Dolphin 2.5 Mixtral 8x7B
Dolphin 2.5 Mixtral 8x7B has model metadata, but missing tracked provider pricing keeps it from being a default production pick.
Use it for
- Teams evaluating coding and classification
- Workloads that can use a 32k context window
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Dolphin
- Released
- 2023-12-18
- Context
- 32k
- Parameters
- 8x7B
- Architecture
- Mixture of Experts
- Knowledge cutoff
- 2023-12
- Specialization
- general
- Training
- finetuned
No tracked provider token pricing is available yet.
About
The Dolphin 2.5 Mixtral 8x7B is a sophisticated large language model designed primarily for coding tasks, known for its proficiency across diverse programming languages including Kotlin. It utilizes the Mixtral-8x7b architecture and has been fine-tuned on datasets like Dolphin-Coder and MagiCoder, employing qLoRA and Axolotl during training. Featuring a 16k context window for fine-tuning and a base context window of 32k, it offers powerful yet uncensored capabilities, allowing it to handle a wide range of prompts, albeit this introduces ethical considerations. The model is available in various formats on platforms like Hugging Face, catering to different needs with options such as GGUF and GPTQ quantization levels. Despite its strengths, users should be mindful of ethical sensitivities and implement alignment measures when deploying it publicly.
Dolphin 2.5 Mixtral 8x7B is a model in the Dolphin family. The structured metadata tracks a 32k-token context window. This page tracks provider routes through Together AI, with the cheapest tracked route listed at $0.6 input and $0.6 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 44.8, HellaSwag 89.0, and HumanEval 67.9.
Top use-case fit: coding, agents, and build tasks
Coding
1 relevant benchmark in the decision map.
Classification
2 relevant benchmarks in the decision map.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
Benchmark scores(4)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 44.8 | diamond | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
| HellaSwag | 89.0 | 10-shot | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
| HumanEval | 67.9 | pass@1 | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
| Massive Multitask Language Understanding | 71.2 | 5-shot | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
Migration checks
No linked migration route is available for this model yet.