4-bit Autotrain compatible Awq Conversational Endpoints compatible Mistral Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/cnmoro/FuseChat-7B-VaRM-AWQ
FuseChat 7B VaRM AWQ Benchmarks
ARC: 62.88 vs 96.7 (so35)-35%
HellaSwag: 84.25 vs 95.3 (gpt4)-11.6%
MMLU: 63.71 vs 88.3 (so35)-27.8%
TruthfulQA: 45.67 vs 59 (gpt4)-22.6%
WinoGrande: 79.16 vs 87.5 (gpt4)-9.5%
GSM8K: 63.46 vs 96.4 (so35)-34.2%
LLME Score: 0.18161
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)
FuseChat 7B VaRM AWQ Parameters and Internals
| LLM Name | FuseChat 7B VaRM AWQ |
| Repository 🤗 | https://huggingface.co/cnmoro/FuseChat-7B-VaRM-AWQ |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.2 GB |
| Updated | 2024-12-05 |
| Maintainer | cnmoro |
| Model Type | mistral |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MistralForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.38.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32002 |
| Torch Data Type | float16 |
Best Alternatives to FuseChat 7B VaRM AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B Instruct V0.2 AWQ | 32K / 4.2 GB | 79 | 0 |
| Mistral 7B Instruct V0.3 AWQ | 32K / 4.2 GB | 19866 | 3 |
| Mistral 7B Instruct V0.2 AWQ | 32K / 4.2 GB | 33713 | 43 |
| Ghost 7B Alpha AWQ | 32K / 4.2 GB | 80 | 0 |
| Mahou 1.3a Mistral 7B AWQ | 32K / 4.2 GB | 80 | 1 |
| Tess 7B V2.0 AWQ | 32K / 4.2 GB | 79 | 1 |
| Mahou 1.3 Mistral 7B AWQ | 32K / 4.2 GB | 87 | 0 |
| Breeze 7B Instruct V1.0 AWQ | 32K / 4.6 GB | 9 | 0 |
| ...reeze 7B 32K Instruct V1.0 AWQ | 32K / 4.7 GB | 9 | 0 |
| ...Instruct V0.2 AWQ 4bit Smashed | 32K / 4.2 GB | 92 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than cnmoro/FuseChat-7B-VaRM-AWQ .
Rank the FuseChat 7B VaRM 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? 43508 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227