4-bit Autotrain compatible Awq Conversational Endpoints compatible Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow
Llama 3 15B Instruct Ft V2 AWQ Benchmarks
ARC: 61.35 vs 96.7 (so35)-36.6%
HellaSwag: 78.81 vs 95.3 (gpt4)-17.3%
MMLU: 67.31 vs 88.3 (so35)-23.8%
TruthfulQA: 52.33 vs 59 (gpt4)-11.3%
WinoGrande: 76.32 vs 87.5 (gpt4)-12.8%
GSM8K: 72.48 vs 96.4 (so35)-24.8%
LLME Score: 0.23353
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 15B Instruct Ft V2 AWQ Parameters and Internals
| LLM Name | Llama 3 15B Instruct Ft V2 AWQ |
| Repository 🤗 | https://huggingface.co/solidrust/Llama-3-15B-Instruct-ft-v2-AWQ |
| Base Model(s) | |
| Model Size | 15b |
| Required VRAM | 9.4 GB |
| Updated | 2024-09-02 |
| Maintainer | solidrust |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Llama 3 15B Instruct Ft V2 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| L3 Aethora 15B V2 EXL2 6.0bpw | 8K / 11.9 GB | 3 | 1 |
| L3 Aethora 15B V2 EXL2 8.0bpw | 8K / 12.4 GB | 2 | 1 |
| L3 Aethora 15B V2 EXL2 4.0bpw | 8K / 8.4 GB | 1 | 1 |
| L3 Aethora 15B V2 EXL2 5.0bpw | 8K / 10.2 GB | 1 | 1 |
| L3 Aethora 15B V2 | 8K / 30.1 GB | 43 | 39 |
| OpenCrystal 15B L3 V3 | 8K / 30 GB | 59 | 6 |
| OpenCrystal L3 15B V2.1 | 8K / 30 GB | 23 | 5 |
| OpenCrystal 15B L3 V2 | 8K / 30 GB | 36 | 4 |
| Meta Llama 3 15B Instruct | 8K / 23.9 GB | 1 | 1 |
| Llama 3 15B Instruct Ft V2 | 8K / 30.1 GB | 3 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than solidrust/Llama-3-15B-Instruct-ft-v2-AWQ .
Rank the Llama 3 15B Instruct Ft V2 AWQ 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? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803