Update README.md

README.md

@@ -1,62 +1,54 @@
 ---
-base_model: []
-library_name: transformers
+license: apache-2.0
 tags:
-- mergekit
-- merge
-
+- mixtral
+- dense
+- mistral
+- expert
 ---
-# output-model-directory
-
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
-## Merge Details
-### Merge Method
+# Unmixtraled 22B 8x linear merge
 
-This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
+> [!WARNING]
+> This model outputs gibberish as it was not trained under the dense configuration. Finetuning or merging is needed to make this model useful.
 
-### Models Merged
+This is a 22B Mistral model recycling weights from [mistral-community/Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1). 
+The model was adapted from a Mixtral architecture to a dense Mistral architecture with the same number of layers, attention heads and hidden dimensions.  
+Embeddings, attention, layer norms and LM head weights were taken directly from the 8x22B model, MLP weights are a linear merge of experts 0 to 7 weights.
 
-The following models were included in the merge:
-* /workspace/junk/singlestral5
-* /workspace/junk/singlestral6
-* /workspace/junk/singlestral1
-* /workspace/junk/singlestral3
-* /workspace/junk/singlestral4
-* /workspace/junk/singlestral7
-* /workspace/junk/singlestral0
-* /workspace/junk/singlestral2
+The following named weight correspondance was used:
 
-### Configuration
+| Mistral weight | Mixtral weight               |
+|----------------|------------------------------|
+| `gate_proj`    | `experts.{layer_num}.w1`     |
+| `down_proj`    | `experts.{layer_num}.w2`     |
+| `up_proj`      | `experts.{layer_num}.w3`     |
 
-The following YAML configuration was used to produce this model:
+This mergekit configuration was used to merge the experts:
 
 ```yaml
 models:
-  - model: /workspace/junk/singlestral0
-    parameters:
-        weight: 0.125
-  - model: /workspace/junk/singlestral1
-    parameters:
-        weight: 0.125
-  - model: /workspace/junk/singlestral2
-    parameters:
-        weight: 0.125
-  - model: /workspace/junk/singlestral3
-    parameters:
-        weight: 0.125
-  - model: /workspace/junk/singlestral4
-    parameters:
-        weight: 0.125
-  - model: /workspace/junk/singlestral5
-    parameters:
-        weight: 0.125
-  - model: /workspace/junk/singlestral6
-    parameters:
-        weight: 0.125
-  - model: /workspace/junk/singlestral7
-    parameters:
-        weight: 0.125
+  - model: thomasgauthier/Unmixtraled-22B-v0.1-expert-0
+  - model: thomasgauthier/Unmixtraled-22B-v0.1-expert-1
+  - model: thomasgauthier/Unmixtraled-22B-v0.1-expert-2
+  - model: thomasgauthier/Unmixtraled-22B-v0.1-expert-3
+  - model: thomasgauthier/Unmixtraled-22B-v0.1-expert-4
+  - model: thomasgauthier/Unmixtraled-22B-v0.1-expert-5
+  - model: thomasgauthier/Unmixtraled-22B-v0.1-expert-6
+  - model: thomasgauthier/Unmixtraled-22B-v0.1-expert-7
 merge_method: linear
 dtype: float16
 ```
+
+## Unmixtraled models
+| Expert | Source | Wikitext perplexity |
+|--------|-----------------|---------------------|
+| [Unmixtraled-22B-v0.1-expert-0](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-expert-0) | Mixtral 8x22B embed, attn, layernorm, lm_head + expert 0 MLPs | 696.6932983398438 |
+| [Unmixtraled-22B-v0.1-expert-1](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-expert-1) | Mixtral 8x22B embed, attn, layernorm, lm_head + expert 1 MLPs | 6853.04248046875 |
+| [Unmixtraled-22B-v0.1-expert-2](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-expert-2) | Mixtral 8x22B embed, attn, layernorm, lm_head + expert 2 MLPs | 4689.181640625 |
+| [Unmixtraled-22B-v0.1-expert-3](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-expert-3) | Mixtral 8x22B embed, attn, layernorm, lm_head + expert 3 MLPs | 782.3755493164062 |
+| [Unmixtraled-22B-v0.1-expert-4](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-expert-4) | Mixtral 8x22B embed, attn, layernorm, lm_head + expert 4 MLPs | 2844.943603515625 |
+| [Unmixtraled-22B-v0.1-expert-5](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-expert-5) | Mixtral 8x22B embed, attn, layernorm, lm_head + expert 5 MLPs | 1099.32373046875 |
+| [Unmixtraled-22B-v0.1-expert-6](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-expert-6) | Mixtral 8x22B embed, attn, layernorm, lm_head + expert 6 MLPs | 341.5309753417969 |
+| [Unmixtraled-22B-v0.1-expert-7](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-expert-7) | Mixtral 8x22B embed, attn, layernorm, lm_head + expert 7 MLPs | 2099.63818359375 |
+| [**Unmixtraled-22B-v0.1-lerp**](https://huggingface.co/thomasgauthier/Unmixtraled-22B-v0.1-lerp) | **Mixtral 8x22B embed, attn, layernorm, lm_head + linear merge of expert 0-7 MLPs** | **1873.9874267578125** |