Falcon 40B Instruct GPTQ 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 Instruct GPTQ Parameters and Internals
| LLM Name | Falcon 40B Instruct GPTQ |
| Repository 🤗 | https://huggingface.co/rmihaylov/falcon-40b-instruct-GPTQ |
| Base Model(s) | |
| Model Size | 40b |
| Required VRAM | 22.5 GB |
| Updated | 2024-11-12 |
| Maintainer | rmihaylov |
| Model Type | RefinedWeb |
| Instruction-Based | Yes |
| 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 | 65024 |
| Torch Data Type | bfloat16 |
Best Alternatives to Falcon 40B Instruct GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Falcon 40B Instruct GPTQ | 0K / 22.5 GB | 106 | 198 |
| ...truct GPTQ Inference Endpoints | 0K / 22.5 GB | 19 | 2 |
| Falcon 40B Instruct 8bit | 0K / 41.8 GB | 39 | 6 |
| ...alcon 40B Instruct W4 G128 AWQ | 0K / 22.3 GB | 26 | 2 |
| H2ogpt Oig Oasst1 Falcon 40B | 0K / 82.5 GB | 27 | 6 |
Note: green Score (e.g. "73.2") means that the model is better than rmihaylov/falcon-40b-instruct-GPTQ .
Rank the Falcon 40B Instruct GPTQ 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? 37901 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110