Arxiv:2305.18290 Autotrain compatible Base model:finetune:ryanyr/ref... Base model:ryanyr/reflect llam... Conversational Dpo Endpoints compatible Generated from trainer Llama Region:us Safetensors Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/RyanYr/reflect_llama8B_om2-mstlrg300k460k-llama3370b130k-t12_sft-t1_psdp-t1_b.5
Reflect Llama8B Om2 Mstlrg300k460k Llama3370b130k T12 Sft T1 Psdp T1 B.5 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)
Reflect Llama8B Om2 Mstlrg300k460k Llama3370b130k T12 Sft T1 Psdp T1 B.5 Parameters and Internals
| LLM Name | Reflect Llama8B Om2 Mstlrg300k460k Llama3370b130k T12 Sft T1 Psdp T1 B.5 |
| Repository 🤗 | https://huggingface.co/RyanYr/reflect_llama8B_om2-mstlrg300k460k-llama3370b130k-t12_sft-t1_psdp-t1_b.5 |
| Model Name | reflect_llama8B_om2-mstlrg300k460k-llama3370b130k-t12_sft-t1_psdp-t1_b.5 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2025-06-01 |
| Maintainer | RyanYr |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.45.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | [PAD] |
| Vocabulary Size | 128257 |
| Torch Data Type | bfloat16 |
Best Alternatives to Reflect Llama8B Om2 Mstlrg300k460k Llama3370b130k T12 Sft T1 Psdp T1 B.5
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...otron 8B UltraLong 4M Instruct | 4192K / 32.1 GB | 3482 | 107 |
| UltraLong Thinking | 4192K / 16.1 GB | 312 | 2 |
| ...a 3.1 8B UltraLong 4M Instruct | 4192K / 32.1 GB | 176 | 24 |
| ...a 3.1 8B UltraLong 2M Instruct | 2096K / 32.1 GB | 875 | 9 |
| ...otron 8B UltraLong 2M Instruct | 2096K / 32.1 GB | 418 | 15 |
| Zero Llama 3.1 8B Beta6 | 1048K / 16.1 GB | 730 | 1 |
| ...otron 8B UltraLong 1M Instruct | 1048K / 32.1 GB | 1794 | 43 |
| ...a 3.1 8B UltraLong 1M Instruct | 1048K / 32.1 GB | 1387 | 29 |
| ...xis Bookwriter Llama3.1 8B Sft | 1048K / 16.1 GB | 53 | 4 |
| ...dger Nu Llama 3.1 8B UltraLong | 1048K / 16.2 GB | 57 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than RyanYr/reflect_llama8B_om2-mstlrg300k460k-llama3370b130k-t12_sft-t1_psdp-t1_b.5 .
Rank the Reflect Llama8B Om2 Mstlrg300k460k Llama3370b130k T12 Sft T1 Psdp T1 B.5 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227