Qwen 1 8B Llamafied Benchmarks
ARC: 37.71-60.8%
HellaSwag: 58.87-38.2%
MMLU: 46.37-46.4%
TruthfulQA: 39.41-33.2%
WinoGrande: 61.72-29.5%
GSM8K: 24.41-73.5%
nn.n% — How the model compares to the GPT-4.
Qwen 1 8B Llamafied Parameters and Internals
| LLM Name | Qwen 1 8B Llamafied |
| Repository | Open on 🤗 |
| Model Size | 8b |
| Required VRAM | 3.7 GB |
| Updated | 2024-07-26 |
| Maintainer | KnutJaegersberg |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.34.0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
Best Alternatives to Qwen 1 8B Llamafied
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...a 3 8B Instruct Gradient 1048K | 0.5 | 1024K / 16.1 GB | 41419 | 658 |
| ...struct Gradient 1048K MAC Lora | 0.3 | 1024K / 5.9 GB | 22729 | 0 |
| ...SLERP Gradient1048k OpenBioLLM | 0.3 | 1024K / 16.1 GB | 318 | 0 |
| ... Instruct Gradient 1048K Agent | 0.3 | 1024K / 16.1 GB | 264 | 1 |
| Dolphin 2.9 Llama3 8B 1M | 0.2 | 1024K / 16.1 GB | 13 | 24 |
| L3 8B LingYang V1 | 0.2 | 1024K / 16.1 GB | 23 | 0 |
| Llama 3 8B 1M PoSE | 0.2 | 1024K / 16.1 GB | 47 | 6 |
| Llama 3 8B Instruct 1048K | 0.2 | 1024K / 16.1 GB | 36 | 4 |
| ... V0.1.0 Llama 3 8B Instruct 1M | 0.2 | 1024K / 16.1 GB | 28 | 0 |
| Meta Llama 3 8B 1M | 0.2 | 1024K / 16.1 GB | 9 | 6 |
Note: green Score (e.g. "73.2") means that the model is better than KnutJaegersberg/Qwen-1_8B-Llamafied .
Rank the Qwen 1 8B Llamafied 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501