LLM Name | H2ogpt Gm Oasst1 En 2048 Falcon 40B V2 GGML |
Repository ๐ค | https://huggingface.co/TheBloke/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2-GGML |
Model Size | 40b |
Required VRAM | 13.7 GB |
Updated | 2024-09-07 |
Maintainer | TheBloke |
Model Type | falcon |
Model Files | |
Supported Languages | en |
GGML Quantization | Yes |
Quantization Type | ggml |
Model Architecture | AutoModel |
License | apache-2.0 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Falcon 40B Sft Mix 1226 GGML | 0K / 13.7 GB | 2 | 11 |
Falcon 40B Sft Top1 560 GGML | 0K / 13.7 GB | 2 | 6 |
Falcon 40B Instruct GGML | 0K / 13.7 GB | 3 | 58 |
...dLM Uncensored Falcon 40B GGML | 0K / 13.7 GB | 3 | 40 |
Alfred 40B 1023 GGUF | 0K / 17.4 GB | 501 | 4 |
Ct2fast Falcon 40B Instruct | 0K / 41.3 GB | 4 | 2 |
Ct2fast Falcon 40B | 0K / 41.3 GB | 2 | 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