This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 3e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - trainingsteps: 1800 - mixedprecisiontraining: Native AMP - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
Open-weight model · Text classification
snd_sentiment_analysis
by Danish Mahdi DanishMahdi/snd_sentiment_analysis
This repository contains a fine-tuned XLM-RoBERTa Base model for 3-class sentiment classification in Sindhi.
Parameters278M
Context514
Weights1.1 GB
Licensemit
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve snd_sentiment_analysis (278M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
By Danish Mahdi, published under mit, revision b7558588e027.
This repository contains a fine-tuned XLM-RoBERTa Base model for 3-class sentiment classification in Sindhi. The model predicts one of the following labels: - positive - neutral - negative This model is intended for research, experimentation, and lightweight production prototyping on Sindhi-language sentiment analysis tasks. It may be useful for short-text classification such as reviews, feedback, and social-media snippets. It should not be used as the only basis for high-stakes decisions. Performance can vary by domain, dialect, and writing style, and human review is recommended when errors could affect people or organizations. The saved model artifacts in this repository report the…
Read Danish Mahdi's full model card
Sindhi Sentiment Analysis
This repository contains a fine-tuned XLM-RoBERTa Base model for 3-class sentiment classification in Sindhi. The model predicts one of the following labels:
- positive
- neutral
- negative
Model details
- Base model: FacebookAI/xlm-roberta-base
- Task: text classification
- Language: Sindhi (sd)
- Labels: positive, neutral, negative
- Framework: Hugging Face Transformers
- Max sequence length: 128 tokens
Intended use
This model is intended for research, experimentation, and lightweight production prototyping on Sindhi-language sentiment analysis tasks. It may be useful for short-text classification such as reviews, feedback, and social-media snippets.
It should not be used as the only basis for high-stakes decisions. Performance can vary by domain, dialect, and writing style, and human review is recommended when errors could affect people or organizations.
Usage
from transformers import pipeline
classifier = pipeline(
"text-classification",
model="DanishMahdi/snd_sentiment_analysis",
tokenizer="DanishMahdi/snd_sentiment_analysis",
)
texts = [
"هي فلم تمام سٺي آهي.",
"هي سروس تمام خراب آهي.",
"اڄ عام ڏينهن آهي.",
]
for text in texts:
print(text)
print(classifier(text))
Evaluation summary
The saved model artifacts in this repository report the following evaluation results on the held-out test split:
- Accuracy: 0.7553
- Macro precision: 0.7604
- Macro recall: 0.7554
- Macro F1: 0.7549
These values are taken from the model’s saved evaluation output and reflect the performance reported for the final checkpoint in this project.
Model card notes
This repository contains the trained model weights and tokenizer files, along with evaluation outputs. The full training script and dataset card are not included here, so the strongest claims that can be made are the ones supported by the saved artifacts in this project.
Limitations
- This model may not generalize equally across all Sindhi dialects and writing styles.
- Neutral sentiment is often harder to predict than positive or negative sentiment.
- Results may vary depending on the application domain and the class distribution of the input data.
- Confidence values should be interpreted cautiously unless calibration is evaluated separately.
Acknowledgements
This model builds on the pretrained XLM-RoBERTa Base model.
License
This model card uses the MIT license, which is compatible with the XLM-RoBERTa base model licensing used in this project.
Configuration
- Architecture
- XLMRobertaForSequenceClassification
- Context length (tokens)
- 514
- Layers
- 12
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Vocabulary size
- 250,002
- Model type
- xlm-roberta
Identity and Version
- Repository
- DanishMahdi/snd_sentiment_analysis
- Publisher
- Danish Mahdi
- Task
- Text classification
- Modality
- Text
- Library
- transformers
- Parameters
- 278M parameters
- Languages
- sd
- Revision
- b7558588e0272136027bc64326dd1ea3fdc69ab7
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
7 files, 1.1 GB in total. The weights are 2 files totalling 1.1 GB in bin, safetensors.
Weights2 files · 1.1 GB
Configuration1 file · 970 B
Tokenizer2 files · 17.1 MB
Documentation1 file · 3.0 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.1 GB | 9472cd445d34 |
| training_args.bin | Weights | 5.2 KB | fa1db0ea4aba |
| config.json | Configuration | 970 B | — |
| README.md | Documentation | 3.0 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.1 MB | b7c3dd928f1e |
| tokenizer_config.json | Tokenizer | 343 B | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 1.1 GB
Download from Danish Mahdi
Released by Danish Mahdi through its official repository on Hugging Face. Read the license.
Built From
- Derived from FacebookAI/xlm-roberta-base
- Trained on (disclosed) alinawazmahar/Sindhi_Sentiment_dataset
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.1 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About snd_sentiment_analysis
How much GPU memory does snd_sentiment_analysis need?
About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (278M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run snd_sentiment_analysis on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use snd_sentiment_analysis commercially?
Yes. snd_sentiment_analysis is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
What is snd_sentiment_analysis's context length?
514 tokens, from the maximum position embeddings in its published configuration.
Similar Models
We have updated the new reranker, supporting larger lengths, more languages, and achieving better performance. More details please refer to our Github: FlagEmbedding. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 3/18/2024: Release new rerankers, built upon powerful M3 and LLM (GEMMA and MiniCPM, not so large actually) backbones, supporitng multi-lingual processing and larger inputs, massive improvements of ranking performances on BEIR, C-MTEB/Retrieval, MIRACL, LlamaIndex Evaluation. - 3/18/2024: Release Visualized-BGE, equipping BGE with visual capabilities. Visualized-BGE can be utilized to generate embeddings for hybrid image-text…
This model is a fine-tuned version of xlm-roberta-base on the Language Identification dataset. This model is an XLM-RoBERTa transformer model with a classification head on top (i.e. a linear layer on top of the pooled output). For additional information please refer to the xlm-roberta-base model card or to the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. You can directly use this model as a language detector, i.e. for sequence classification tasks. Currently, it supports the following 20 languages: arabic (ar), bulgarian (bg), german (de), modern greek (el), english (en), spanish (es), french (fr), hindi (hi), italian (it), japanese (ja), dutch (nl)…
LLM-powered applications are susceptible to prompt attacks, which are prompts intentionally designed to subvert the developer’s intended behavior of the LLM. Categories of prompt attacks include prompt injection and jailbreaking: - Prompt Injections are inputs that exploit the concatenation of untrusted data from third parties and users into the context window of a model to get a model to execute unintended instructions. - Jailbreaks are malicious instructions designed to override the safety and security features built into a model. Prompt Guard is a classifier model trained on a large corpus of attacks, capable of detecting both explicitly malicious prompts as well as data that contains…
Paper: SciFive: a text-to-text transformer model for biomedical literature Authors: Long N. Phan, James T. Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan-Bonnet For more details, do check out our Github repo.
roberta-large-mnli is the RoBERTa large model fine-tuned on the Multi-Genre Natural Language Inference (MNLI) corpus. The model is a pretrained model on English language text using a masked language modeling (MLM) objective. Use the code below to get started with the model. The model can be loaded with the zero-shot-classification pipeline like so: You can then use this pipeline to classify sequences into any of the class names you specify. For example: This fine-tuned model can be used for zero-shot classification tasks, including zero-shot sentence-pair classification (see the GitHub repo for examples) and zero-shot sequence classification. The model should not be used to intentionally…