Autotrain compatible Conversational Dataset:databricks/databricks-... Endpoints compatible Instruct License:apache-2.0 Mixtral Moe Region:us Safetensors Sharded Tensorflow
Rank the Instruct Mixtral 8x7B V0.1 Dolly15K 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! 🌟
Quantized Models of the Instruct Mixtral 8x7B V0.1 Dolly15K
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| ...ixtral 8x7B V0.1 Dolly15K GGUF | 3 | 227 | 15 GB |
| ...ixtral 8x7B V0.1 Dolly15K GPTQ | 2 | 6 | 23 GB |
| ...Mixtral 8x7B V0.1 Dolly15K AWQ | 1 | 6 | 24 GB |
Best Alternatives to Instruct Mixtral 8x7B V0.1 Dolly15K
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Mixtral 8x7B Instruct V0.1 | 77.75 | 32K / 93.6 GB | 501288 | 3937 |
| ...lQA Mixtral 8x7B Instruct V0.1 | — | 32K / 43.3 GB | 9 | 2 |
| Mixtral 8x7B Instruct V0.1 FP8 | — | 32K / 47.1 GB | 226 | 1 |
| ...tral 8x7B Instruct V0.1 FP8 V2 | — | 32K / 47.1 GB | 112 | 0 |
| ...tral 8x7B Instruct V0.1 FP8 V3 | — | 32K / 47.1 GB | 35 | 0 |
| ...tral 8x7B Instruct V0.1 FP8 V1 | — | 32K / 47.1 GB | 7 | 0 |
| Mixtral Instruct ITR 8x7B | — | 32K / 91.4 GB | 1 | 1 |
| Maid Yuzu V8 Alter | — | 32K / 91.7 GB | 1 | 2 |
| Merge Mixtral Prometheus 8x7B | — | 32K / 91.9 GB | 216 | 1 |
| ...ELT Mixtral 8x7B Instruct V0.1 | — | 32K / 92 GB | 1 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Brillibits/Instruct_Mixtral-8x7B-v0.1_Dolly15K .
Instruct Mixtral 8x7B V0.1 Dolly15K Parameters and Internals
| LLM Name | Instruct Mixtral 8x7B V0.1 Dolly15K |
| Repository | Open on 🤗 |
| Model Size | 46.7b |
| Required VRAM | 93.6 GB |
| Updated | 2024-07-04 |
| Maintainer | Brillibits |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Initializer Range | 0.02 |
| Torch Data Type | bfloat16 |
What open-source LLMs or SLMs are you in search of? 33742 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801