dphn/Dolphin-X1-8B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Dolphin
2025-10-13 16:58:57 +00:00
committed by system
parent 7e3acb98a2
commit b105f402ba
1 changed files with 16 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
README.md
View File

@@ -23,7 +23,7 @@ Our appreciation for the generous sponsors of Dolphin:
- [Lium](https://lium.io) - provided on-demand 8x H200s for testing and evaluation. - [Lium](https://lium.io) - provided on-demand 8x H200s for testing and evaluation.
- [Andreessen Horowitz](https://a16z.com/) - provided a [grant](https://a16z.com/supporting-the-open-source-ai-community/) that make Dolphin 1.0 possible and enabled us to bootstrap our lab - [Andreessen Horowitz](https://a16z.com/) - provided a [grant](https://a16z.com/supporting-the-open-source-ai-community/) that make Dolphin 1.0 possible and enabled me to bootstrap my homelab
## What is Dolphin X1 8B? ## What is Dolphin X1 8B?
@@ -43,21 +43,18 @@ https://erichartford.com/uncensored-models
## Chat Template ## Chat Template
We maintained the default Llama-3 chat template for this model. A typical input would look like this We maintained the default Tulu chat template for this model. A typical input would look like this
``` ```
<|begin_of_text|><|start_header_id|>system<|end_header_id|> <|system|>
system-prompt
Cutting Knowledge Date: December 2023 <|user|>
Today Date: 26 Jul 2024 user-prompt
<|assistant|>
system-prompt<|eot_id|><|start_header_id|>user<|end_header_id|> assistant-prompt<|end_of_text|>
user-prompt<|eot_id|><|start_header_id|>assistant<|end_header_id|>
assistant-prompt<|eot_id|>
``` ```
## System Prompt ## 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. 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.
@@ -88,10 +85,10 @@ See the [documentation](https://docs.vllm.ai/en/latest/) for more information.
## Evals ## Evals
MMLU = 0.626900 MMLU = 0.626900
MMLU_PROFESSIONAL = 0.610200 MMLU_PROFESSIONAL = 0.610200
MMLU_COLLEGE = 0.529400 MMLU_COLLEGE = 0.529400
MMLU_HIGH_SCHOOL = 0.691600 MMLU_HIGH_SCHOOL = 0.691600
MMLU_OTHER = 0.663700 MMLU_OTHER = 0.663700
IFEVAL = 0.608100 IFEVAL = 0.608100
Dolphin-refusals = 95.96% pass rate on 4.5k commonly refused prompts Dolphin-refusals = 95.96% pass rate on 4.5k commonly refused prompts