4-bit Autotrain compatible Awq Base model:brillibits/instruct... Conversational Dataset:databricks/databricks-... Instruct License:apache-2.0 Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow
Instruct Mixtral 8x7B V0.1 Dolly15K AWQ Benchmarks
HF Avg Score: 63.5 vs 86.1 (GPT-4) -26.2%
ARC: 61-36.7%
HellaSwag: 73.6-22.8%
MMLU: 62.4-27.9%
TruthfulQA: 62.25.4%
WinoGrande: 80.9-7.5%
GSM8K: 42.8-53.5%
nn.n% — How the model compares to the GPT-4.
Rank the Instruct Mixtral 8x7B V0.1 Dolly15K AWQ 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! 🌟
Best Alternatives to Instruct Mixtral 8x7B V0.1 Dolly15K AWQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...ixtral Instruct 8x7b Zloss AWQ | 64.2 | 32K / 24.7 GB | 10 | 1 |
| ...utLM Mixtral 8x7B Instruct AWQ | 63.8 | 32K / 24.7 GB | 468 | 2 |
| Mixtral 8x7B Instruct V0.1 AWQ | 63.7 | 32K / 24.7 GB | 1025 | 54 |
| Mixtral Instruct AWQ | — | 32K / 24.7 GB | 14524 | 39 |
| Dolphin 2.7 Mixtral 8x7b AWQ | — | 32K / 24.7 GB | 3985 | 19 |
| Dolphin 2.6 Mixtral 8x7b AWQ | — | 32K / 24.7 GB | 20 | 13 |
| Mixtral 8x7B Instruct V0.1 AWQ | — | 32K / 24.7 GB | 13832 | 11 |
| Dolphin 2.5 Mixtral 8x7b AWQ | — | 32K / 24.7 GB | 8 | 6 |
| ...0.1 LimaRP ZLoss DARE TIES AWQ | — | 32K / 24.7 GB | 288 | 3 |
| ...1 Mixtral 8x7b Instruct V3 AWQ | — | 32K / 24.7 GB | 36 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Instruct_Mixtral-8x7B-v0.1_Dolly15K-AWQ .
Instruct Mixtral 8x7B V0.1 Dolly15K AWQ Parameters and Internals
| LLM Name | Instruct Mixtral 8x7B V0.1 Dolly15K AWQ |
| Repository | Open on 🤗 |
| Model Name | Instruct Mixtral 8X7B V0.1 Dolly15K |
| Model Creator | Brillibits |
| Base Model(s) | |
| Model Size | 6.5b |
| Required VRAM | 24.7 GB |
| Updated | 2024-07-01 |
| Maintainer | TheBloke |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Initializer Range | 0.02 |
| Torch Data Type | float16 |
What open-source LLMs or SLMs are you in search of? 34238 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801