Model Type |
| |||||||||
Additional Notes | Join us on Together Discord: https://discord.gg/6ZVDU8tTD4 | |||||||||
Supported Languages |
| |||||||||
Training Details |
| |||||||||
Input Output |
|
LLM Name | Llama 2 7B 32K Instruct |
Repository ๐ค | https://huggingface.co/togethercomputer/Llama-2-7B-32K-Instruct |
Model Size | 7b |
Required VRAM | 13.5 GB |
Updated | 2024-11-09 |
Maintainer | togethercomputer |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
Model Architecture | LlamaForCausalLM |
License | llama2 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.31.0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Llama 2 7B 32K Instruct GGUF | 55 | 1411 | 2 GB |
Llama 2 7B 32K Instruct AWQ | 2 | 23 | 3 GB |
Llama 2 7B 32K Instruct GPTQ | 27 | 43 | 3 GB |
Llama 2 7B 32K Instruct GGML | 8 | 16 | 2 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
... Qwen2.5llamaify 7B V23.1 200K | 195K / 15.2 GB | 2743 | 0 |
Qwen2 7B Instruct Llama | 32K / 15.2 GB | 11 | 3 |
Qwen2 7B Instruct Mistral | 32K / 15.2 GB | 15 | 1 |
AIRIC The Mistral | 32K / 14.4 GB | 724 | 7 |
...ls Vikhr 7B Instruct 0.4 4bits | 32K / 5.2 GB | 5 | 0 |
Vikhr 7B Instruct 0.3 | 32K / 14.6 GB | 32 | 4 |
... Samantha Philosopher 7B Slerp | 32K / 13.4 GB | 14 | 2 |
Vikhr 7B Instruct Merged | 32K / 14.6 GB | 9 | 4 |
Clinical Ehr Prototype 0.1 | 32K / 14.4 GB | 10 | 2 |
...stral 7B Instruct V0.1 Sharded | 32K / 14.4 GB | 1632 | 13 |
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