16bit Autotrain compatible Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Chan2chan1/solar_test_240517_16bit
Solar Test 240517 16bit 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)
Solar Test 240517 16bit Parameters and Internals
| LLM Name | Solar Test 240517 16bit |
| Repository 🤗 | https://huggingface.co/Chan2chan1/solar_test_240517_16bit |
| Model Size | 10.7b |
| Required VRAM | 21.4 GB |
| Updated | 2025-08-19 |
| Maintainer | Chan2chan1 |
| Model Type | llama |
| Model Files | |
| Quantization Type | 16bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.39.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Solar Test 240517 16bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 10.7B Instruct V1.0 128K EXL2 | 128K / 5.6 GB | 6 | 1 |
| ...e KoSoLAR 10.7B V0.2 1.4 Dedup | 4K / 43.2 GB | 841 | 0 |
| KoSoLAR 10.7B V0.2 1.4 Dedup 1 | 4K / 21.6 GB | 835 | 0 |
| KoSoLAR 10.7B V0.2 1.4 Dedup | 4K / 21.6 GB | 12 | 0 |
| Frostwind 10.7B V1 EXL2 | 4K / 10.9 GB | 5 | 1 |
| Eclectus 1.1 Dedup | 4K / 21.4 GB | 836 | 0 |
| Eclectus1.1 | 4K / 21.4 GB | 734 | 0 |
| Solar 10.7B Bnb 4bit | 4K / 5.9 GB | 10 | 3 |
| ...ess 10.7B V1.5B 8.0bpw H8 EXL2 | 4K / 10.9 GB | 5 | 1 |
| DaringLotus V2.10.7B 3bpw EXL2 | 4K / 4.3 GB | 5 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Chan2chan1/solar_test_240517_16bit .
Rank the Solar Test 240517 16bit 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? 50751 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124