4-bit Autotrain compatible Awq Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/anyisalin/Midnight-Rose-70B-v2.0.3-AWQ
Midnight Rose 70B V2.0.3 AWQ Benchmarks
ARC: 70.65 vs 96.7 (so35)-26.9%
HellaSwag: 87.5 vs 95.3 (gpt4)-8.2%
MMLU: 69.64 vs 88.3 (so35)-21.1%
TruthfulQA: 65.27 vs 59 (gpt4)10.6%
WinoGrande: 81.22 vs 87.5 (gpt4)-7.2%
GSM8K: 28.35 vs 96.4 (so35)-70.6%
LLME Score: 0.1597
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)
Midnight Rose 70B V2.0.3 AWQ Parameters and Internals
| LLM Name | Midnight Rose 70B V2.0.3 AWQ |
| Repository 🤗 | https://huggingface.co/anyisalin/Midnight-Rose-70B-v2.0.3-AWQ |
| Base Model(s) | |
| Model Size | 70b |
| Required VRAM | 36.7 GB |
| Updated | 2025-09-18 |
| Maintainer | anyisalin |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Midnight Rose 70B V2.0.3 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...0B Instruct Gradient 1048K AWQ | 1024K / 39.9 GB | 11 | 1 |
| ...70B Instruct Gradient 262K AWQ | 256K / 39.9 GB | 6 | 0 |
| Llama 3.3 70B Instruct AWQ | 128K / 39.9 GB | 360446 | 6 |
| Llama 3.3 70B Instruct AWQ | 128K / 39.9 GB | 148349 | 35 |
| ...lama 3.3 70B Instruct AWQ INT4 | 128K / 39.9 GB | 20913 | 25 |
| ... SauerkrautLM 70B Instruct AWQ | 128K / 39.9 GB | 67 | 5 |
| MultiVerse 70B AWQ | 32K / 41.3 GB | 7 | 2 |
| Opus V1.2 70B AWQ | 32K / 36.7 GB | 8 | 1 |
| QuartetAnemoi 70B T0.0001 AWQ | 31K / 36.7 GB | 4 | 1 |
| Senku 70B AWQ 4bit GEMM | 31K / 36.7 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than anyisalin/Midnight-Rose-70B-v2.0.3-AWQ .
Rank the Midnight Rose 70B V2.0.3 AWQ 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? 51435 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124