4-bit Adapter Axolotl Base model:adapter:meta-llama/... Base model:meta-llama/meta-lla... Bitsandbytes En Finetuned Generated from trainer Instruct Llama Lora Peft Region:us Safetensors
Llama3 8B Instruct Code Benchmarks
ARC: 56.4 vs 96.7 (so35)-41.7%
HellaSwag: 78.32 vs 95.3 (gpt4)-17.8%
MMLU: 64.38 vs 88.3 (so35)-27.1%
TruthfulQA: 48.84 vs 59 (gpt4)-17.2%
WinoGrande: 73.8 vs 87.5 (gpt4)-15.7%
GSM8K: 58.07 vs 96.4 (so35)-39.8%
LLME Score: 0.2429
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)
Llama3 8B Instruct Code Parameters and Internals
| LLM Name | Llama3 8B Instruct Code |
| Repository 🤗 | https://huggingface.co/ibivibiv/llama3-8b-instruct-code |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.2 GB |
| Updated | 2024-09-07 |
| Maintainer | ibivibiv |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | llama3 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|down_proj|v_proj|gate_proj|up_proj|k_proj|o_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
Best Alternatives to Llama3 8B Instruct Code
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 3 8B Instruct Bvr Finetune V3 | 8K / 16.1 GB | 8 | 0 |
| Vortex2 | 0K / 4.4 GB | 8 | 0 |
| Llama3 Tw 8B Btc Qlora | 0K / 0.1 GB | 37 | 3 |
| Llama 3 8B Claudstruct V3 | 0K / 0.1 GB | 5 | 0 |
| Llama 3 8B Claudstruct V1 | 0K / 0.1 GB | 5 | 0 |
| Llama 3 8B Instruct 80K QLoRA | 0K / 2.2 GB | 0 | 22 |
| ...Llama 3 8B Instruct ORPO QLoRA | 0K / 0.7 GB | 5 | 0 |
| Llama3 8b Sa V0.1 | 0K / 0 GB | 5 | 0 |
| Llama3 Rm 96k Summ | 0K / 0 GB | 23 | 0 |
| ...ta Llama 3 8B Instruct Chatbot | 0K / 2.5 GB | 14 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ibivibiv/llama3-8b-instruct-code .
Rank the Llama3 8B Instruct Code 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