cohere2moe-rocmfpx.patch

--- a/src/llama-arch.h
+++ b/src/llama-arch.h
@@ -72,6 +72,7 @@
     LLM_ARCH_XVERSE,
     LLM_ARCH_COMMAND_R,
     LLM_ARCH_COHERE2,
+    LLM_ARCH_COHERE2MOE,
     LLM_ARCH_DBRX,
     LLM_ARCH_OLMO,
     LLM_ARCH_OLMO2,
--- a/src/llama-arch.cpp
+++ b/src/llama-arch.cpp
@@ -67,6 +67,7 @@
     { LLM_ARCH_XVERSE,           "xverse"           },
     { LLM_ARCH_COMMAND_R,        "command-r"        },
     { LLM_ARCH_COHERE2,          "cohere2"          },
+    { LLM_ARCH_COHERE2MOE,       "cohere2moe"       },
     { LLM_ARCH_DBRX,             "dbrx"             },
     { LLM_ARCH_OLMO,             "olmo"             },
     { LLM_ARCH_OLMO2,            "olmo2"            },
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -155,6 +155,8 @@
             return new llama_model_command_r(params);
         case LLM_ARCH_COHERE2:
             return new llama_model_cohere2(params);
+        case LLM_ARCH_COHERE2MOE:
+            return new llama_model_cohere2moe(params);
         case LLM_ARCH_DBRX:
             return new llama_model_dbrx(params);
         case LLM_ARCH_OLMO:
@@ -1788,7 +1790,7 @@
             LLAMA_LOG_INFO("%s: n_ff_shexp            = %d\n",     __func__, hparams.n_ff_shexp);
         }
 
-        if (arch == LLM_ARCH_QWEN3MOE || arch == LLM_ARCH_OPENAI_MOE || arch == LLM_ARCH_QWEN3VLMOE || arch == LLM_ARCH_RND1) {
+        if (arch == LLM_ARCH_COHERE2MOE || arch == LLM_ARCH_QWEN3MOE || arch == LLM_ARCH_OPENAI_MOE || arch == LLM_ARCH_QWEN3VLMOE || arch == LLM_ARCH_RND1) {
             LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
         }
 
@@ -2338,6 +2340,7 @@
         case LLM_ARCH_XVERSE:
         case LLM_ARCH_COMMAND_R:
         case LLM_ARCH_COHERE2:
+        case LLM_ARCH_COHERE2MOE:
         case LLM_ARCH_OLMO:
         case LLM_ARCH_ARCTIC:
         case LLM_ARCH_DEEPSEEK:
--- a/src/models/models.h
+++ b/src/models/models.h
@@ -964,6 +964,20 @@
 };
 
 
+
+struct llama_model_cohere2moe : public llama_model_base {
+    llama_model_cohere2moe(const struct llama_model_params & params) : llama_model_base(params) {}
+    void load_arch_hparams(llama_model_loader & ml) override;
+    void load_arch_tensors(llama_model_loader & ml) override;
+
+    struct graph : public llm_graph_context {
+        graph(const llama_model & model, const llm_graph_params & params);
+    };
+
+    std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
+};
+
+
 struct llama_model_dbrx : public llama_model_base {
     llama_model_dbrx(const struct llama_model_params & params) : llama_model_base(params) {}
     void load_arch_hparams(llama_model_loader & ml) override;
--- a/src/llama-model-saver.cpp
+++ b/src/llama-model-saver.cpp
@@ -21,6 +21,7 @@
         case LLM_ARCH_GEMMA3:
         case LLM_ARCH_GEMMA3N:
         case LLM_ARCH_COHERE2:
+        case LLM_ARCH_COHERE2MOE:
         case LLM_ARCH_OLMO2:
         case LLM_ARCH_BITNET:
         case LLM_ARCH_T5:
