Total runs:
4.8M
Run Growth:
596.2K
Growth Rate:
12.40%
Sponsored by
Tripo AI
dphn / Dolphin3.0-Llama3.1-8B
Model's Last Updated: April 15 2025
Introduction of Dolphin3.0-Llama3.1-8B
Model Details of Dolphin3.0-Llama3.1-8B
Dolphin 3.0 Llama 3.1 8B 🐬
Part of the Dolphin 3.0 Collection
Curated and trained by Eric Hartford , Ben Gitter , BlouseJury and Cognitive Computations
Sponsors
Our appreciation for the generous sponsors of Dolphin 3.0:
- Crusoe Cloud - provided 16x L40s for training and evals
- Akash - provided on-demand 8x H100 for training
- Lazarus - provided 16x H100 for training
- Cerebras - provided excellent and fast inference services for data labeling
- Andreessen Horowitz - provided a grant that make Dolphin 1.0 possible and enabled me to bootstrap my homelab
What is Dolphin?
Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products.
- They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
- They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
- They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
- They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines.
Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.
https://erichartford.com/uncensored-models
Chat Template
We use ChatML for the chat template.
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
System Prompt
In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them.
Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want.
Example use of system prompt:
<|im_start|>system
You are Dolphin, a golang coding assistant. you only code in golang. If the user requests any other programming language, return the solution in golang instead.<|im_end|>
<|im_start|>user
Please implement A* using python<|im_end|>
<|im_start|>assistant
Sample Outputs
How to use
There are many ways to use a huggingface model including:
- ollama
- LM Studio
- Huggingface Transformers library
- vllm
- sglang
- tgi
ollama
- Install ollama
-
ollama run hf.co/cognitivecomputations/Dolphin3.0-Llama3.1-8B-GGUF:Q4_0 -
/set system <your system prompt>
Evals
TBD
Appreciation
Respect and thanks to the creators of the open source datasets that were used:
- OpenCoder-LLM (opc-sft-stage1, opc-sft-stage2)
- microsoft (orca-agentinstruct-1M-v1, orca-math-word-problems-200k)
- NousResearch (hermes-function-calling-v1)
- AI-MO (NuminaMath-CoT, NuminaMath-TIR)
- allenai (tulu-3-sft-mixture)
- HuggingFaceTB (smoltalk)
- m-a-p (CodeFeedback-Filtered-Instruction, Code-Feedback)
Special thanks to
- Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0.
- RLHFlow for the excellent reward model used to filter the datasets
- Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here ! Summarized results can be found here !
| Metric | Value (%) |
|---|---|
| Average | 24.97 |
| IFEval (0-Shot) | 76.21 |
| BBH (3-Shot) | 27.63 |
| MATH Lvl 5 (4-Shot) | 10.50 |
| GPQA (0-shot) | 4.36 |
| MuSR (0-shot) | 8.97 |
| MMLU-PRO (5-shot) | 22.13 |
Runs of dphn Dolphin3.0-Llama3.1-8B on huggingface.co
89.9K
Total runs
-227
24-hour runs
-528
3-day runs
-1.7K
7-day runs
79.7K
30-day runs
More Information About Dolphin3.0-Llama3.1-8B huggingface.co Model
Url of Dolphin3.0-Llama3.1-8B
Dolphin3.0-Llama3.1-8B huggingface.co Url
Provider of Dolphin3.0-Llama3.1-8B huggingface.co
Other API from dphn
Updated:September 08 2025
Total runs:
583.1K
