LLM Name | Mychen76 Mistral7b Ocr To Json V1 HQQ 1bit Smashed |
Repository ๐ค | https://huggingface.co/PrunaAI/mychen76-mistral7b_ocr_to_json_v1-HQQ-1bit-smashed |
Base Model(s) | |
Required VRAM | 1.6 GB |
Updated | 2024-09-06 |
Maintainer | PrunaAI |
Model Type | mistral |
Model Files | |
Quantization Type | 1bit |
Model Architecture | MistralForCausalLM |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.40.0 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...cr To Json V1 HQQ 1bit Smashed | 0 | 5 | 1 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
NemoMix Unleashed EXL2 4bpw | 1000K / 7.3 GB | 60 | 3 |
...cr To Json V1 HQQ 4bit Smashed | 32K / 4.2 GB | 5 | 0 |
ScikitLLM Model EXL2 | 32K / 3 GB | 3 | 1 |
Chargen V2 8bpw EXL2 | 32K / 7.4 GB | 9 | 1 |
...tral PairRM DPO 8.0bpw H8 EXL2 | 32K / 7.4 GB | 3 | 2 |
HamSter 0.2 8.0bpw H8 EXL2 | 32K / 7.4 GB | 9 | 1 |
...N L1 Chat RL V1.3.0bpw H6 EXL2 | 32K / 3 GB | 30 | 0 |
...N L1 Chat RL V1.6.0bpw H6 EXL2 | 32K / 5.6 GB | 11 | 1 |
...Bruins V2.1.1 8.0bpw H8 EXL2 2 | 32K / 7.4 GB | 13 | 2 |
...Bruins V2.1.1 6.0bpw H6 EXL2 2 | 32K / 5.6 GB | 14 | 1 |
๐ 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! ๐