4-bit Autotrain compatible Conversational Endpoints compatible Gptq Mistral Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/ramitpahwa13/OpenHermes-2.5-Mistral-7B-Pruned50-GPTQ-Marlin
OpenHermes 2.5 Mistral 7B Pruned50 GPTQ Marlin 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)
OpenHermes 2.5 Mistral 7B Pruned50 GPTQ Marlin Parameters and Internals
| LLM Name | OpenHermes 2.5 Mistral 7B Pruned50 GPTQ Marlin |
| Repository 🤗 | https://huggingface.co/ramitpahwa13/OpenHermes-2.5-Mistral-7B-Pruned50-GPTQ-Marlin |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4 GB |
| Updated | 2024-10-18 |
| Maintainer | ramitpahwa13 |
| Model Type | mistral |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MistralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.42.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 32002 |
| Torch Data Type | float16 |
Best Alternatives to OpenHermes 2.5 Mistral 7B Pruned50 GPTQ Marlin
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B Instruct V0.3 GPTQ | 32K / 4.2 GB | 20914 | 0 |
| Mistral 7B Instruct V0.2 GPTQ | 32K / 4.2 GB | 487409 | 50 |
| Mistral 7B Instruct V0.1 GPTQ | 32K / 4.2 GB | 939205 | 77 |
| Mistral 7B OpenOrca GPTQ | 32K / 4.2 GB | 440706 | 100 |
| ...ral 7B Instruct V0.3 GPTQ 4bit | 32K / 4.2 GB | 1260 | 15 |
| ...ephyr 7B Beta Channelwise Gptq | 32K / 4 GB | 11422 | 0 |
| ...hyr 7B Beta Channelwise Marlin | 32K / 4 GB | 6193 | 0 |
| Zephyr 7B Beta Marlin | 32K / 4.1 GB | 6254 | 0 |
| Dolphin 2.0 Mistral 7B GPTQ | 32K / 4.2 GB | 119027 | 8 |
| Mistral 7B Unsloth Gptq 8bit | 32K / 7.7 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ramitpahwa13/OpenHermes-2.5-Mistral-7B-Pruned50-GPTQ-Marlin .
Rank the OpenHermes 2.5 Mistral 7B Pruned50 GPTQ Marlin 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? 38770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124