Text Generation
Transformers
Safetensors
mistral
chat
conversational
text-generation-inference
Inference Endpoints
magnum-v2-123b / README.md
kalomaze's picture
Update README.md
4463bf1 verified
|
raw
history blame
2.22 kB
metadata
license: apache-2.0
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ru
  - zh
  - ja
pipeline_tag: text-generation
tags:
  - chat

image/png This is the sixth in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of Mistral-Large-Instruct-2407.

Prompting

Model has been Instruct tuned with the Mistral formatting. A typical input would look like this:

"""[INST] Hi there! [/INST]Nice to meet you!</s>[INST] Can I ask a question? [/INST]
"""

Credits

This model has been a team effort, and the credits goes to all members of Anthracite.

Training

The training was done for 1.5 epochs. We used 8x AMD Instinct™ MI300X Accelerators for the full-parameter fine-tuning of the model.

In addition to this, we noticed that Mistral Large models seemed much more sensitive to learning rate adjustments than other models:

image/png

We hypothesize this is primarily due to the particularly narrow and low variance weight distributions typical of Mistral derived models regardless of their scale. In the end, we settled on 2e-6 with an effective batch size of 64 (and a packed tokens batch size of 8192; effectively ~500,000 tokens per batch).

We also trained with a weight decay of 0.01 to help further stabilize the loss trajectory and mitigate overfitting.

Built with Axolotl

Safety

...