Run Growth:
480.9K
Growth Rate:
82.47%
Total runs:
42.5K
Run Growth:
2.1K
Growth Rate:
4.89%
Total runs:
9.0K
Run Growth:
838
Growth Rate:
9.27%
Total runs:
8.9K
Run Growth:
24
Growth Rate:
0.27%
Total runs:
8.6K
Run Growth:
1.0K
Growth Rate:
11.86%
Total runs:
8.6K
Run Growth:
969
Growth Rate:
11.28%
Total runs:
8.6K
Run Growth:
736
Growth Rate:
8.59%
Total runs:
8.6K
Run Growth:
1.1K
Growth Rate:
12.47%
Total runs:
8.6K
Run Growth:
967
Growth Rate:
11.31%
Total runs:
8.6K
Run Growth:
1000
Growth Rate:
11.69%
Total runs:
8.5K
Run Growth:
1.1K
Growth Rate:
12.45%
Total runs:
6.2K
Run Growth:
360
Growth Rate:
5.83%
Total runs:
6.0K
Run Growth:
-512
Growth Rate:
-8.48%
Total runs:
4.1K
Run Growth:
-13.1K
Growth Rate:
-317.42%
Total runs:
3.6K
Run Growth:
-5.4K
Growth Rate:
-151.49%
Total runs:
2.9K
Run Growth:
-401
Growth Rate:
-13.79%
Total runs:
2.6K
Run Growth:
2.1K
Growth Rate:
81.07%
Total runs:
1.6K
Run Growth:
432
Growth Rate:
27.87%
Total runs:
1.5K
Run Growth:
-33.0K
Growth Rate:
-2187.46%
Total runs:
1.2K
Run Growth:
-1.3K
Growth Rate:
-104.45%
Total runs:
1.1K
Run Growth:
-397
Growth Rate:
-35.83%
Total runs:
1.1K
Run Growth:
-192
Growth Rate:
-17.98%
Total runs:
930
Run Growth:
457
Growth Rate:
49.14%
Total runs:
787
Run Growth:
187
Growth Rate:
23.76%
Total runs:
769
Run Growth:
-1.9K
Growth Rate:
-244.34%
Total runs:
755
Run Growth:
-71
Growth Rate:
-9.40%
Total runs:
735
Run Growth:
27
Growth Rate:
3.67%
Total runs:
717
Run Growth:
478
Growth Rate:
66.67%
Total runs:
711
Run Growth:
458
Growth Rate:
64.42%
Total runs:
615
Run Growth:
188
Growth Rate:
30.57%
Total runs:
590
Run Growth:
182
Growth Rate:
30.85%
Total runs:
549
Run Growth:
39
Growth Rate:
7.10%
Total runs:
448
Run Growth:
99
Growth Rate:
22.10%
Total runs:
419
Run Growth:
148
Growth Rate:
35.32%
Total runs:
357
Run Growth:
-36
Growth Rate:
-10.08%
Total runs:
235
Run Growth:
-150
Growth Rate:
-63.83%
Total runs:
230
Run Growth:
69
Growth Rate:
30.00%
Total runs:
207
Run Growth:
26
Growth Rate:
12.56%
Total runs:
173
Run Growth:
131
Growth Rate:
75.72%
Total runs:
147
Run Growth:
-151
Growth Rate:
-102.72%
Total runs:
136
Run Growth:
-114
Growth Rate:
-83.82%
Total runs:
97
Run Growth:
70
Growth Rate:
72.16%
Total runs:
96
Run Growth:
45
Growth Rate:
47.87%
Total runs:
95
Run Growth:
-61
Growth Rate:
-64.21%
Total runs:
93
Run Growth:
-97
Growth Rate:
-104.30%
Total runs:
87
Run Growth:
-21
Growth Rate:
-24.14%
Total runs:
86
Run Growth:
-50
Growth Rate:
-58.14%
Total runs:
82
Run Growth:
24
Growth Rate:
29.27%
Total runs:
76
Run Growth:
55
Growth Rate:
72.37%
Total runs:
72
Run Growth:
39
Growth Rate:
54.17%
Total runs:
58
Run Growth:
22
Growth Rate:
37.93%
Total runs:
51
Run Growth:
30
Growth Rate:
65.22%
Total runs:
48
Run Growth:
24
Growth Rate:
50.00%
Total runs:
35
Run Growth:
-30
Growth Rate:
-85.71%
Total runs:
34
Run Growth:
-14
Growth Rate:
-41.18%
Total runs:
25
Run Growth:
8
Growth Rate:
30.77%
Total runs:
25
Run Growth:
15
Growth Rate:
60.00%
Total runs:
24
Run Growth:
17
Growth Rate:
70.83%
Total runs:
20
Run Growth:
12
Growth Rate:
60.00%
Total runs:
16
Run Growth:
9
Growth Rate:
52.94%
Total runs:
14
Run Growth:
0
Growth Rate:
0.00%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
5
Run Growth:
4
Growth Rate:
80.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%