Model Card on HF 🤗: https://huggingface.co/AWS/FalconLite
FalconLite 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)
FalconLite Parameters and Internals
| LLM Name | FalconLite |
| Repository 🤗 | https://huggingface.co/AWS/FalconLite |
| Model Size | 40b |
| Required VRAM | 22.3 GB |
| Updated | 2025-04-09 |
| Maintainer | AWS |
| Model Type | RefinedWeb |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | RWForCausalLM |
| License | apache-2.0 |
| Model Max Length | 2048 |
| Transformers Version | 4.29.2 |
| Is Biased | 0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 65040 |
| Torch Data Type | float16 |
Best Alternatives to FalconLite
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Alfred 40B 1023 GPTQ | 0K / 22.5 GB | 14 | 3 |
| FalconLite | 0K / 22.3 GB | 284 | 170 |
| Falcon 40B Instruct GPTQ | 0K / 22.5 GB | 323 | 197 |
| Falcon 40B Gptq | 0K / 23.3 GB | 24 | 2 |
| ...st1 En 2048 Falcon 40B V2 GPTQ | 0K / 22.5 GB | 24 | 8 |
| Falcon 40B Gptq | 0K / 23.4 GB | 51 | 13 |
| Falcon 40B Instruct GPTQ | 0K / 22.5 GB | 14 | 1 |
| ...truct GPTQ Inference Endpoints | 0K / 22.5 GB | 15 | 2 |
| Falcon 40B 8bit | 0K / 41.8 GB | 13 | 1 |
| ...dLM Uncensored Falcon 40B GPTQ | 0K / 22.5 GB | 36 | 60 |
Note: green Score (e.g. "73.2") means that the model is better than AWS/FalconLite .
Rank the FalconLite 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? 50804 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124