llama : add Command-R support (#6033)

Information about the Command-R 35B model (128k context) can be found at:
	https://huggingface.co/CohereForAI/c4ai-command-r-v01

Based on the llama2 model with a few changes:

1) New hyper parameter to scale output logits (logit_scale)
2) Uses LayerNorm instead of RMSNorm
3) Transfomer layers have a single shared LayerNorm that feeds into both the
   self-attention and FFN layers in parallel. There is no post-attention LayerNorm.
4) No support for Rotary Position Embeddings (RoPE) scaling
5) No biases used

Find GGUF files here:
	https://huggingface.co/andrewcanis/c4ai-command-r-v01-GGUF

To convert model to GGUF format yourself:

1) Download Command-R Hugging Face safetensors:
	git lfs install
	git clone https://huggingface.co/CohereForAI/c4ai-command-r-v01

2) Run:
	python3 convert-hf-to-gguf.py --outtype f16 ./c4ai-command-r-v01

1 files changed, 15 insertions, 0 deletions

diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py
index 458a641d..4a4facb0 100644
--- a/gguf-py/gguf/constants.py
+++ b/gguf-py/gguf/constants.py
@@ -42,6 +42,7 @@ class Keys:
         EXPERT_COUNT          = "{arch}.expert_count"
         EXPERT_USED_COUNT     = "{arch}.expert_used_count"
         POOLING_TYPE          = "{arch}.pooling_type"
+        LOGIT_SCALE           = "{arch}.logit_scale"
 
     class Attention:
         HEAD_COUNT        = "{arch}.attention.head_count"
@@ -121,6 +122,7 @@ class MODEL_ARCH(IntEnum):
     GEMMA      = auto()
     STARCODER2 = auto()
     MAMBA      = auto()
+    COMMAND_R  = auto()
 
 
 class MODEL_TENSOR(IntEnum):
@@ -187,6 +189,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
     MODEL_ARCH.GEMMA:          "gemma",
     MODEL_ARCH.STARCODER2:     "starcoder2",
     MODEL_ARCH.MAMBA:          "mamba",
+    MODEL_ARCH.COMMAND_R:      "command-r",
 }
 
 TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
@@ -579,6 +582,18 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.SSM_D,
         MODEL_TENSOR.SSM_OUT,
     ],
+    MODEL_ARCH.COMMAND_R: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+    ],
     # TODO
 }