--- a/src/llama-vocab.cpp
+++ b/src/llama-vocab.cpp
@@ -2267,7 +2267,8 @@
                 pre_type = LLAMA_VOCAB_PRE_TYPE_GPT4O;
                 clean_spaces = false;
             } else if (
-                tokenizer_pre == "tiny_aya") {
+                tokenizer_pre == "tiny_aya" ||
+                tokenizer_pre == "cohere2moe") {
                 pre_type = LLAMA_VOCAB_PRE_TYPE_TINY_AYA;
                 clean_spaces = false;
             } else if (
--- a/gguf-py/gguf/constants.py
+++ b/gguf-py/gguf/constants.py
@@ -467,6 +467,7 @@
     XVERSE           = auto()
     COMMAND_R        = auto()
     COHERE2          = auto()
+    COHERE2MOE       = auto()
     DBRX             = auto()
     OLMO             = auto()
     OLMO2            = auto()
@@ -1029,6 +1030,7 @@
     MODEL_ARCH.XVERSE:           "xverse",
     MODEL_ARCH.COMMAND_R:        "command-r",
     MODEL_ARCH.COHERE2:          "cohere2",
+    MODEL_ARCH.COHERE2MOE:       "cohere2moe",
     MODEL_ARCH.DBRX:             "dbrx",
     MODEL_ARCH.OLMO:             "olmo",
     MODEL_ARCH.OLMO2:            "olmo2",
@@ -2905,6 +2907,33 @@
         MODEL_TENSOR.FFN_DOWN,
         MODEL_TENSOR.FFN_UP,
     ],
+    MODEL_ARCH.COHERE2MOE: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        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,
+        MODEL_TENSOR.FFN_GATE_INP,
+        MODEL_TENSOR.FFN_GATE_EXP,
+        MODEL_TENSOR.FFN_GATE_UP_EXP,
+        MODEL_TENSOR.FFN_DOWN_EXP,
+        MODEL_TENSOR.FFN_UP_EXP,
+        MODEL_TENSOR.FFN_GATE_SHEXP,
+        MODEL_TENSOR.FFN_DOWN_SHEXP,
+        MODEL_TENSOR.FFN_UP_SHEXP,
+        MODEL_TENSOR.NEXTN_EH_PROJ,
+        MODEL_TENSOR.NEXTN_EMBED_TOKENS,
+        MODEL_TENSOR.NEXTN_ENORM,
+        MODEL_TENSOR.NEXTN_HNORM,
+        MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD,
+        MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM,
+    ],
     MODEL_ARCH.DBRX: [
         MODEL_TENSOR.TOKEN_EMBD,
         MODEL_TENSOR.OUTPUT_NORM,
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -1443,7 +1443,7 @@
             res = "command-r"
         if chkhsh == "d772b220ace2baec124bed8cfafce0ead7d6c38a4b65ef11261cf9d5d62246d1":
             # ref: https://huggingface.co/CohereLabs/tiny-aya-base
-            res = "tiny_aya"
+            res = "tiny_aya"  # also used by cohere2moe / North Mini
         if chkhsh == "e636dc30a262dcc0d8c323492e32ae2b70728f4df7dfe9737d9f920a282b8aea":
             # ref: https://huggingface.co/Qwen/Qwen1.5-7B
             res = "qwen2"
@@ -8978,6 +8978,89 @@
         yield from super().modify_tensors(data_torch, name, bid)
 
 
+
+@ModelBase.register("Cohere2MoeForCausalLM")
+class Cohere2MoeModel(TextModel):
+    """Cohere2 MoE (North Mini Code). Ported from mainline conversion/command_r.py.
+    Per-expert FC biases: skipped when zero; ValueError if non-zero (runtime has no bias path required for North GGUFs).
