4-bit Autotrain compatible Base model:lumiopen/poro-34b Base model:quantized:lumiopen/... Bloom Dataset:allenai/dolma Dataset:bigcode/starcoderdata Dataset:cerebras/slimpajama-62... Dataset:mc4 Gptq Quantized Region:us Safetensors
Poro 34B GPTQ Benchmarks
ARC: 47.01 vs 96.7 (so35)-51.4%
HellaSwag: 73.75 vs 95.3 (gpt4)-22.6%
MMLU: 32.47 vs 88.3 (so35)-63.2%
TruthfulQA: 38.37 vs 59 (gpt4)-35%
WinoGrande: 71.35 vs 87.5 (gpt4)-18.5%
GSM8K: 5.08 vs 96.4 (so35)-94.7%
LLME Score: 0.21085
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)
Poro 34B GPTQ Parameters and Internals
| LLM Name | Poro 34B GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Poro-34B-GPTQ |
| Model Name | Poro 34B |
| Model Creator | LumiOpen |
| Base Model(s) | |
| Model Size | 34b |
| Required VRAM | 20.3 GB |
| Updated | 2024-09-07 |
| Maintainer | TheBloke |
| Model Type | bloom |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | BloomForCausalLM |
| License | apache-2.0 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | BloomTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 128000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Poro 34B GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Poro 34B Chat | 0K / 68 GB | 834 | 9 |
| Poro 34B | 0K / 68 GB | 1726 | 112 |
| Poro 34B AWQ | 0K / 21 GB | 30 | 2 |
| Poro 34B AWQ | 0K / 21 GB | 15 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Poro-34B-GPTQ .
Rank the Poro 34B 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! 🌟
What open-source LLMs or SLMs are you in search of? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803