LLM Name | WordWoven 13B GPTQ |
Repository ๐ค | https://huggingface.co/TheBloke/WordWoven-13B-GPTQ |
Model Name | WordWoven 13B |
Model Creator | wbag |
Base Model(s) | |
Model Size | 13b |
Required VRAM | 7.1 GB |
Updated | 2024-09-07 |
Maintainer | TheBloke |
Model Type | mixtral |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq |
Model Architecture | MixtralForCausalLM |
License | mit |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.37.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <s> |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...et 7Bx2 MoE 13B 6.0bpw H6 EXL2 | 32K / 9.8 GB | 11 | 3 |
...et 7Bx2 MoE 13B 4.0bpw H6 EXL2 | 32K / 6.7 GB | 13 | 1 |
...et 7Bx2 MoE 13B 3.0bpw H6 EXL2 | 32K / 5.1 GB | 13 | 0 |
LuminRP 13B 128K | 128K / 25.8 GB | 5 | 2 |
Yunconglong 13B Slerp | 32K / 25.7 GB | 13 | 0 |
T3Q MSlerp 13B | 32K / 51.8 GB | 66 | 0 |
Eclipse 13B DPO | 32K / 25.8 GB | 63 | 0 |
13B MATH DPO | 32K / 25.8 GB | 70 | 1 |
WordWoven 13B AWQ | 32K / 7.1 GB | 8 | 2 |
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