+    """
+    model_arch = gguf.MODEL_ARCH.COHERE2MOE
+    _n_main_layers = None
+    _expert_tensor_re = __import__("re").compile(
+        r"model\.layers\.(\d+)\.mlp\.experts\.(\d+)\.(down_proj|gate_proj|up_proj)\.weight"
+    )
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        n_nextn = int(self.hparams.get("num_nextn_predict_layers", 0) or 0)
+        if n_nextn > 0 and not getattr(self, "no_mtp", False):
+            self.block_count += n_nextn
+            self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)
+        self._experts = [{} for _ in range(self.block_count)]
+
+    def set_gguf_parameters(self):
+        hparams = self.hparams
+        expert_intermediate_size = hparams["intermediate_size"]
+        mlp_layer_types = hparams.get("mlp_layer_types")
+        n_dense_lead = hparams.get("first_k_dense_replace", 0)
+        if mlp_layer_types is not None:
+            n_dense_lead = next((i for i, tp in enumerate(mlp_layer_types) if tp != "dense"), len(mlp_layer_types))
+        super().set_gguf_parameters()
+        self.gguf_writer.add_logit_scale(hparams["logit_scale"])
+        self.gguf_writer.add_sliding_window(hparams["sliding_window"])
+        self.gguf_writer.add_sliding_window_pattern([tp == "sliding_attention" for tp in hparams["layer_types"]])
+        self.gguf_writer.add_vocab_size(hparams["vocab_size"])
+        self.gguf_writer.add_expert_feed_forward_length(expert_intermediate_size)
+        self.gguf_writer.add_leading_dense_block_count(n_dense_lead)
+        self.gguf_writer.add_expert_weights_norm(hparams.get("norm_topk_prob", False))
+        if (num_shared_experts := hparams.get("num_shared_experts", 0)) > 0:
+            if hparams.get("shared_expert_combination_strategy", "average") != "average":
+                raise ValueError("Cohere2 MoE only supports average shared expert combination")
+            self.gguf_writer.add_expert_shared_count(num_shared_experts)
+            self.gguf_writer.add_expert_shared_feed_forward_length(expert_intermediate_size * num_shared_experts)
+        n_nextn = hparams.get("num_nextn_predict_layers", 0)
+        if n_nextn > 0 and not getattr(self, "no_mtp", False):
+            self.gguf_writer.add_nextn_predict_layers(n_nextn)
+        self.gguf_writer.add_rope_dimension_count(hparams["head_dim"])
+        self.gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.NONE)
+
+    def modify_tensors(self, data_torch, name, bid=None):
+        import torch
+        if name.endswith(".bias"):
+            if torch.any(data_torch != 0):
+                raise ValueError(f"Bias tensor {name!r} is not zero.")
+            logger.debug(f"Skipping bias tensor {name!r}.")
+            return
+        m = self._expert_tensor_re.fullmatch(name)
+        if m is not None:
+            n_experts = self.hparams["num_experts"]
+            layer_idx = int(m.group(1))
+            self._experts[layer_idx][name] = data_torch
+            expected = {
+                f"model.layers.{layer_idx}.mlp.experts.{xid}.{w_name}.weight"
+                for xid in range(n_experts)
+                for w_name in ("down_proj", "gate_proj", "up_proj")
+            }
+            if expected.issubset(self._experts[layer_idx]):
+                for w_name in ["down_proj", "gate_proj", "up_proj"]:
+                    datas = []
+                    for xid in range(n_experts):
+                        ename = f"model.layers.{layer_idx}.mlp.experts.{xid}.{w_name}.weight"
+                        datas.append(self._experts[layer_idx][ename])
+                        del self._experts[layer_idx][ename]
+                    data_torch = torch.stack(datas, dim=0)
+                    merged_name = f"model.layers.{layer_idx}.mlp.experts.{w_name}.weight"
+                    yield from super().modify_tensors(data_torch, merged_name, layer_idx)
+            return
+        yield from super().modify_tensors(data_torch, name, bid)
+
+    def prepare_tensors(self):
+        super().prepare_tensors()
+        experts = [k for d in self._experts for k in d.keys()]
+        if len(experts) > 0:
+            raise ValueError(f"Unprocessed experts: {experts}")
+
+
 @ModelBase.register("OlmoForCausalLM")
 @ModelBase.register("OLMoForCausalLM")
 class OlmoModel(TextModel):
--- a/conversion/__init__.py
+++ b/conversion/__init__.py
@@ -42,6 +42,7 @@
     "CodeShellForCausalLM": "codeshell",
     "CogVLMForCausalLM": "cogvlm",
     "Cohere2ForCausalLM": "command_r",
+    "Cohere2MoeForCausalLM": "command_r",
     "CohereForCausalLM": "command_r",
     "DbrxForCausalLM": "dbrx",
     "DeciLMForCausalLM": "deci",
--- a/conversion/base.py
+++ b/conversion/base.py
@@ -1505,7 +1505,7 @@
             res = "command-r"
         if chkhsh == "d772b220ace2baec124bed8cfafce0ead7d6c38a4b65ef11261cf9d5d62246d1":
             # ref: https://huggingface.co/CohereLabs/tiny-aya-base
-            res = "tiny_aya"
+            res = "tiny_aya"  # also used by cohere2moe / North Mini
         if chkhsh == "e636dc30a262dcc0d8c323492e32ae2b70728f4df7dfe9737d9f920a282b8aea":
             # ref: https://huggingface.co/Qwen/Qwen1.5-7B
             res = "qwen2"
--- a/src/models/cohere2moe.cpp
+++ b/src/models/cohere2moe.cpp
@@ -0,0 +1,310 @@
+#include "models.h"
+
+// Port of ggml-org/llama.cpp cohere2moe into ROCmFPX fork.
