Autotrain compatible Conversational Dataset:teknium/openhermes-2.5 En Endpoints compatible Q7 Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/jueyuan111/q7-oher
Q7 Oher Benchmarks
MMLU Pro: 16.34
GPQA: 2.57
MUSR: 4.47
BBH: 16.21
IFEval: 29.35 vs 88 (so35)-66.6%
MATH Lvl 5: 0.08
LLME Score: 0.22525
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)
Q7 Oher Parameters and Internals
| LLM Name | Q7 Oher |
| Repository 🤗 | https://huggingface.co/jueyuan111/q7-oher |
| Model Size | 7.7b |
| Required VRAM | 15.4 GB |
| Updated | 2024-08-26 |
| Maintainer | jueyuan111 |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | q7 |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.39.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the Q7 Oher 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227