Autotrain compatible Conversational Endpoints compatible Gguf Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow
Vi Math Llama3 Parameters and Internals
| LLM Name | Vi Math Llama3 |
| Repository | Open on 🤗 |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2024-07-26 |
| Maintainer | dachieu |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | LlamaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Vi Math Llama3
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...truct Gradient 1048K IMat GGUF | 0.3 | 1024K / 2 GB | 430 | 6 |
| ...B Instruct Gradient 1048K GGUF | 0.2 | 1024K / 3.2 GB | 297 | 3 |
| Llama 3 8B Instruct 262K GGUF | 0.2 | 256K / 3.2 GB | 363 | 2 |
| Alpha R S V2 Q8 0 GGUF | 0.2 | 39K / 8.5 GB | 17 | 0 |
| ...ama3 8B Chinese Chat GGUF 8bit | 0.4 | 8K / 8.5 GB | 22032 | 156 |
| CircularConstructionGPT 1 | 0.3 | 8K / 16.1 GB | 1921 | 0 |
| ...ama3 8B Chinese Chat GGUF 4bit | 0.3 | 8K / 4.7 GB | 3773 | 18 |
| ...lama3 8B Chinese Chat GGUF F16 | 0.3 | 8K / 16.1 GB | 2908 | 25 |
| ...hinese 8B Instruct V3 Accident | 0.3 | 8K / 16.1 GB | 167 | 1 |
| Llama 3 Chinese 8B Instruct V3 | 0.3 | 8K / 16.1 GB | 161 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than dachieu/vi-math-llama3 .
Rank the Vi Math Llama3 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501