+// Adapted to fork APIs:
+//   - hparams.n_layer field (not n_layer())
+//   - hparams.nextn_predict_layers (not n_layer_nextn / n_layer_all)
+//   - no embeddings_nextn_masked / t_h_nextn (fork lacks those result slots)
+//   - SWA pattern loaded as bool array into hparams.swa_layers
+// Bias tensors: HF Cohere2 MoE ships per-expert FC biases, but conversion
+// drops them when zero (mainline convert raises if non-zero). Production
+// North-Mini-Code GGUF has 0 bias tensors; graph therefore passes nullptr
+// biases, matching mainline. Optional TENSOR_NOT_REQUIRED bias loads are
+// included so a future non-zero-bias GGUF can bind without recompile.
+
+void llama_model_cohere2moe::load_arch_hparams(llama_model_loader & ml) {
+    const bool found_norm     = ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS,     hparams.f_norm_eps,     false);
+    const bool found_norm_rms = ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps, false);
+    if (!found_norm && !found_norm_rms) {
+        throw std::runtime_error("missing Cohere2 MoE norm epsilon");
+    }
+    if (!found_norm_rms) {
+        hparams.f_norm_rms_eps = 0.0f;
+    }
+
+    ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW,    hparams.n_swa);
+    ml.get_key(LLM_KV_LOGIT_SCALE,                 hparams.f_logit_scale);
+    ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT,   hparams.n_layer_dense_lead);
+    ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH,  hparams.n_ff_exp);
+    ml.get_key(LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, hparams.n_ff_shexp, false);
+    ml.get_key(LLM_KV_EXPERT_SHARED_COUNT,         hparams.n_expert_shared, false);
+    ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM,         hparams.expert_weights_norm, false);
+    ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE,        hparams.expert_weights_scale, false);
+    ml.get_key(LLM_KV_EXPERT_GATING_FUNC,          hparams.expert_gating_func, false);
+
+    ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS,        hparams.nextn_predict_layers, false);
+    GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
+
+    if (hparams.expert_gating_func == LLAMA_EXPERT_GATING_FUNC_TYPE_NONE) {
+        hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SIGMOID;
+    }
+
+    hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
+    // Prefer full per-layer bool pattern (North Mini GGUF ships this);
+    // fall back to period integer used by some cohere2 exports.
+    if (!ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.swa_layers, hparams.n_layer, false)) {
+        uint32_t swa_period = 4;
+        if (ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, swa_period, false)) {
+            hparams.set_swa_pattern(swa_period, true);
+        } else {
+            hparams.set_swa_pattern(swa_period, true);
+        }
+    }
+
+    hparams.rope_freq_base_train_swa  = hparams.rope_freq_base_train;
+    hparams.rope_freq_scale_train_swa = hparams.rope_freq_scale_train;
+    ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false);
+
+    // MTP layers (if any) are the last nextn_predict_layers of n_layer, same
+    // convention as glm4-moe in this fork.
+    if (hparams.nextn_predict_layers > 0) {
+        hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;
+    }
+
+    switch (hparams.n_layer) {
+        case 49: type = LLM_TYPE_30B_A3B; break; // North Mini Code (48 trunk + optional nextn)
+        default: type = LLM_TYPE_UNKNOWN;
+    }
+}
+
+void llama_model_cohere2moe::load_arch_tensors(llama_model_loader & ml) {
+    LLAMA_LOAD_LOCALS;
+
+    tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0);
+
+    output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0);
+    output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED);
+
+    if (output == NULL) {
+        output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, TENSOR_DUPLICATED);
+    }
+
+    if (n_expert == 0) {
+        throw std::runtime_error("n_expert must be > 0 for Cohere2Moe");
+    }
+    if (n_expert_used == 0) {
+        throw std::runtime_error("n_expert_used must be > 0 for Cohere2Moe");
+    }
+
+    const int n_transformer_layers = n_layer - (int) hparams.nextn_predict_layers;
+
+    for (int i = 0; i < n_layer; ++i) {
+        auto & layer = layers[i];
+        int flags = 0;
+        const bool is_mtp = hparams.nextn_predict_layers > 0 &&
+                            static_cast<uint32_t>(i) >= static_cast<uint32_t>(n_transformer_layers);
+        if (is_mtp) {
+            // Load MTP tensors but skip execution in the main graph (glm4-moe pattern).
