LLM Name | Llama 3 8B Instruct Coder |
Repository | Open on ๐ค |
Base Model(s) | |
Model Size | 8b |
Required VRAM | 16.1 GB |
Updated | 2024-07-27 |
Maintainer | rombodawg |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.40.1 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|end_of_text|> |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...B Instruct Gradient 1048K 4bit | 0.2 | 1024K / 4.5 GB | 13 | 2 |
...B Instruct Gradient 1048K 8bit | 0.2 | 1024K / 8.6 GB | 16 | 1 |
...truct Gradient 1048K Bpw6 EXL2 | 0.2 | 1024K / 6.7 GB | 11 | 2 |
...truct Gradient 1048K Bpw5 EXL2 | 0.2 | 1024K / 5.8 GB | 6 | 0 |
Llama 3 8B Instruct 1048K 4bit | 0.2 | 1024K / 4.5 GB | 29 | 25 |
Llama 3 8B Instruct 1048K 8bit | 0.2 | 1024K / 8.6 GB | 12 | 16 |
... Gradient 1048K 8.0bpw H8 EXL2 | 0.2 | 1024K / 8.6 GB | 19 | 3 |
...ct Gradient 1048K Bpw2.25 EXL2 | 0.2 | 1024K / 3.4 GB | 7 | 1 |
...B Instruct 262k V2 EXL2 8.0bpw | 0.2 | 256K / 8.4 GB | 40 | 0 |
Llama 3 8B Instruct 262K 2bit | 0.2 | 256K / 2.5 GB | 10 | 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