Arxiv:2312.13558 Autotrain compatible Endpoints compatible Exl2 Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/laser-dolphin-mixtral-2x7b-dpo-8.0bpw-h8-exl2
Laser Dolphin Mixtral 2x7b DPO 8.0bpw H8 EXL2 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)
Laser Dolphin Mixtral 2x7b DPO 8.0bpw H8 EXL2 Parameters and Internals
| LLM Name | Laser Dolphin Mixtral 2x7b DPO 8.0bpw H8 EXL2 |
| Repository 🤗 | https://huggingface.co/LoneStriker/laser-dolphin-mixtral-2x7b-dpo-8.0bpw-h8-exl2 |
| Model Size | 7b |
| Required VRAM | 13 GB |
| Updated | 2024-12-22 |
| Maintainer | LoneStriker |
| Model Type | mixtral |
| Model Files | |
| Quantization Type | exl2 |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32001 |
| Torch Data Type | bfloat16 |
Best Alternatives to Laser Dolphin Mixtral 2x7b DPO 8.0bpw H8 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...izardLM 2 4x7B MoE EXL2 3 0bpw | 32K / 9.4 GB | 12 | 1 |
| Buttercup 4x7B 6bpw EXL2 | 32K / 18.4 GB | 12 | 2 |
| BurningBruce 003 EXL2 B8.0 | 32K / 24.3 GB | 13 | 1 |
| ...ixtral 2x7b DPO 4.0bpw H6 EXL2 | 32K / 6.7 GB | 21 | 1 |
| ...ixtral 2x7b DPO 6.0bpw H6 EXL2 | 32K / 9.8 GB | 19 | 1 |
| ...ixtral 2x7b DPO 5.0bpw H6 EXL2 | 32K / 8.3 GB | 15 | 1 |
| ...t V0.2 2x7B MoE 6.0bpw H6 EXL2 | 32K / 9.9 GB | 10 | 1 |
| ...iveFusion 4x7b MoE EXL2 3.5BPW | 8K / 10.8 GB | 14 | 1 |
| ...lue Orchid 2x7b 8.0bpw H8 EXL2 | 8K / 13 GB | 42 | 5 |
| ...lue Orchid 2x7b 5.0bpw H6 EXL2 | 8K / 8.2 GB | 27 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/laser-dolphin-mixtral-2x7b-dpo-8.0bpw-h8-exl2 .
Rank the Laser Dolphin Mixtral 2x7b DPO 8.0bpw H8 EXL2 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217