+            flags |= TENSOR_SKIP;
+        }
+
+        layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), { n_embd }, flags);
+
+        // Q: n_embd x (n_embd_head_k * n_head); K/V: n_embd x n_embd_gqa
+        create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head, n_embd_gqa, n_embd_gqa, flags);
+        layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), { n_embd_head_k * n_head, n_embd }, flags);
+
+        // Optional attention output bias (HF may ship zeros; production GGUF has none).
+        layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), { n_embd }, flags | TENSOR_NOT_REQUIRED);
+
+        if (!is_mtp && static_cast<uint32_t>(i) < hparams.n_layer_dense_lead) {
+            // Leading dense FFN (layer 0 on North Mini)
+            layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), { n_embd, n_ff }, flags);
+            layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd }, flags);
+            layer.ffn_up   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), { n_embd, n_ff }, flags);
+
+            // Optional dense FC biases
+            layer.ffn_gate_b = create_tensor(tn(LLM_TENSOR_FFN_GATE, "bias", i), { n_ff },   flags | TENSOR_NOT_REQUIRED);
+            layer.ffn_up_b   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "bias", i), { n_ff },   flags | TENSOR_NOT_REQUIRED);
+            layer.ffn_down_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "bias", i), { n_embd }, flags | TENSOR_NOT_REQUIRED);
+        } else {
+            const int64_t n_ff_exp = hparams.n_ff_exp ? hparams.n_ff_exp : n_ff;
+
+            layer.ffn_gate_inp  = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP,  "weight", i), { n_embd, n_expert }, flags);
+            layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), { n_ff_exp, n_embd, n_expert }, flags);
+            create_tensor_gate_up_exps(layer, i, n_embd, n_ff_exp, n_expert, flags);
+
+            // Optional per-expert FC biases (mainline convert drops zeros; bind if present).
+            // Merged expert bias tensors would be named like ffn_*_exps.bias if ever exported.
+            layer.ffn_gate_exps_b = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "bias", i), { n_ff_exp, n_expert }, flags | TENSOR_NOT_REQUIRED);
+            layer.ffn_up_exps_b   = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS,   "bias", i), { n_ff_exp, n_expert }, flags | TENSOR_NOT_REQUIRED);
+            layer.ffn_down_exps_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "bias", i), { n_embd, n_expert },   flags | TENSOR_NOT_REQUIRED);
+            layer.ffn_gate_inp_b  = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP,  "bias", i), { n_expert },           flags | TENSOR_NOT_REQUIRED);
+
+            if (hparams.n_expert_shared > 0) {
+                const int64_t n_ff_shexp = hparams.n_ff_shexp ? hparams.n_ff_shexp : n_ff_exp * hparams.n_expert_shared;
+                layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), { n_embd, n_ff_shexp }, flags);
+                layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), { n_ff_shexp, n_embd }, flags);
+                layer.ffn_up_shexp   = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP,   "weight", i), { n_embd, n_ff_shexp }, flags);
+            }
+        }
+
+        if (is_mtp) {
+            layer.nextn.eh_proj          = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ,          "weight", i), { 2 * n_embd, n_embd }, flags);
+            layer.nextn.enorm            = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM,            "weight", i), { n_embd },              flags);
+            layer.nextn.hnorm            = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM,            "weight", i), { n_embd },              flags);
+            layer.nextn.embed_tokens     = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS,     "weight", i), { n_embd, n_vocab },     flags | TENSOR_NOT_REQUIRED);
+            layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", i), { n_embd, n_vocab },     flags | TENSOR_NOT_REQUIRED);
+            layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", i), { n_embd },              flags | TENSOR_NOT_REQUIRED);
+        }
+    }
+}
+
+std::unique_ptr<llm_graph_context> llama_model_cohere2moe::build_arch_graph(const llm_graph_params & params) const {
+    return std::make_unique<graph>(*this, params);
+}
+
+llama_model_cohere2moe::graph::graph(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
+    const int64_t n_embd_head = hparams.n_embd_head_v();
+
+    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k());
+    GGML_ASSERT(n_embd_head == n_rot);
+
+    const llm_norm_type cohere2moe_norm_type = hparams.f_norm_rms_eps == 0.0f ? LLM_NORM : LLM_NORM_RMS;
+    const float f_logit_scale = hparams.f_logit_scale;
+
+    ggml_tensor * cur;
+    ggml_tensor * inpL = build_inp_embd(model.tok_embd);
+    ggml_tensor * inp_pos = build_inp_pos();
+
+    auto * inp_attn = build_attn_inp_kv_iswa();
+    ggml_tensor * inp_out_ids = build_inp_out_ids();
+
+    // Skip MTP tail layers in the main decoder pass (glm4-moe convention).
