Harmonia 20B 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)
Harmonia 20B Parameters and Internals
| LLM Name | Harmonia 20B |
| Repository 🤗 | https://huggingface.co/athirdpath/Harmonia-20B |
| Model Size | 20b |
| Required VRAM | 39.9 GB |
| Updated | 2024-09-16 |
| Maintainer | athirdpath |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-nc-4.0 |
| 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 |
Quantized Models of the Harmonia 20B
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| ...a No Robots 20B 3.0bpw H6 EXL2 | 1 | 1 | 7 GB |
Best Alternatives to Harmonia 20B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Internlm2 20B Llama | 32K / 39.6 GB | 671 | 20 |
| Stellaris Internlm2 20B R512 | 32K / 39.8 GB | 6 | 3 |
| Internlm2 Chat 20B Llama Old | 32K / 39.6 GB | 6 | 3 |
| Internlm2 Base 20B Llama | 32K / 39.6 GB | 6 | 3 |
| Deita 20B | 32K / 39.8 GB | 73 | 1 |
| Internlm2 Base 20B Llama | 32K / 39.6 GB | 9 | 0 |
| Bagel 20B V04 Llama | 32K / 39.6 GB | 5 | 7 |
| Bagel DPO 20B V04 Llama | 32K / 39.6 GB | 9 | 3 |
| Internlm2 Limarp Chat 20B | 32K / 39.6 GB | 8 | 2 |
| Internlm2 Chat 20B Llama | 32K / 39.8 GB | 13 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than athirdpath/Harmonia-20B .
Rank the Harmonia 20B 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