Model Card on HF 🤗: https://huggingface.co/nisten/shqiponja-15b-v2-8bit
Shqiponja 15B V2 8bit 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)
Shqiponja 15B V2 8bit Parameters and Internals
| Additional Notes |
|
| LLM Name | Shqiponja 15B V2 8bit |
| Repository 🤗 | https://huggingface.co/nisten/shqiponja-15b-v2-8bit |
| Model Size | 15b |
| Required VRAM | 16.3 GB |
| Updated | 2025-02-22 |
| Maintainer | nisten |
| Model Type | mixtral |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|8bit |
| Model Architecture | MixtralForCausalLM |
| License | gpl-3.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Shqiponja 15B V2 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Helion 4x34B GPTQ | 195K / 58.3 GB | 33 | 3 |
| Shqiponja 15B V1 | 32K / 31.3 GB | 2 | 3 |
| HelpingAI 15B | 4K / 31.6 GB | 57 | 12 |
| HelpingAI 15B | 4K / 31.6 GB | 140 | 13 |
Note: green Score (e.g. "73.2") means that the model is better than nisten/shqiponja-15b-v2-8bit .
Rank the Shqiponja 15B V2 8bit 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? 43508 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227