Update README.md
This commit is contained in:
35
README.md
35
README.md
@@ -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.
|
||||
|
||||
- [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?
|
||||
|
||||
@@ -43,21 +43,18 @@ https://erichartford.com/uncensored-models
|
||||
|
||||
## 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|>
|
||||
|
||||
Cutting Knowledge Date: December 2023
|
||||
Today Date: 26 Jul 2024
|
||||
|
||||
system-prompt<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
|
||||
user-prompt<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
assistant-prompt<|eot_id|>
|
||||
<|system|>
|
||||
system-prompt
|
||||
<|user|>
|
||||
user-prompt
|
||||
<|assistant|>
|
||||
assistant-prompt<|end_of_text|>
|
||||
```
|
||||
|
||||
|
||||
## 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.
|
||||
@@ -88,10 +85,10 @@ See the [documentation](https://docs.vllm.ai/en/latest/) for more information.
|
||||
|
||||
## Evals
|
||||
|
||||
MMLU = 0.626900
|
||||
MMLU_PROFESSIONAL = 0.610200
|
||||
MMLU_COLLEGE = 0.529400
|
||||
MMLU_HIGH_SCHOOL = 0.691600
|
||||
MMLU_OTHER = 0.663700
|
||||
IFEVAL = 0.608100
|
||||
Dolphin-refusals = 95.96% pass rate on 4.5k commonly refused prompts
|
||||
MMLU = 0.626900
|
||||
MMLU_PROFESSIONAL = 0.610200
|
||||
MMLU_COLLEGE = 0.529400
|
||||
MMLU_HIGH_SCHOOL = 0.691600
|
||||
MMLU_OTHER = 0.663700
|
||||
IFEVAL = 0.608100
|
||||
Dolphin-refusals = 95.96% pass rate on 4.5k commonly refused prompts
|
||||
Reference in New Issue
Block a user