Arxiv:2303.08774 Arxiv:2309.11235 Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7... C-rlft Conversational Endpoints compatible Exl2 Mistral Openchat Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/openchat-3.5-0106-128k-8.0bpw-h8-exl2
Openchat 3.5 0106 128K 8.0bpw H8 EXL2 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)
Openchat 3.5 0106 128K 8.0bpw H8 EXL2 Parameters and Internals
| Model Type |
|
| LLM Name | Openchat 3.5 0106 128K 8.0bpw H8 EXL2 |
| Repository 🤗 | https://huggingface.co/LoneStriker/openchat-3.5-0106-128k-8.0bpw-h8-exl2 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 7.4 GB |
| Updated | 2024-12-22 |
| Maintainer | LoneStriker |
| Model Type | mistral |
| Model Files | |
| Quantization Type | exl2 |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32002 |
| Torch Data Type | bfloat16 |
Best Alternatives to Openchat 3.5 0106 128K 8.0bpw H8 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...al Nemo Instruct 2407 Bnb 4bit | 1000K / 8.3 GB | 17491 | 25 |
| ...istral Nemo Base 2407 Bnb 4bit | 1000K / 8.3 GB | 4347 | 12 |
| ...t 3.5 0106 128K 4.0bpw H6 EXL2 | 128K / 3.9 GB | 17 | 1 |
| ...tral 7B Instruct V0.3 Bnb 4bit | 32K / 4.1 GB | 278266 | 15 |
| NaturalLM 7B Instruct | 32K / 14.5 GB | 80 | 10 |
| Mistral 7B V0.3 Bnb 4bit | 32K / 4.1 GB | 63384 | 13 |
| Mistral 7B Instruct V0.2 4bit | 32K / 4.3 GB | 639 | 1 |
| Mistral 7B Instruct V0.2 Fp16 | 32K / 14.4 GB | 9 | 0 |
| ...tral 7B Instruct V0.2 Bnb 4bit | 32K / 4.1 GB | 11707 | 31 |
| ...eMistral 7B Instruct Ead 16bit | 32K / 14.5 GB | 38 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/openchat-3.5-0106-128k-8.0bpw-h8-exl2 .
Rank the Openchat 3.5 0106 128K 8.0bpw H8 EXL2 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