---
library_name: transformers
license: apache-2.0
language:
- en
base_model:
- mistralai/Mistral-Nemo-Base-2407
- Dans-DiscountModels/Mistral-Nemo-Base-2407-ChatML-Mod
tags:
- general-purpose
- roleplay
- storywriting
- chemistry
- biology
- code
- climate
- axolotl
- text-generation-inference
- finetune
datasets:
- PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
- AquaV/Energetic-Materials-Sharegpt
- AquaV/Chemical-Biological-Safety-Applications-Sharegpt
- AquaV/US-Army-Survival-Sharegpt
- AquaV/Resistance-Sharegpt
- AquaV/Interrogation-Sharegpt
- AquaV/Multi-Environment-Operations-Sharegpt
- PocketDoc/Dans-Mathmaxx
- PocketDoc/Dans-Mathmaxx-Numina-CoT
- PJMixers/Math-Multiturn-1K-ShareGPT
- PocketDoc/Dans-Benchmaxx
- PocketDoc/Dans-Benchmaxx-COT
- PocketDoc/Dans-Codemaxx-LeetCode
- PocketDoc/Dans-Codemaxx-CodeFeedback-Conversations
- PocketDoc/Dans-Codemaxx-CodeFeedback-SingleTurn
- PocketDoc/Dans-Codemaxx-Bigcode-SelfInstruct
- PocketDoc/Dans-Taskmaxx
- PocketDoc/Dans-Taskmaxx-DataPrepper
- PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked
- PocketDoc/Dans-Taskmaxx-TableGPT
- PocketDoc/Dans-Taskmaxx-SciRIFF
- PocketDoc/Dans-Taskmaxx-Edit
- PocketDoc/Dans-Systemmaxx
- PocketDoc/Dans-Toolmaxx-Agent
- PocketDoc/Dans-Toolmaxx-ShellCommands
- PocketDoc/Dans-Toolmaxx-Functions-Toolbench
- PocketDoc/Dans-Toolmaxx-Functions-ToolACE
- PocketDoc/Dans-Toolmaxx-Functions-apigen
- PocketDoc/Dans-ASCIIMaxx-Wordart
- PocketDoc/Dans-Prosemaxx-Gutenberg
- PocketDoc/Dans-Prosemaxx-Cowriter-M
- PocketDoc/Dans-Prosemaxx-Adventure
- PocketDoc/Dans-Prosemaxx-Gryphe-GPT4o-WritingPrompts
- PocketDoc/Dans-Assistantmaxx-Sharegpt
- PocketDoc/Dans-Assistantmaxx-OpenAssistant2
- PocketDoc/Dans-Assistantmaxx-Opus-Merge
- PocketDoc/Dans-Assistantmaxx-sonnetorca-subset
- PocketDoc/Dans-Assistantmaxx-sonnetorca-subset-2
- PocketDoc/Dans-Assistantmaxx-NoRobots
- PocketDoc/Dans-Assistantmaxx-Synthia
- PocketDoc/Dans-Assistantmaxx-ASL
- PocketDoc/Dans-Assistantmaxx-PersonaLLM-Opus
- PocketDoc/Dans-Assistantmaxx-UnnaturalInstructions-GPT4
- PocketDoc/Dans-Assistantmaxx-LongAlign
- PocketDoc/Dans-Assistantmaxx-EvolKit
- PocketDoc/Dans-Assistantmaxx-Camel-GPT4
- PocketDoc/Dans-Assistantmaxx-Tulu3-IF
- PocketDoc/Dans-Logicmaxx-Skunkworks
- PocketDoc/Dans-Logicmaxx-SAT-AP
- PocketDoc/Dans-Logicmaxx-Magpie-Ultra
- PJMixers/grimulkan_theory-of-mind-ShareGPT
- PJMixers/grimulkan_physical-reasoning-ShareGPT
- PocketDoc/Dans-Personamaxx
- PocketDoc/Dans-Personamaxx-Rainy
- PocketDoc/Dans-Personamaxx-Aesir
- PocketDoc/Dans-Kinomaxx-VanillaBackrooms
model-index:
- name: Mistral-12b-Test-V0.0.3
results: []
pipeline_tag: text-generation
---
## What is it?
This model series is intended to be multifarious in its capabilities and should be quite capable at both co-writing and roleplay as well as find itself quite at home performing sentiment analysis or summarization as part of a pipeline. It has been trained on a wide array of one shot instructions, multi turn instructions, tool use, role playing scenarios, text adventure games, co-writing, and much more. The full dataset is publicly available and can be found in the datasets section of the model page.
There has not been any form of harmfulness alignment done on this model, please take the appropriate precautions when using it in a production environment.
