SAVRN Model Hub · Comparisons
Bangla-twoclass-Sentiment-Analyzer vs Prompt-Guard-86M
Bangla-twoclass-Sentiment-Analyzer has 278M parameters and Prompt-Guard-86M has 279M parameters; Bangla-twoclass-Sentiment-Analyzer is released under MIT License and Prompt-Guard-86M under Meta Llama 3.1 Community License; at 16-bit, Bangla-twoclass-Sentiment-Analyzer needs about 0.7 GB (1x MI300X from $1.85 an hour) and Prompt-Guard-86M about 0.7 GB (1x MI300X from $1.85 an hour).
| Field | Bangla-twoclass-Sentiment-Analyzer Arunavaonly/Bangla-twoclass-Sentiment-Analyzer | Prompt-Guard-86M meta-llama/Prompt-Guard-86M |
|---|---|---|
| Publisher | Arunava Kar | Meta Llama |
| Task | Text classification | Text classification |
| Modality | Text | Text |
| Parameters, as reported | 278M parameters | 279M parameters |
| Architecture | XLMRobertaForSequenceClassification | DebertaV2ForSequenceClassification |
| Library | transformers | transformers |
| Context length | 514 tokens | Not stated |
| Repository size | 2.2 GB | 1.1 GB |
| Artifact formats | safetensors, pytorch, tensorboard | safetensors, pytorch |
| License | mit | llama3.1 |
| Access | Open weights, no gate | Access requested at publisher |
| Memory at 16-bit (weights and margin) | 0.7 GB | 0.7 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.2 GB | 0.2 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | b2b3ca5db5ea | 1209add6ca7d |
| Downloads reported by the hub | 428.8k | 4.5M |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on Bangla-twoclass-Sentiment-Analyzer
Two labels, one language. Bangla sentiment classification is the whole job for this 278M parameter model, fine-tuned from xlm-roberta-base for 1,800 steps at a batch size of 16, with the fine-tuning dataset left unnamed. At 16-bit the weights come to 0.6 GB and 0.7 GB of memory is needed. The cheapest configuration on the table is a single MI300X, 192 GB, $1.85 per hour on-demand, far more card than the work requires, so we would put it on shared capacity rather than a device of its own.
MIT terms allow commercial use, modification and redistribution with the notices intact, so the license will not block a deployment. What to check is the lineage and the data: the relation to FacebookAI/xlm-roberta-base is recorded, the training set is not, and no evaluation results are reported. The 514-token window suits short reviews and messages, and the files ship as safetensors and pytorch.
SAVRN's Notes on Prompt-Guard-86M
Nothing here generates a reply. It sits in front of the model that does and flags the two attack types Meta names, prompt injection and jailbreaks. Loaded at 16-bit it wants 0.7 GB of memory for 0.6 GB of weights, under half a percent of the cheapest Index setup, a single MI300X with 192 GB at $1.85 an hour on-demand. Co-locate it with the model it protects and the memory is noise.
Read the license closely. The Llama 3.1 Community License allows commercial use, but a licensee whose products had more than 700 million monthly active users on the release date must request a license from Meta, attribution is required, and Meta's Acceptable Use Policy applies. Access is gated; plan for the wait. The name says 86M while the file counts 279 million parameters, and no evaluations are reported, so you measure it on your own traffic before trusting it.
Questions
Which is larger, Bangla-twoclass-Sentiment-Analyzer or Prompt-Guard-86M?
Prompt-Guard-86M (279M parameters) is larger than Bangla-twoclass-Sentiment-Analyzer (278M parameters), by the parameter counts their publishers report.
Which is cheaper to run, Bangla-twoclass-Sentiment-Analyzer or Prompt-Guard-86M?
At 4-bit, Bangla-twoclass-Sentiment-Analyzer fits on 1x MI300X from $1.85 an hour and Prompt-Guard-86M on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Bangla-twoclass-Sentiment-Analyzer commercially?
Yes. Bangla-twoclass-Sentiment-Analyzer 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.
Can I use Prompt-Guard-86M commercially?
Yes, with conditions. Prompt-Guard-86M is released under Meta Llama 3.1 Community License. The Llama 3.1 Community License permits commercial use, except that a licensee whose products had more than 700 million monthly active users on the release date must request a license from Meta. It requires attribution as the license specifies and compliance with Meta's Acceptable Use Policy.