Autotrain compatible Conversational Endpoints compatible Fp16 Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow Yi
Model Card on HF 🤗: https://huggingface.co/cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16
TomGrc FusionNet 34Bx2 MoE V0.1 DPO F16 Benchmarks
ARC: 74.06 vs 96.7 (so35)-23.4%
HellaSwag: 86.74 vs 95.3 (gpt4)-9%
MMLU: 76.65 vs 88.3 (so35)-13.2%
TruthfulQA: 72.24 vs 59 (gpt4)22.4%
WinoGrande: 83.35 vs 87.5 (gpt4)-4.7%
GSM8K: 74.45 vs 96.4 (so35)-22.8%
LLME Score: 0.17836
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)
TomGrc FusionNet 34Bx2 MoE V0.1 DPO F16 Parameters and Internals
| Model Type |
|
| LLM Name | TomGrc FusionNet 34Bx2 MoE V0.1 DPO F16 |
| Repository 🤗 | https://huggingface.co/cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 |
| Model Size | 60.8b |
| Required VRAM | 121.8 GB |
| Updated | 2025-09-23 |
| Maintainer | cloudyu |
| Model Type | mixtral |
| Model Files | |
| Quantization Type | fp16 |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 200000 |
| Model Max Length | 200000 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to TomGrc FusionNet 34Bx2 MoE V0.1 DPO F16
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| 60B MoE Coder V3 | 195K / 121.8 GB | 5 | 3 |
| Mixtral 34Bx2 MoE 60B | 195K / 121.9 GB | 9915 | 111 |
| Yi 34Bx2 MoE 60B DPO | 195K / 121.8 GB | 9734 | 3 |
| Bagel Hermes 2x34B | 195K / 121.9 GB | 67 | 16 |
| Yi 34Bx2 MoE 200K | 195K / 121.9 GB | 9768 | 2 |
| Yi 34Bx2 MoE 60B | 195K / 121.9 GB | 9792 | 65 |
| ...34Bx2 MoE V0.1 Full Linear DPO | 195K / 121.8 GB | 5 | 2 |
| FusionNet 34Bx2 MoE V0.1 | 195K / 121.2 GB | 7 | 8 |
| ... Cloudyu Mixtral 34Bx2 MoE 60B | 195K / 121.8 GB | 8 | 0 |
| FusionNet 34Bx2 MoE | 32K / 121.2 GB | 1719 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 .
Rank the TomGrc FusionNet 34Bx2 MoE V0.1 DPO F16 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124