Arxiv:1910.09700 4-bit 4bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/zurd46/Zurd_llama-3-8b-Instruct-bnb-4bit
Zurd Llama 3 8B Instruct Bnb 4bit Benchmarks
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)
Zurd Llama 3 8B Instruct Bnb 4bit Parameters and Internals
| LLM Name | Zurd Llama 3 8B Instruct Bnb 4bit |
| Repository 🤗 | https://huggingface.co/zurd46/Zurd_llama-3-8b-Instruct-bnb-4bit |
| Model Size | 8b |
| Required VRAM | 5.8 GB |
| Updated | 2024-07-21 |
| Maintainer | zurd46 |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| Vocabulary Size | 128256 |
| PEFT Type | LORA |
| PEFT Target Modules | down_proj|gate_proj|up_proj|k_proj|o_proj|q_proj|v_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
| Torch Data Type | float16 |
Best Alternatives to Zurd Llama 3 8B Instruct Bnb 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...B Instruct Gradient 1048K 4bit | 1024K / 4.5 GB | 24 | 2 |
| ...B Instruct Gradient 1048K 8bit | 1024K / 8.6 GB | 21 | 1 |
| ...truct Gradient 1048K Bpw6 EXL2 | 1024K / 6.7 GB | 10 | 2 |
| ...truct Gradient 1048K Bpw5 EXL2 | 1024K / 5.8 GB | 9 | 0 |
| Llama 3 8B Instruct 1048K 4bit | 1024K / 4.5 GB | 12 | 25 |
| Llama 3 8B Instruct 1048K 8bit | 1024K / 8.6 GB | 25 | 17 |
| ... Gradient 1048K 8.0bpw H8 EXL2 | 1024K / 8.6 GB | 8 | 3 |
| ...ct Gradient 1048K Bpw2.25 EXL2 | 1024K / 3.4 GB | 10 | 1 |
| ...B Instruct 262k V2 EXL2 8.0bpw | 256K / 8.4 GB | 32 | 0 |
| Llama 3 8B Instruct 262K 2bit | 256K / 2.5 GB | 19 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than zurd46/Zurd_llama-3-8b-Instruct-bnb-4bit .
Rank the Zurd Llama 3 8B Instruct Bnb 4bit 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? 41636 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227