Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Conversational Endpoints compatible Generated from trainer Qwen2 Region:us Safetensors Sft Trl
Model Card on HF 🤗: https://huggingface.co/tsavage68/Error_Q1.5_500steps_1e6rate_SFT
Error Q1.5 500steps 1e6rate SFT 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)
Error Q1.5 500steps 1e6rate SFT Parameters and Internals
| LLM Name | Error Q1.5 500steps 1e6rate SFT |
| Repository 🤗 | https://huggingface.co/tsavage68/Error_Q1.5_500steps_1e6rate_SFT |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 3.5 GB |
| Updated | 2025-02-22 |
| Maintainer | tsavage68 |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | LlamaTokenizerFast |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
Best Alternatives to Error Q1.5 500steps 1e6rate SFT
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ReaderLM V2 | 500K / 3.5 GB | 26440 | 512 |
| Reader Lm 1.5B | 250K / 3.1 GB | 1295 | 589 |
| DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 1075846 | 904 |
| DeepScaleR 1.5B Preview | 128K / 7.1 GB | 14543 | 462 |
| ...Seek R1 Distill Qwen 1.5B ONNX | 128K / GB | 46386 | 51 |
| Qwen2.5 1.5B | 128K / 3.1 GB | 505611 | 78 |
| AceInstruct 1.5B | 128K / 3.5 GB | 592 | 17 |
| DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 15506 | 10 |
| Qwen2 1.5B | 128K / 3.1 GB | 104122 | 88 |
| Stella En 1.5B V5 | 128K / 6.2 GB | 581890 | 211 |
Note: green Score (e.g. "73.2") means that the model is better than tsavage68/Error_Q1.5_500steps_1e6rate_SFT .
Rank the Error Q1.5 500steps 1e6rate SFT 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