4-bit Autotrain compatible Awq Base model:nlpai-lab/kullm3 Base model:quantized:nlpai-lab... Conversational En Endpoints compatible Ko Llama Quantized Region:us Safetensors Sharded Tensorflow
KULLM3 AWQ 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)
KULLM3 AWQ Parameters and Internals
| LLM Name | KULLM3 AWQ |
| Repository 🤗 | https://huggingface.co/taeminlee/KULLM3-awq |
| Base Model(s) | |
| Model Size | 10.7b |
| Required VRAM | 6 GB |
| Updated | 2024-09-08 |
| Maintainer | taeminlee |
| Model Type | llama |
| Model Files | |
| Supported Languages | en ko |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to KULLM3 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SOLAR 10.7B Instruct V1.0 AWQ | 4K / 6 GB | 320653 | 5 |
| STOCK SOLAR 10.7B AWQ | 4K / 6 GB | 5 | 0 |
| Tess 10.7B V1.5B AWQ | 4K / 6 GB | 24 | 4 |
| Nous Hermes 2 SOLAR 10.7B AWQ | 4K / 6 GB | 45 | 9 |
| Sensualize Solar 10.7B AWQ | 4K / 6 GB | 8 | 1 |
| CarbonVillain En 10.7B V4 AWQ | 4K / 6 GB | 5 | 1 |
| LMCocktail 10.7B V1 AWQ | 4K / 6 GB | 7 | 1 |
| Frostwind 10.7B V1 AWQ | 4K / 6 GB | 10 | 1 |
| Solar 10.7B SLERP AWQ | 4K / 6 GB | 28 | 1 |
| SOLAR Platypus 10.7B V2 AWQ | 4K / 6 GB | 6 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than taeminlee/KULLM3-awq .
Rank the KULLM3 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803