4-bit Awq Base model:adapter:chat-error/... Base model:chat-error/rose-kim... Fp16 Generated from trainer Llama Peft Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Rose-Kimiko-20B-AWQ
Rose Kimiko 20B 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)
Rose Kimiko 20B AWQ Parameters and Internals
| Model Type |
| |||||||||
| Use Cases |
| |||||||||
| Additional Notes |
| |||||||||
| Training Details |
| |||||||||
| Input Output |
|
| LLM Name | Rose Kimiko 20B AWQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Rose-Kimiko-20B-AWQ |
| Model Name | Rose Kimiko 20B |
| Model Creator | nRuaif |
| Base Model(s) | |
| Model Size | 20b |
| Required VRAM | 10.9 GB |
| Updated | 2025-08-22 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | fp16|awq |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Rose Kimiko 20B AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Norocetacean 20B 10K AWQ | 10K / 10.9 GB | 6 | 2 |
| DaringMaid 20B AWQ | 4K / 10.9 GB | 6 | 2 |
| Nethena 20B Glued AWQ | 4K / 10.9 GB | 8 | 2 |
| Iambe Storyteller 20B AWQ | 4K / 10.9 GB | 6 | 1 |
| Noromaid 20B V0.1.1 AWQ | 4K / 10.9 GB | 96 | 4 |
| Iambe 20B DARE AWQ | 4K / 10.9 GB | 6 | 1 |
| Rose 20B AWQ | 4K / 10.9 GB | 25 | 1 |
| Nethena 20B AWQ | 4K / 10.9 GB | 16 | 2 |
| MXLewd L2 20B AWQ | 4K / 10.9 GB | 10 | 3 |
| InternLM2 Chat 20B ToxicRP | 32K / 39.9 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Rose-Kimiko-20B-AWQ .
Rank the Rose Kimiko 20B 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? 50835 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124