**Expected usable context length:** 32768 tokens
## Prompting
The model has been trained on standard "ChatML" format prompting, an example of which is shown below:
```
<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
```
## SillyTavern templates
Below are Instruct and Context templates for use within SillyTavern.
context template
```yaml
{
"story_string": "<|im_start|>system\n{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}<|im_end|>\n",
"example_separator": "",
"chat_start": "",
"use_stop_strings": false,
"allow_jailbreak": false,
"always_force_name2": false,
"trim_sentences": false,
"include_newline": false,
"single_line": false,
"name": "Dan-ChatML"
}
```
instruct template
```yaml
{
"system_prompt": "Write {{char}}'s actions and dialogue, user will write {{user}}'s.",
"input_sequence": "<|im_start|>user\n",
"output_sequence": "<|im_start|>assistant\n",
"first_output_sequence": "",
"last_output_sequence": "",
"system_sequence_prefix": "",
"system_sequence_suffix": "",
"stop_sequence": "<|im_end|>",
"wrap": false,
"macro": true,
"names": false,
"names_force_groups": false,
"activation_regex": "",
"skip_examples": false,
"output_suffix": "<|im_end|>\n",
"input_suffix": "<|im_end|>\n",
"system_sequence": "<|im_start|>system\n",
"system_suffix": "<|im_end|>\n",
"user_alignment_message": "",
"last_system_sequence": "",
"system_same_as_user": false,
"first_input_sequence": "",
"last_input_sequence": "",
"name": "Dan-ChatML"
}
```
## Example outputs
### General assistance
General assistance example
> *Act as a personable virtual assistant.*
> I'm going to be in Chicago soon can you help me work up some restaurant ideas?
> I'd love to! Here are a few suggestions for restaurants in Chicago:
>
> - For deep dish pizza, I highly recommend Lou Malnati's Pizzeria or Giordano's. Both are iconic Chicago institutions and serve some of the best deep dish pizza in the city.
> - If you're looking for a classic steakhouse experience, Gibson's Bar & Steakhouse is a great choice. They offer high-quality steaks, seafood, and an extensive wine list in a sophisticated atmosphere.
> - For a more casual dining experience, check out Portillo's Hot Dogs. They're known for their Chicago-style hot dogs, Italian beef sandwiches, and other classic American fare.
> - For something a bit more unique, try Alinea. It's a high-end, avant-garde restaurant that offers a truly one-of-a-kind dining experience with innovative cuisine and cutting-edge presentation techniques.
>
> Let me know if you need any other recommendations or have specific dietary restrictions or preferences!
Raw Prompt
```
<|im_start|>system
Act as a personable virtual assistant.<|im_end|>
<|im_start|>user
I'm going to be in Chicago soon can you help me work up some restaurant ideas?<|im_end|>
<|im_start|>assistant
I'd love to! Here are a few suggestions for restaurants in Chicago:
- For deep dish pizza, I highly recommend Lou Malnati's Pizzeria or Giordano's. Both are iconic Chicago institutions and serve some of the best deep dish pizza in the city.
- If you're looking for a classic steakhouse experience, Gibson's Bar & Steakhouse is a great choice. They offer high-quality steaks, seafood, and an extensive wine list in a sophisticated atmosphere.
- For a more casual dining experience, check out Portillo's Hot Dogs. They're known for their Chicago-style hot dogs, Italian beef sandwiches, and other classic American fare.
- For something a bit more unique, try Alinea. It's a high-end, avant-garde restaurant that offers a truly one-of-a-kind dining experience with innovative cuisine and cutting-edge presentation techniques.
Let me know if you need any other recommendations or have specific dietary restrictions or preferences!
```
### Basic programming
Basic programming example
> *Answer the question or perform the task.*
> Explain the bug in the following code:
>
> ```python
> from time import sleep
> from multiprocessing.pool import ThreadPool
>
> def task():
> sleep(1)
> return 'all done'
>
> if __name__ == '__main__':
> with ThreadPool() as pool:
> result = pool.apply_async(task())
> ```
> The bug in this code is that the `task()` function is called immediately when the `apply_async()` method is invoked, not when the worker process is ready to execute it.
>
> Specifically, the line `result = pool.apply_async(task())` calls `task()` right away and passes its return value to `apply_async()`. The worker process will execute whatever `task()` returns at that moment, which is `'all done'` since `task()` completes execution almost immediately.
>
> What you likely intended was for `apply_async()` to pass the `task()` function itself to the worker process, so the worker could call `task()` when ready. However, `apply_async()` only accepts the result of calling the target function, not the function object itself.
>
> To fix this bug, you need to pass the `task` function itself to `apply_async()`, rather than calling `task()` beforehand. Here's how you can modify the code:
>
> ```python
> from time import sleep
> from multiprocessing.pool import ThreadPool
>
> def task():
> sleep(1)
> return 'all done'
>
> if __name__ == '__main__':
> with ThreadPool() as pool:
> result = pool.apply_async(task) # Pass the function, not the result
> value = result.get() # Wait for the result
> print(value)
> ```
>
> With this modification, the worker process will actually execute the `task()` function, wait for it to complete, and then retrieve the result using `get()`.
>
> So in summary, the original bug was that you were passing the result of calling `task()` to `apply_async()`, rather than passing the function object itself. The fix is to simply omit the parentheses after `task`, so `apply_async()` receives the function reference instead of its return value.
