Added llama.cpp GGUF for Cohere's Command-R model

No quantization. Uses original F16 precision.

Note: Hugging face does not support uploading files larger than 50GB so
I uploaded the GGUF as 2 split files.

To join the files, run the following on Linux and macOS:
cat c4ai-command-r-v01-f16.gguf-split-* > c4ai-command-r-v01-f16.gguf
Then you can remove the split files to save space:
rm c4ai-command-r-v01-f16.gguf-split-*

Expected model parameters:
llama_model_loader: - kv 0: general.architecture str = command-r
llama_model_loader: - kv 1: general.name str = 9fe64d67d13873f218cb05083b6fc2faab2d034a
llama_model_loader: - kv 2: command-r.block_count u32 = 40
llama_model_loader: - kv 3: command-r.context_length u32 = 131072
llama_model_loader: - kv 4: command-r.embedding_length u32 = 8192
llama_model_loader: - kv 5: command-r.feed_forward_length u32 = 22528
llama_model_loader: - kv 6: command-r.attention.head_count u32 = 64
llama_model_loader: - kv 7: command-r.attention.head_count_kv u32 = 64
llama_model_loader: - kv 8: command-r.rope.freq_base f32 = 8000000.000000
llama_model_loader: - kv 9: command-r.attention.layer_norm_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 1
llama_model_loader: - kv 11: command-r.logit_scale f32 = 0.062500
llama_model_loader: - kv 12: command-r.rope.scaling.type str = none
llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,256000] = ["<PAD>", "<UNK>", "<CLS>", "<SEP>", ...
llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 3, 3, 3, 3, 1, 1, 1, 1, ...
llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,253333] = ["Ġ Ġ", "Ġ t", "e r", "i n", "Ġ a...
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 5
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 255001
llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - type f32: 41 tensors
llama_model_loader: - type f16: 281 tensors
llm_load_vocab: special tokens definition check successful ( 1008/256000 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = command-r
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 256000
llm_load_print_meta: n_merges = 253333
llm_load_print_meta: n_ctx_train = 131072
llm_load_print_meta: n_embd = 8192
llm_load_print_meta: n_head = 64
llm_load_print_meta: n_head_kv = 64
llm_load_print_meta: n_layer = 40
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 8192
llm_load_print_meta: n_embd_v_gqa = 8192
llm_load_print_meta: f_norm_eps = 1.0e-05
llm_load_print_meta: f_norm_rms_eps = 0.0e+00
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 6.2e-02
llm_load_print_meta: n_ff = 22528
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attm = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
llm_load_print_meta: rope scaling = none
llm_load_print_meta: freq_base_train = 8000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 131072
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: model type = 35B
llm_load_print_meta: model ftype = F16
llm_load_print_meta: model params = 34.98 B
llm_load_print_meta: model size = 65.16 GiB (16.00 BPW)
llm_load_print_meta: general.name = 9fe64d67d13873f218cb05083b6fc2faab2d034a
llm_load_print_meta: BOS token = 5 '<BOS_TOKEN>'
llm_load_print_meta: EOS token = 255001 '<|END_OF_TURN_TOKEN|>'
llm_load_print_meta: PAD token = 0 '<PAD>'
llm_load_print_meta: LF token = 136 'Ä'

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text

c4ai-command-r-v01-f16.gguf-split-a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc5c8aebb085158aea3e0d7f76460e8ecbf34e2d5e1d5827951ef8d7c6523a5
+size 34986609552

c4ai-command-r-v01-f16.gguf-split-b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5fae9f8a84f02cb0bac25cd44bac3b3be5d8da2ece784f2105171baa9b5a65
+size 34986609552