Adapter Base model:deepseek-ai/deepsee... Codegen Dataset:generator Finetuned Generated from trainer License:other Lora Peft Region:us Safetensors Sft Trl
Model Card on HF 🤗: https://huggingface.co/stojchet/python-sft-r64-a64
Python Sft R64 A64 Parameters and Internals
| LLM Name | Python Sft R64 A64 |
| Repository 🤗 | https://huggingface.co/stojchet/python-sft-r64-a64 |
| Base Model(s) | |
| Model Size | 1.3b |
| Required VRAM | 0.1 GB |
| Updated | 2024-07-04 |
| Maintainer | stojchet |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | Adapter |
| License | other |
| Model Max Length | 16384 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|v_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| R Param | 64 |
Best Alternatives to Python Sft R64 A64
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Deepseek 1.3b Instruct Adapter | 0K / 0.3 GB | 5 | 0 |
| ...t 10K Good 1e R64 A16 D0.05 E1 | 0K / 0.1 GB | 6 | 0 |
| ...on Sft 10K 1e R64 A16 D0.05 E1 | 0K / 0.1 GB | 5 | 0 |
| ...ython Sft 50K R64 A16 D0.05 E1 | 0K / 0.1 GB | 5 | 0 |
| ... Sft 10K Good R64 A16 D0.05 E3 | 0K / 0.1 GB | 5 | 0 |
| Python Sft Markdown | 0K / 0.1 GB | 5 | 0 |
| Python Sft | 0K / 0.1 GB | 6 | 0 |
| Test | 0K / 0.1 GB | 5 | 0 |
| Hyperparam Rust Sft Lora | 0K / 0.1 GB | 14 | 1 |
| Python Sft R64 A16 D0.05 | 0K / 0.1 GB | 0 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than stojchet/python-sft-r64-a64 .
Rank the Python Sft R64 A64 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