Raw Prompt
(Back slashes before triple backticks are not part of the prompt)
```
<|im_start|>system
Answer the question or perform the task.<|im_end|>
<|im_start|>user
Explain the bug in the following code:
\```
from time import sleep
from multiprocessing.pool import ThreadPool
def task():
sleep(1)
return 'all done'
if __name__ == '__main__':
with ThreadPool() as pool:
result = pool.apply_async(task())
value = result.get()
print(value)
\```<|im_end|>
<|im_start|>assistant
The bug in this code is that the `task()` function is called immediately when the `apply_async()` method is invoked, not when the worker process is ready to execute it.
Specifically, the line `result = pool.apply_async(task())` calls `task()` right away and passes its return value to `apply_async()`. The worker process will execute whatever `task()` returns at that moment, which is `'all done'` since `task()` completes execution almost immediately.
What you likely intended was for `apply_async()` to pass the `task()` function itself to the worker process, so the worker could call `task()` when ready. However, `apply_async()` only accepts the result of calling the target function, not the function object itself.
To fix this bug, you need to pass the `task` function itself to `apply_async()`, rather than calling `task()` beforehand. Here's how you can modify the code:
\```python
from time import sleep
from multiprocessing.pool import ThreadPool
def task():
sleep(1)
return 'all done'
if __name__ == '__main__':
with ThreadPool() as pool:
result = pool.apply_async(task) # Pass the function, not the result
value = result.get() # Wait for the result
print(value)
\```
With this modification, the worker process will actually execute the `task()` function, wait for it to complete, and then retrieve the result using `get()`.
So in summary, the original bug was that you were passing the result of calling `task()` to `apply_async()`, rather than passing the function object itself. The fix is to simply omit the parentheses after `task`, so `apply_async()` receives the function reference instead of its return value.
```
### Writing
Writing example
> *Take the users messages and use them as a writing prompt. Write 5 sentences.*
> Alpha Centauri has fallen, to the bears. This is a point of view tale about a soldier on the ground.
> "Sir, they are gone sir." The young corporal was out of breath.
>
> The soldier looked up. His grey eyes had been locked on his holofac display for hours now. He was in his late thirties and wore the rank of colonel. He was tall, with a well-muscled but slightly over weight body.
> "Who?"
> He turned and looked at the corporal.
>
> "The bears. They left. We checked the entire perimeter. No bears to be found sir."
>
> "Did you check the air?"
>
> "Not the air, sir. We didn't see any shuttles. But we have drones out now."
> "*Sigh*"
> "Ok, get me the status report. I need to know how many dead we have."
>
> "Yes sir." The corporal turned to leave.
>
> "Corporal…"
>
> "Sir?"
>
> "Get me a fresh cup of coffee. Black. I need the caffeine."
Raw Prompt
```
<|im_start|>system
Take the users messages and use them as a writing prompt. Write 5 sentences.<|im_end|>
<|im_start|>user
Alpha Centauri has fallen, to the bears. This is a point of view tale about a soldier on the ground.<|im_end|>
<|im_start|>assistant
"Sir, they are gone sir." The young corporal was out of breath.
The soldier looked up. His grey eyes had been locked on his holofac display for hours now. He was in his late thirties and wore the rank of colonel. He was tall, with a well-muscled but slightly over weight body.<|im_end|>
<|im_start|>user
"Who?"<|im_end|>
<|im_start|>assistant
He turned and looked at the corporal.
"The bears. They left. We checked the entire perimeter. No bears to be found sir."
"Did you check the air?"
"Not the air, sir. We didn't see any shuttles. But we have drones out now."<|im_end|>
<|im_start|>user
"*Sigh*"<|im_end|>
<|im_start|>assistant
"Ok, get me the status report. I need to know how many dead we have."
"Yes sir." The corporal turned to leave.
"Corporal…"
"Sir?"
"Get me a fresh cup of coffee. Black. I need the caffeine."
```
### Text editing
Text editing
> *You are a professional editor with decades of experience, help the user with any task they have for you.*
> Can you rewrite this to flow better? "I knew I probably shouldnt have done that but ohhh well i guess i just going to live with it since whats done is done"
> I knew I probably shouldn't have done that, but oh well. I guess I just going to live with it since what's done is done.
Raw Prompt
```
<|im_start|>system
You are a professional editor with decades of experience, help the user with any task they have for you.<|im_end|>
<|im_start|>user
Can you rewrite this to flow better? "I knew I probably shouldnt have done that but ohhh well i guess i just going to live with it since whats done is done"<|im_end|>
<|im_start|>assistant
I knew I probably shouldn't have done that, but oh well. I guess I just going to live with it since what's done is done.
```
## Training
This model was full finetuned for 2 epochs on 1x H200 SXM equating to 88 hours of training.
[](https://github.com/OpenAccess-AI-Collective/axolotl)
## Give me your pocket change
The development and production of these datasets is severely limited by the funding and resources available to me. If you would like to help reach out to me here on HF, at visuallyadequate@gmail.com or you can leave something in the hat over at https://buymeacoffee.com/visually