Autotrain compatible Conversational Endpoints compatible Mixtral Moe Region:us Safetensors Sharded Tensorboard Tensorflow
Functionary Medium V2.4 Parameters and Internals
| LLM Name | Functionary Medium V2.4 |
| Repository | Open on 🤗 |
| Model Size | 46.7b |
| Required VRAM | 93.6 GB |
| Updated | 2024-07-27 |
| Maintainer | meetkai |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32004 |
| Torch Data Type | bfloat16 |
Best Alternatives to Functionary Medium V2.4
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Mixtral 8x7B Instruct V0.1 | 0.6 | 32K / 93.6 GB | 651236 | 3978 |
| Nous Hermes 2 Mixtral 8x7B DPO | 0.5 | 32K / 93.6 GB | 56412 | 403 |
| Mixtral 8x7B V0.1 | 0.5 | 32K / 93.6 GB | 44820 | 1602 |
| Dolphin 2.5 Mixtral 8x7b | 0.4 | 32K / 93.6 GB | 51154 | 1182 |
| ...rkrautLM Mixtral 8x7B Instruct | 0.4 | 32K / 93.6 GB | 52785 | 21 |
| Notux 8x7b V1 | 0.3 | 32K / 93.6 GB | 21 | 164 |
| Karakuri Lm 8x7b Instruct V0.1 | 0.3 | 32K / 93.6 GB | 1114 | 16 |
| Nous Hermes 2 Mixtral 8x7B SFT | 0.3 | 32K / 93.6 GB | 426 | 55 |
| MAmmoTH2 8x7B Plus | 0.3 | 32K / 93.6 GB | 2741 | 12 |
| Karakuri Lm 8x7b Chat V0.1 | 0.3 | 32K / 93.6 GB | 1638 | 18 |
Note: green Score (e.g. "73.2") means that the model is better than meetkai/functionary-medium-v2.4 .
Rank the Functionary Medium V2.4 Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501