lucataco / dolphin-2.2.1-mistral-7b

Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)

  • Public
  • 35.3K runs
  • L40S
  • GitHub
  • Paper
  • License

Input

*string
Shift + Return to add a new line
integer

The maximum number of tokens the model should generate as output.

Default: 512

number

The value used to modulate the next token probabilities.

Default: 0.8

number

A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).

Default: 0.95

integer

The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).

Default: 50

number

Presence penalty

Default: 0

number

Frequency penalty

Default: 0

string
Shift + Return to add a new line

The template used to format the prompt. The input prompt is inserted into the template using the `{prompt}` placeholder.

Default: "<|im_start|>system\nYou are Dolphin, a helpful AI assistant.\n<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"

Output

Step 1: Building Trust The first step in training a dolphin is to gain its trust. Spend time in the water with the dolphin and allow it to become familiar with your presence. Be calm and gentle, as dolphins are highly intuitive and can sense fear or aggression. Step 2: Establishing Communication Before you can train the dolphin, you need to establish a way of communicating with it. This can be done through hand signals or vocal commands, depending on your preference. Practice these signals or commands in the presence of the dolphin to familiarize it with your intentions. Step 3: Teaching Basic Commands Start with basic commands such as "come," "stay," and "go." Use the communication method you established in step 2 to teach these commands. Once the dolphin understands these basic commands, move on to more advanced commands. Step 4: Rewarding Good Behavior Positive reinforcement is key when training a dolphin. When the dolphin successfully completes a command, reward it with a treat or verbal praise. This will encourage the dolphin to continue learning and obeying your commands. Step 5: Patience and Consistency Training a dolphin takes time and patience. Be consistent in your training and don't expect immediate results. Gradually increase the complexity of the commands as the dolphin becomes more familiar with the training process. Step 6: Maintaining the Relationship Once the dolphin is trained, it's important to maintain the relationship by continuing to spend time with it and reinforcing the commands. This will help ensure that the dolphin continues to obey your commands and respect your authority.
Generated in

Run time and cost

This model costs approximately $0.0051 to run on Replicate, or 196 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 6 seconds. The predict time for this model varies significantly based on the inputs.

Readme

About

Dolphin 2.2.1 🐬 https://erichartford.com/dolphin

Dolphin-2.1-mistral-7b’s training was sponsored by a16z.

This is a checkpoint release, to fix overfit training. ie, it was responding with CoT even when it was not requested, and also it was too compliant even when the request made no sense. This one should be better.