azureFoundry/azureml-restricted/databricks-dbrx-base@5
# Key capabilities ## About this model DBRX is a transformer-based decoder-only large language model (LLM) that was trained using next-token prediction. The training mix used for DBRX contains both natural-language and code examples. ## Key model capabilities - **Inputs:** D
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 71.9%
- Open LLM Leaderboard v2: 16.359%
azureFoundry/azureml-restricted/databricks-dbrx-base@1
# Model Overview DBRX is a [transformer-based](https://www.isattentionallyouneed.com/) decoder-only large language model (LLM) that was trained using next-token prediction. It uses a fine-grained mixture-of-experts (MoE) architecture with 132B total parameters of which 36B param
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-restricted/databricks-dbrx-base@2
# Model Overview DBRX is a [transformer-based](https://www.isattentionallyouneed.com/) decoder-only large language model (LLM) that was trained using next-token prediction. It uses a fine-grained mixture-of-experts (MoE) architecture with 132B total parameters of which 36B param
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-restricted/databricks-dbrx-base@3
# Model Overview DBRX is a [transformer-based](https://www.isattentionallyouneed.com/) decoder-only large language model (LLM) that was trained using next-token prediction. It uses a fine-grained mixture-of-experts (MoE) architecture with 132B total parameters of which 36B param
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-restricted/databricks-dbrx-base@4
# Key capabilities ## About this model DBRX is a transformer-based decoder-only large language model (LLM) that was trained using next-token prediction. The training mix used for DBRX contains both natural-language and code examples. ## Key model capabilities - **Inputs:** D
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-restricted/databricks-dbrx-instruct@6
# Key capabilities ## About this model DBRX is a transformer-based decoder-only large language model (LLM) that was trained using next-token prediction. The training mix used for DBRX contains both natural-language and code examples. ## Key model capabilities These are sever
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 74.47%
- Open LLM Leaderboard v2: 25.199%
azureFoundry/azureml-restricted/databricks-dbrx-instruct@1
# Model Overview DBRX is a [transformer-based](https://www.isattentionallyouneed.com/) decoder-only large language model (LLM) that was trained using next-token prediction. It uses a fine-grained mixture-of-experts (MoE) architecture with 132B total parameters of which 36B param
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-restricted/databricks-dbrx-instruct@2
# Model Overview DBRX is a [transformer-based](https://www.isattentionallyouneed.com/) decoder-only large language model (LLM) that was trained using next-token prediction. It uses a fine-grained mixture-of-experts (MoE) architecture with 132B total parameters of which 36B param
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-restricted/databricks-dbrx-instruct@3
# Model Overview DBRX is a [transformer-based](https://www.isattentionallyouneed.com/) decoder-only large language model (LLM) that was trained using next-token prediction. It uses a fine-grained mixture-of-experts (MoE) architecture with 132B total parameters of which 36B param
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-restricted/databricks-dbrx-instruct@4
# Model Overview DBRX is a [transformer-based](https://www.isattentionallyouneed.com/) decoder-only large language model (LLM) that was trained using next-token prediction. It uses a fine-grained mixture-of-experts (MoE) architecture with 132B total parameters of which 36B param
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-restricted/databricks-dbrx-instruct@5
# Model Overview DBRX is a [transformer-based](https://www.isattentionallyouneed.com/) decoder-only large language model (LLM) that was trained using next-token prediction. It uses a fine-grained mixture-of-experts (MoE) architecture with 132B total parameters of which 36B param
- Input modalities
- text
- Output modalities
- text
huggingface/databricks/dolly-v1-6b
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 6.981%
huggingface/databricks/dolly-v2-12b
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 39.457%
- Open LLM Leaderboard v2: 6.37%
azureFoundry/azureml/databricks-dolly-v2-12b@12
# **Model Details** Databricks' dolly-v2-12b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-12b, Dolly is trained on ~15k instruction/response fine tuning records databricks-
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/databricks-dolly-v2-12b@13
# **Model Details** Databricks' dolly-v2-12b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-12b, Dolly is trained on ~15k instruction/response fine tuning records databricks-
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/databricks-dolly-v2-12b@15
Databricks' `dolly-v2-12b`, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on `pythia-12b`, Dolly is trained on ~15k instruction/response fine tuning records [`databricks-dolly-15k`](htt
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/databricks-dolly-v2-12b@16
Databricks' `dolly-v2-12b`, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on `pythia-12b`, Dolly is trained on ~15k instruction/response fine tuning records [`databricks-dolly-15k`](htt
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/databricks-dolly-v2-12b@17
Databricks' `dolly-v2-12b`, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on `pythia-12b`, Dolly is trained on ~15k instruction/response fine tuning records [`databricks-dolly-15k`](htt
- Input modalities
- text
- Output modalities
- text