+    const int n_transformer_layers = n_layer - (int) hparams.nextn_predict_layers;
+
+    for (int il = 0; il < n_transformer_layers; ++il) {
+        const bool is_swa = hparams.is_swa(il);
+        // Dense-prefix full-attention layers use RoPE; later layers follow SWA pattern.
+        const bool force_rope = static_cast<uint32_t>(il) < hparams.n_layer_dense_lead;
+
+        cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, cohere2moe_norm_type, il);
+        cb(cur, "attn_norm", il);
+
+        ggml_tensor * ffn_inp = cur;
+
+        {
+            const auto & layer = model.layers[il];
+
+            auto [Qcur, Kcur, Vcur] = build_qkv(layer, cur,
+                    n_embd_head, n_head, n_head_kv, il);
+
+            if (is_swa || force_rope) {
+                ggml_tensor * rope_factors = model.get_rope_factors(cparams, il);
+
+                Qcur = ggml_rope_ext(
+                        ctx0, Qcur, inp_pos, rope_factors,
+                        n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
+                        ext_factor, attn_factor, beta_fast, beta_slow);
+
+                Kcur = ggml_rope_ext(
+                        ctx0, Kcur, inp_pos, rope_factors,
+                        n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
+                        ext_factor, attn_factor, beta_fast, beta_slow);
+            }
+
+            cb(Qcur, "Qcur", il);
+            cb(Kcur, "Kcur", il);
+            cb(Vcur, "Vcur", il);
+
+            cur = build_attn(inp_attn,
+                    layer.wo, layer.wo_b, layer.wo_s,
+                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr,
+                    1.0f / sqrtf(float(n_embd_head)), il);
+        }
+
+        if (il == n_transformer_layers - 1 && inp_out_ids) {
+            cur     = ggml_get_rows(ctx0, cur, inp_out_ids);
+            inpL    = ggml_get_rows(ctx0, inpL, inp_out_ids);
+            ffn_inp = ggml_get_rows(ctx0, ffn_inp, inp_out_ids);
+        }
+
+        ggml_tensor * attn_out = cur;
+
+        const auto & layer = model.layers[il];
+
+        if (layer.ffn_gate_inp == nullptr) {
+            cur = build_ffn(ffn_inp,
+                    layer.ffn_up,   layer.ffn_up_b,   layer.ffn_up_s,
+                    layer.ffn_gate, layer.ffn_gate_b, layer.ffn_gate_s,
+                    layer.ffn_down, layer.ffn_down_b, layer.ffn_down_s,
+                    nullptr, LLM_FFN_SILU, LLM_FFN_PAR, il);
+            cb(cur, "ffn_out", il);
+        } else {
+            // Prefer bias-aware overload if any expert bias is present; else weight-only path.
