Model Type |
| ||||||||||||
Use Cases |
| ||||||||||||
Additional Notes |
| ||||||||||||
Supported Languages |
| ||||||||||||
Training Details |
| ||||||||||||
Input Output |
|
LLM Name | Llama3 DiscoLeo Instruct 8B 32K V0.1 4bit AWQ |
Repository ๐ค | https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-32k-v0.1-4bit-awq |
Base Model(s) | |
Model Size | 8b |
Required VRAM | 5.8 GB |
Updated | 2024-12-21 |
Maintainer | DiscoResearch |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | de en |
AWQ Quantization | Yes |
Quantization Type | awq|4bit |
Model Architecture | LlamaForCausalLM |
License | llama3 |
Context Length | 65536 |
Model Max Length | 65536 |
Transformers Version | 4.40.2 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|end_of_text|> |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...8B Instruct Gradient 1048K AWQ | 1024K / 5.8 GB | 14 | 0 |
...radient 1048K AWQ 4bit Smashed | 1024K / 5.8 GB | 32 | 1 |
...Instruct 262K AWQ 4bit Smashed | 256K / 5.8 GB | 13 | 4 |
...ta Llama 3 8B Instruct 64K AWQ | 64K / 5.8 GB | 12 | 0 |
Llama 3 8B Instruct AWQ | 8K / 5.8 GB | 79006 | 20 |
Meta Llama 3 8B Instruct AWQ | 8K / 5.8 GB | 1394 | 4 |
Meta Llama 3 8B Instruct AWQ | 8K / 5.8 GB | 1272 | 0 |
Meta Llama 3 8B Instruct AWQ | 8K / 5.8 GB | 112 | 0 |
...eta Llama 3 8B Instruct Hf AWQ | 8K / 5.8 GB | 446 | 8 |
Meta Llama 3 8B Instruct AWQ | 8K / 5.8 GB | 8 | 0 |
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