5-bit Autotrain compatible Conversational En Endpoints compatible Exl2 Instruct Llama Llama-3 Meta Quantized Region:us Safetensors
Llama 3 8B Instruct Gradient 1048K Bpw5 EXL2 Benchmarks
ARC: 54.44 vs 96.7 (so35)-43.7%
HellaSwag: 76.77 vs 95.3 (gpt4)-19.4%
MMLU: 61.92 vs 88.3 (so35)-29.9%
TruthfulQA: 49.26 vs 59 (gpt4)-16.5%
WinoGrande: 72.3 vs 87.5 (gpt4)-17.4%
GSM8K: 44.35 vs 96.4 (so35)-54%
LLME Score: 0.23524
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)
Llama 3 8B Instruct Gradient 1048K Bpw5 EXL2 Parameters and Internals
| LLM Name | Llama 3 8B Instruct Gradient 1048K Bpw5 EXL2 |
| Repository 🤗 | https://huggingface.co/blockblockblock/Llama-3-8B-Instruct-Gradient-1048k-bpw5-exl2 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 5.8 GB |
| Updated | 2024-09-06 |
| Maintainer | blockblockblock |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Quantization Type | exl2 |
| Model Architecture | LlamaForCausalLM |
| License | llama3 |
| Context Length | 1048576 |
| Model Max Length | 1048576 |
| Transformers Version | 4.41.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama 3 8B Instruct Gradient 1048K Bpw5 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...B Instruct Gradient 1048K 4bit | 1024K / 4.5 GB | 5 | 2 |
| ...B Instruct Gradient 1048K 8bit | 1024K / 8.6 GB | 7 | 1 |
| ...truct Gradient 1048K Bpw6 EXL2 | 1024K / 6.7 GB | 9 | 2 |
| Llama 3 8B Instruct 1048K 4bit | 1024K / 4.5 GB | 10 | 25 |
| Llama 3 8B Instruct 1048K 8bit | 1024K / 8.6 GB | 5 | 16 |
| ... Gradient 1048K 8.0bpw H8 EXL2 | 1024K / 8.6 GB | 4 | 3 |
| ...ct Gradient 1048K Bpw2.25 EXL2 | 1024K / 3.4 GB | 4 | 1 |
| Llama 3 8B Instruct 262K 2bit | 256K / 2.5 GB | 4 | 1 |
| ...B Instruct 262k V2 EXL2 5.0bpw | 256K / 5.8 GB | 4 | 1 |
| ...B Instruct 262k V2 EXL2 6.0bpw | 256K / 6.7 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than blockblockblock/Llama-3-8B-Instruct-Gradient-1048k-bpw5-exl2 .
Rank the Llama 3 8B Instruct Gradient 1048K Bpw5 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803