4-bit Autotrain compatible Base model:rombodawg/open gpt4... Gptq License:apache-2.0 Merge Mixtral Moe Quantized Region:us Safetensors
Open Gpt4 8x7B V0.2 GPTQ Benchmarks
HF Avg Score: 64.5 vs 86.1 (GPT-4) -25.1%
ARC: 60.4-37.3%
HellaSwag: 72.4-24%
MMLU: 63.4-26.7%
TruthfulQA: 6916.9%
WinoGrande: 81.9-6.4%
GSM8K: 42.6-53.7%
nn.n% — How the model compares to the GPT-4.
Rank the Open Gpt4 8x7B V0.2 GPTQ 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! 🌟
Best Alternatives to Open Gpt4 8x7B V0.2 GPTQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| UNAversal 8x7B V1beta GPTQ | 64.7 | 32K / 23.8 GB | 6 | 1 |
| ...xtral Instruct 8x7b Zloss GPTQ | 64.2 | 32K / 23.8 GB | 27 | 2 |
| ...Hermes 2 Mixtral 8x7B DPO GPTQ | 64.1 | 32K / 23.8 GB | 11568 | 25 |
| Notux 8x7b V1 GPTQ | 64 | 32K / 23.8 GB | 6 | 2 |
| ...tLM Mixtral 8x7B Instruct GPTQ | 63.8 | 32K / 23.8 GB | 48 | 3 |
| ...ixtral 8x7B Instruct V0.1 GPTQ | 63.7 | 32K / 23.8 GB | 694568 | 127 |
| Bagel DPO 8x7b V0.2 GPTQ | 63.6 | 32K / 23.8 GB | 1 | 2 |
| ...ixtral 8x7B V0.1 Dolly15K GPTQ | 63.5 | 32K / 23.8 GB | 6 | 2 |
| ...Hermes 2 Mixtral 8x7B SFT GPTQ | 63.2 | 32K / 23.8 GB | 35 | 10 |
| Firefly Mixtral 8x7b GPTQ | 61.7 | 32K / 23.8 GB | 5 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Open_Gpt4_8x7B_v0.2-GPTQ .
Open Gpt4 8x7B V0.2 GPTQ Parameters and Internals
| LLM Name | Open Gpt4 8x7B V0.2 GPTQ |
| Repository | Open on 🤗 |
| Model Name | Open Gpt4 8X7B V0.2 |
| Model Creator | rombo dawg |
| Base Model(s) | |
| Model Size | 6.1b |
| Required VRAM | 23.8 GB |
| Updated | 2024-07-01 |
| Maintainer | TheBloke |
| Model Type | mixtral |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Initializer Range | 0.02 |
| Torch Data Type | float16 |
What open-source LLMs or SLMs are you in search of? 34238 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801