+            if (layer.ffn_up_exps_b || layer.ffn_gate_exps_b || layer.ffn_down_exps_b || layer.ffn_gate_inp_b) {
+                cur = build_moe_ffn(ffn_inp,
+                        layer.ffn_gate_inp,  layer.ffn_gate_inp_b,
+                        layer.ffn_up_exps,   layer.ffn_up_exps_b,
+                        layer.ffn_gate_exps, layer.ffn_gate_exps_b,
+                        layer.ffn_down_exps, layer.ffn_down_exps_b,
+                        nullptr,
+                        n_expert, n_expert_used,
+                        LLM_FFN_SILU, hparams.expert_weights_norm,
+                        hparams.expert_weights_scale,
+                        (llama_expert_gating_func_type) hparams.expert_gating_func,
+                        il,
+                        nullptr, layer.ffn_gate_up_exps, layer.ffn_gate_up_exps_b,
+                        layer.ffn_up_exps_s,
+                        layer.ffn_gate_exps_s,
+                        layer.ffn_down_exps_s);
+            } else {
+                cur = build_moe_ffn(ffn_inp,
+                        layer.ffn_gate_inp,
+                        layer.ffn_up_exps,
+                        layer.ffn_gate_exps,
+                        layer.ffn_down_exps,
+                        nullptr,
+                        n_expert, n_expert_used,
+                        LLM_FFN_SILU, hparams.expert_weights_norm,
+                        hparams.expert_weights_scale,
+                        (llama_expert_gating_func_type) hparams.expert_gating_func,
+                        il,
+                        nullptr, layer.ffn_gate_up_exps,
+                        layer.ffn_up_exps_s,
+                        layer.ffn_gate_exps_s,
+                        layer.ffn_down_exps_s);
+            }
+            cb(cur, "ffn_moe_out", il);
+
+            if (layer.ffn_up_shexp) {
+                ggml_tensor * ffn_shexp = build_ffn(ffn_inp,
+                        layer.ffn_up_shexp,   nullptr, layer.ffn_up_shexp_s,
+                        layer.ffn_gate_shexp, nullptr, layer.ffn_gate_shexp_s,
+                        layer.ffn_down_shexp, nullptr, layer.ffn_down_shexp_s,
+                        nullptr, LLM_FFN_SILU, LLM_FFN_PAR, il);
+                cb(ffn_shexp, "ffn_shexp", il);
+
+                cur = ggml_add(ctx0, cur, ffn_shexp);
+                cur = ggml_scale(ctx0, cur, 0.5f);
+                cb(cur, "ffn_out", il);
+            }
+        }
+
+        // Parallel residual: residual + FFN + attention (Cohere-style)
+        cur = ggml_add(ctx0, cur, inpL);
+        cur = ggml_add(ctx0, cur, attn_out);
+
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
+        inpL = cur;
+    }
+
+    cur = inpL;
+    cur = build_norm(cur, model.output_norm, nullptr, cohere2moe_norm_type, -1);
+
+    cb(cur, "result_norm", -1);
+    res->t_embd = cur;
+
+    cur = build_lora_mm(model.output, cur);
+
+    if (f_logit_scale) {
+        cur = ggml_scale(ctx0, cur, f_logit_scale);
+    }
+
+    cb(cur, "result_output", -1);
+    res->t_logits = cur;
+
+    ggml_build_forward_expand(gf, cur);
+}
--- a/conversion/command_r.py
+++ b/conversion/command_r.py
@@ -0,0 +1,177 @@
+from __future__ import annotations
+
+import re
+from typing import Iterable, TYPE_CHECKING
+
+import torch
+
+if TYPE_CHECKING:
+    from torch import Tensor
+
+from .base import ModelBase, TextModel, gguf, logger
+
+
+@ModelBase.register("CohereForCausalLM")
+class CommandR2Model(TextModel):
+    model_arch = gguf.MODEL_ARCH.COMMAND_R
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+        # max_position_embeddings = 8192 in config.json but model was actually
+        # trained on 128k context length
+        # aya-23 models don't have model_max_length specified
+        self.hparams["max_position_embeddings"] = self.find_hparam(["model_max_length", "max_position_embeddings"])
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+        self.gguf_writer.add_logit_scale(self.hparams["logit_scale"])
+        self.gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.NONE)
+
+
+@ModelBase.register("Cohere2ForCausalLM")
+class Cohere2Model(TextModel):
+    model_arch = gguf.MODEL_ARCH.COHERE2
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+
+        self.gguf_writer.add_logit_scale(self.hparams["logit_scale"])
+        self.gguf_writer.add_sliding_window(self.hparams["sliding_window"])
+        self.gguf_writer.add_vocab_size(self.hparams["vocab_size"])
+
+        rotary_pct = self.hparams["rotary_pct"]
+        hidden_size = self.hparams["hidden_size"]
+        num_attention_heads = self.hparams["num_attention_heads"]
+        self.gguf_writer.add_rope_dimension_count(int(rotary_pct * (hidden_size // num_attention_heads)))
+        self.gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.NONE)
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        # Cohere2 runtime in llama.cpp expects no bias tensors;
+        # the actual weight only contains 0-value tensors as bias, we can skip them
+        if name.endswith(".bias"):
+            if torch.any(data_torch != 0):
+                raise ValueError(f"Bias tensor {name!r} is not zero.")
+            logger.debug(f"Skipping bias tensor {name!r} for Cohere2 conversion.")
