Autotrain compatible Base model:finetune:tiiuae/fal... Base model:tiiuae/falcon-7b Conversational Custom code Endpoints compatible Falcon Generated from trainer Lora Region:us Safetensors Tensorboard
Model Card on HF 🤗: https://huggingface.co/Mastane/falcon-7b-dpo-lora
Falcon 7B DPO Lora 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 7B DPO Lora Parameters and Internals
| LLM Name | Falcon 7B DPO Lora |
| Repository 🤗 | https://huggingface.co/Mastane/falcon-7b-dpo-lora |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.5 GB |
| Updated | 2025-09-30 |
| Maintainer | Mastane |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | dense|query_key_value|dense_h_to_4h|dense_4h_to_h |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.1 |
| R Param | 64 |
Best Alternatives to Falcon 7B DPO Lora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B V0.3 | 32K / 14.5 GB | 1030 | 5 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 39 | 5 |
| ...unoichi Lemon Royale V3 32K 7B | 32K / 14.5 GB | 9 | 5 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 295 | 3 |
| ...ralai Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 43 | 2 |
| Mistralai Mistral 7B V0.3 | 32K / 14.5 GB | 21 | 3 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 8 | 0 |
| Mistral 7B V0.2 | 32K / 14.5 GB | 13 | 1 |
| Full V4 Astromistral Final | 32K / 4.5 GB | 6 | 1 |
| LlamaGuard 7B | 4K / 13.5 GB | 9019 | 240 |
Note: green Score (e.g. "73.2") means that the model is better than Mastane/falcon-7b-dpo-lora .
Rank the Falcon 7B DPO Lora 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124