fix: add dequant bf16 repo (#3507) [skip ci]

examples/mistral4/README.md

@@ -6,9 +6,6 @@ Thanks to the team at MistralAI for giving us early access to prepare for this r
 
 ## Getting started
 
-Note: Training this model requires weights in BF16 which we will link to later.
-Users interested in training can convert / descale the existing FP8 weights.
-
 1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
 
 2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage

examples/mistral4/fft-text.yml

@@ -1,4 +1,4 @@
-base_model: mistralai/Mistral-Small-4-119B-2603
+base_model: axolotl-ai-co/Mistral-Small-4-119B-2603-BF16
 
 plugins:
   - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

examples/mistral4/fft-vision.yml

@@ -1,4 +1,4 @@
-base_model: mistralai/Mistral-Small-4-119B-2603
+base_model: axolotl-ai-co/Mistral-Small-4-119B-2603-BF16
 processor_type: AutoProcessor
 
 plugins:

examples/mistral4/qlora-text.yml

@@ -1,4 +1,4 @@
-base_model: mistralai/Mistral-Small-4-119B-2603
+base_model: axolotl-ai-co/Mistral-Small-4-119B-2603-BF16
 
 plugins:
   - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

examples/mistral4/qlora-vision.yml

@@ -1,4 +1,4 @@
-base_model: mistralai/Mistral-Small-4-119B-2603
+base_model: axolotl-ai-co/Mistral-Small-4-119B-2603-BF16
 processor_type: AutoProcessor
 
 plugins: