4-bit Autotrain compatible Awq Chat Conversational En Endpoints compatible Ghost Mistral Quantized Region:us Safetensors Tools Vi
Ghost 7B Alpha AWQ Benchmarks
ARC: 54.86 vs 96.7 (so35)-43.3%
HellaSwag: 76.1 vs 95.3 (gpt4)-20.1%
MMLU: 50.71 vs 88.3 (so35)-42.6%
TruthfulQA: 44.63 vs 59 (gpt4)-24.4%
WinoGrande: 71.9 vs 87.5 (gpt4)-17.8%
GSM8K: 47.69 vs 96.4 (so35)-50.5%
LLME Score: 0.23526
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)
Ghost 7B Alpha AWQ Parameters and Internals
| LLM Name | Ghost 7B Alpha AWQ |
| Repository 🤗 | https://huggingface.co/ghost-x/ghost-7b-alpha-awq |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.2 GB |
| Updated | 2024-09-07 |
| Maintainer | ghost-x |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en vi |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MistralForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Ghost 7B Alpha AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B Instruct V0.2 AWQ | 32K / 4.2 GB | 6 | 0 |
| Mistral 7B Instruct V0.3 AWQ | 32K / 4.2 GB | 2928 | 2 |
| Mistral 7B Instruct V0.2 AWQ | 32K / 4.2 GB | 48232 | 41 |
| ...ybaraHermes 2.5 Mistral 7B AWQ | 32K / 4.2 GB | 7969 | 17 |
| Breeze 7B Instruct V1.0 AWQ | 32K / 4.6 GB | 146 | 0 |
| Mahou 1.3a Mistral 7B AWQ | 32K / 4.2 GB | 45 | 1 |
| ...reeze 7B 32K Instruct V1.0 AWQ | 32K / 4.7 GB | 9 | 0 |
| Mahou 1.3 Mistral 7B AWQ | 32K / 4.2 GB | 5 | 0 |
| Tess 7B V2.0 AWQ | 32K / 4.2 GB | 6 | 1 |
| Mistral 7B Instruct V0.3 AWQ | 32K / 4.2 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ghost-x/ghost-7b-alpha-awq .
Rank the Ghost 7B Alpha 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803