Model Type |
| ||||||||||||
Additional Notes |
| ||||||||||||
Supported Languages |
| ||||||||||||
Training Details |
| ||||||||||||
Input Output |
|
LLM Name | RedPajama INCITE Chat 7B V0.1 GGML |
Repository ๐ค | https://huggingface.co/keldenl/RedPajama-INCITE-Chat-7B-v0.1-GGML |
Model Size | 7b |
Required VRAM | 4.3 GB |
Updated | 2025-08-18 |
Maintainer | keldenl |
Model Type | gpt_neox |
Model Files | |
Supported Languages | en |
GGML Quantization | Yes |
Quantization Type | fp16|ggml|q4 |
Model Architecture | GPTNeoXForCausalLM |
License | apache-2.0 |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.28.1 |
Tokenizer Class | GPTNeoXTokenizer |
Vocabulary Size | 50432 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...a INCITE Instruct 7B V0.1 GGML | 2K / 4.3 GB | 11 | 7 |
Stablelm Tuned Alpha 7B 16bit | 4K / 16 GB | 17 | 5 |
...lm Tuned Alpha 7B Sharded 8bit | 4K / 8.6 GB | 19 | 2 |
Open Calm 7B 8bit | 2K / 7.4 GB | 20 | 10 |
Dolly V2 7B Sharded 8bit | 2K / 7.4 GB | 15 | 1 |
Dolly V2 7B 8bit | 2K / 7.4 GB | 18 | 0 |
Literature 7B 16384 | 16K / 36 GB | 15 | 14 |
RedPajama 7B 16384 | 16K / 36 GB | 14 | 4 |
Stablelm Tuned Alpha 7B | 4K / 31.9 GB | 2774 | 360 |
Stablelm Base Alpha 7B | 4K / 31.9 GB | 2400 | 209 |
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