4-bit Autotrain compatible Bitsandbytes Bn Conversational Endpoints compatible Instruct Lora Mistral Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/ragibhasan/phi-3-bangla-instruct
Phi 3 Bangla Instruct Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Phi 3 Bangla Instruct Parameters and Internals
| LLM Name | Phi 3 Bangla Instruct |
| Repository 🤗 | https://huggingface.co/ragibhasan/phi-3-bangla-instruct |
| Model Size | 2.1b |
| Required VRAM | 0.5 GB |
| Updated | 2025-02-22 |
| Maintainer | ragibhasan |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | bn |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 4096 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|down_proj|v_proj|o_proj|q_proj|k_proj|up_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to Phi 3 Bangla Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3 Mini 4K Instruct LORA | 0K / 7.6 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ragibhasan/phi-3-bangla-instruct .
Rank the Phi 3 Bangla Instruct Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227