4-bit Autotrain compatible Awq Endpoints compatible Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/DeL-TaiseiOzaki/Tengentoppa-11B-Instruct-awq
Tengentoppa 11B Instruct 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)
Tengentoppa 11B Instruct AWQ Parameters and Internals
| LLM Name | Tengentoppa 11B Instruct AWQ |
| Repository 🤗 | https://huggingface.co/DeL-TaiseiOzaki/Tengentoppa-11B-Instruct-awq |
| Base Model(s) | |
| Model Size | 11b |
| Required VRAM | 6.8 GB |
| Updated | 2024-12-22 |
| Maintainer | DeL-TaiseiOzaki |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | T5Tokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 50816 |
| Torch Data Type | float16 |
Best Alternatives to Tengentoppa 11B Instruct AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3 16B Instruct V0.1 | 8K / 33.5 GB | 314 | 5 |
| Llama 3 11B Instruct RP GLUED | 8K / 22.2 GB | 60 | 3 |
| Llama 3 11B Instruct | 8K / 22.1 GB | 54 | 3 |
| Llama 3 Synatra 11B V1 | 8K / 23 GB | 60 | 12 |
| SyntheticMoist 11B V2 | 4K / 21.4 GB | 54 | 2 |
| Antares 11B V1 | 4K / 21.4 GB | 107 | 2 |
| MedMitsu Instruct 11B | 4K / 21.4 GB | 9 | 0 |
| Tengentoppa 11B Instruct | 2K / 23.2 GB | 0 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than DeL-TaiseiOzaki/Tengentoppa-11B-Instruct-awq .
Rank the Tengentoppa 11B Instruct 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217