Merged Model 4bit Autotrain compatible Endpoints compatible Gptq Llama Lora Pytorch Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged-4bit-32g
Openllama 3b EvolInstruct Lora Merged 4bit 32g Benchmarks
ARC: 40.27 vs 96.7 (so35)-58.4%
HellaSwag: 71.6 vs 95.3 (gpt4)-24.9%
MMLU: 27.12 vs 88.3 (so35)-69.3%
TruthfulQA: 34.78 vs 59 (gpt4)-41.1%
WinoGrande: 67.01 vs 87.5 (gpt4)-23.4%
GSM8K: 0.91 vs 96.4 (so35)-99.1%
LLME Score: 0.13388
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)
Openllama 3B EvolInstruct Lora Merged 4bit 32g Parameters and Internals
| LLM Name | Openllama 3b EvolInstruct Lora Merged 4bit 32g |
| Repository 🤗 | https://huggingface.co/KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged-4bit-32g |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 3b |
| Required VRAM | 2.3 GB |
| Updated | 2025-10-16 |
| Maintainer | KnutJaegersberg |
| Model Type | llama |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-4.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.32.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
Best Alternatives to Openllama 3B EvolInstruct Lora Merged 4bit 32g
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ma 3.2 3B Instruct XMADai INT4 | 128K / 3 GB | 7 | 6 |
| Open Llama 3b V2 8K GPTQ | 8K / 2 GB | 9 | 3 |
| Orca2myth7.2 GPTQ | 4K / 10.9 GB | 6 | 4 |
| ...B GPTQ 4bit GPTQ Code Instruct | 2K / 2 GB | 6 | 0 |
| ...zard Evol Instuct V2 196K GPTQ | 2K / 2.1 GB | 41 | 2 |
| ...ama 3B Mathwizard Quantized V2 | 2K / 3.7 GB | 6 | 0 |
| SauerkrautLM 3B V1 GPTQ | 2K / 2.3 GB | 11 | 2 |
| Marx 3B GPTQ | 2K / 2.1 GB | 9 | 3 |
| Griffin 3B GPTQ | 2K / 2.1 GB | 12 | 2 |
| Puma 3B GPTQ | 2K / 2.1 GB | 8 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than KnutJaegersberg/openllama_3b_EvolInstruct_lora_merged-4bit-32g .
Rank the Openllama 3B EvolInstruct Lora Merged 4bit 32g 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? 51547 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124