Model Card on HF 🤗: https://huggingface.co/smangrul/falcon-40B-int4-peft-lora-sfttrainer
Falcon 40B Int4 Peft Lora Sfttrainer 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)
Falcon 40B Int4 Peft Lora Sfttrainer Parameters and Internals
| Model Type |
|
| LLM Name | Falcon 40B Int4 Peft Lora Sfttrainer |
| Repository 🤗 | https://huggingface.co/smangrul/falcon-40B-int4-peft-lora-sfttrainer |
| Model Size | 40b |
| Required VRAM | 1.8 GB |
| Updated | 2025-08-24 |
| Maintainer | smangrul |
| Model Files | |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | query_key_value|dense|dense_h_to_4h|dense_4h_to_h |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.1 |
| R Param | 64 |
Best Alternatives to Falcon 40B Int4 Peft Lora Sfttrainer
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Medfalcon V2 40B Lora | 0K / 0.9 GB | 4 | 3 |
| Falcon 40B Code Alpaca Lora | 0K / 0 GB | 0 | 2 |
| Medfalcon 40B Lora | 0K / 0.9 GB | 0 | 3 |
| Falcon 40B Chat V0.1 | 0K / 0 GB | 7 | 38 |
| Falcon 40B Guanaco Lora | 0K / 0.2 GB | 0 | 4 |
| Falcon 40B Qlora Oasst De | 0K / 1.8 GB | 0 | 2 |
| ...lcon Lora 40b Ckpt 500 Oasst 1 | 0K / 1.8 GB | 0 | 1 |
| ...e WizardLM Uncensored 40B Lora | 0K / 0.1 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than smangrul/falcon-40B-int4-peft-lora-sfttrainer .
Rank the Falcon 40B Int4 Peft Lora Sfttrainer 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? 50856 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124