Updated • 367k • • 248
emrecan/bert-base-turkish-cased-mean-nli-stsb-tr
Sentence Similarity • 0.1B • Updated • 503k • • 53
emilyalsentzer/Bio_ClinicalBERT
Fill-Mask • Updated • 2.38M • • 454
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Text Classification • 67M • Updated • 3.01M • • 1.01k
Add new SentenceTransformer model with an openvino backend
#23 opened over 1 year ago
by ArthurGprog
Add new SentenceTransformer model with an openvino backend
#22 opened over 1 year ago
by ArthurGprog
updated a
model over 1 year ago
liked a
model almost 2 years ago
reacted to tomaarsen's post with 🔥 almost 2 years ago
Post
5,932
I just released Sentence Transformers v3.3.0 & it's huge! 4.5x speedup for CPU with OpenVINO int8 static quantization, training with prompts for a free perf. boost, PEFT integration, evaluation on NanoBEIR, and more! Details:
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
export_static_quantized_openvino_model method to quantize a model.2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
prompts argument in SentenceTransformerTrainingArguments. Our experiments show that you can easily reach 0.66% to 0.90% relative performance improvement on NDCG@10 at no extra cost by adding "query: " before each training query and "document: " before each training answer.3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
liked a
model almost 2 years ago
What does the fim format request look like ?
3
#1 opened over 2 years ago
by 
RobertLiu0905
can inference with vllm?
1
#21 opened over 2 years ago
by 
amosxy
updated a
model over 2 years ago