Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Document Mixtral changes to GGUF #646

Merged
merged 4 commits into from
Dec 13, 2023
Merged

Document Mixtral changes to GGUF #646

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a24f606
add new tensor names
ariez-xyz Dec 12, 2023
a5b3a9f
add new keys
ariez-xyz Dec 12, 2023
3de42d8
fix tensor names
ariez-xyz Dec 13, 2023
4c365ce
gguf : change wording a bit
ggerganov Dec 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions docs/gguf.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -285,6 +285,8 @@ In the following, `[llm]` is used to fill in for the name of a specific LLM arch
- `[llm].tensor_data_layout: string`: When a model is converted to GGUF, tensors may be rearranged to improve performance. This key describes the layout of the tensor data. This is not required; if not present, it is assumed to be `reference`.
- `reference`: tensors are laid out in the same order as the original model
- further options can be found for each architecture in their respective sections
- `[llm].expert_count: uint32`: Number of experts in MoE models (optional for non-MoE arches).
- `[llm].expert_used_count: uint32`: Number of experts used during each token token evaluation (optional for non-MoE arches).

#### Attention

Expand Down Expand Up @@ -341,6 +343,8 @@ The following sections describe the metadata for each model architecture. Each k
.swapaxes(1, 2)
.reshape(weights.shape))
```
- `llama.expert_count`
- `llama.expert_used_count`

##### MPT

Expand Down Expand Up @@ -553,6 +557,10 @@ where N signifies the block number a layer belongs to, and where `BB` could be:
- `ffn_up`: Feed-forward network "up" layer
- `ffn_gate`: Feed-forward network "gate" layer
- `ffn_down`: Feed-forward network "down" layer
- `ffn_gate_inp`: Expert-routing layer for the Fee-forward network in MoE models
- `ffn_gate_exp`: Feed-forward network "gate" layer per expert in MoE models
- `ffn_down_exp`: Feed-forward network "down" layer per expert in MoE models
- `ffn_up_exp`: Feed-forward network "up" layer per expert in MoE models

## Version History

Expand Down