+            return
+
+        yield from super().modify_tensors(data_torch, name, bid)
+
+
+@ModelBase.register("Cohere2MoeForCausalLM")
+class Cohere2MoeModel(TextModel):
+    model_arch = gguf.MODEL_ARCH.COHERE2MOE
+    _n_main_layers: int | None = None
+    _expert_tensor_re = re.compile(
+        r"model\.layers\.(\d+)\.mlp\.experts\.(\d+)\.(down_proj|gate_proj|up_proj)\.weight"
+    )
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        if (n_nextn := int(self.hparams.get("num_nextn_predict_layers", 0) or 0)) > 0 and not self.no_mtp:
+            self.block_count += n_nextn
+            self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)
+        self._experts: list[dict[str, Tensor]] = [{} for _ in range(self.block_count)]
+
+    def _set_vocab_gpt2(self) -> None:
+        tokens, toktypes, tokpre = self.get_vocab_base()
+        self.gguf_writer.add_tokenizer_model("gpt2")
+        self.gguf_writer.add_tokenizer_pre(tokpre)
+        self.gguf_writer.add_token_list(tokens)
+        self.gguf_writer.add_token_types(toktypes)
+
+        special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=True)
+        special_vocab.add_to_gguf(self.gguf_writer)
+
+    def set_gguf_parameters(self):
+        hparams = self.hparams
+        expert_intermediate_size = hparams["intermediate_size"]
+        mlp_layer_types = hparams.get("mlp_layer_types")
+        n_dense_lead = hparams.get("first_k_dense_replace", 0)
+        if mlp_layer_types is not None:
+            n_dense_lead = next((i for i, t in enumerate(mlp_layer_types) if t != "dense"), len(mlp_layer_types))
+
+        super().set_gguf_parameters()
+
+        self.gguf_writer.add_logit_scale(hparams["logit_scale"])
+        self.gguf_writer.add_sliding_window(hparams["sliding_window"])
+        self.gguf_writer.add_sliding_window_pattern([t == "sliding_attention" for t in hparams["layer_types"]])
+        self.gguf_writer.add_vocab_size(hparams["vocab_size"])
+        self.gguf_writer.add_expert_feed_forward_length(expert_intermediate_size)
+        self.gguf_writer.add_leading_dense_block_count(n_dense_lead)
+        self.gguf_writer.add_expert_weights_norm(hparams.get("norm_topk_prob", False))
+        if (num_shared_experts := hparams.get("num_shared_experts", 0)) > 0:
+            if hparams.get("shared_expert_combination_strategy", "average") != "average":
+                raise ValueError("Cohere2 MoE only supports average shared expert combination")
+            self.gguf_writer.add_expert_shared_count(num_shared_experts)
+            self.gguf_writer.add_expert_shared_feed_forward_length(expert_intermediate_size * num_shared_experts)
+        if (n_nextn := hparams.get("num_nextn_predict_layers", 0)) > 0 and not self.no_mtp:
+            self.gguf_writer.add_nextn_predict_layers(n_nextn)
+        self.gguf_writer.add_rope_dimension_count(hparams["head_dim"])
+        self.gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.NONE)
+
+    def index_tensors(self, remote_hf_model_id: str | None = None):
+        hparams = {**self.hparams, **self.hparams.get("text_config", {})}
+        self._n_main_layers = hparams.get("num_hidden_layers")
+        type(self)._n_main_layers = self._n_main_layers
+        return super().index_tensors(remote_hf_model_id=remote_hf_model_id)
+
+    @classmethod
+    def filter_tensors(cls, item):
+        if (titem := super().filter_tensors(item)) is None:
+            return None
+        name, gen = titem
+
+        if cls._n_main_layers is not None:
+            is_mtp = (m := re.match(r"model\.layers\.(\d+)\.", name)) is not None and int(m.group(1)) >= cls._n_main_layers
+            if is_mtp and cls.no_mtp:
+                return None
+            if cls.mtp_only and not is_mtp and name not in (
+                "model.embed_tokens.weight", "model.norm.weight", "lm_head.weight",
+            ):
+                return None
+
+        return name, gen
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        if name.endswith(".bias"):
+            if torch.any(data_torch != 0):
+                raise ValueError(f"Bias tensor {name!r} is not zero.")
+            logger.debug(f"Skipping bias tensor {name!r}.")
+            return
+
+        if (m := self._expert_tensor_re.fullmatch(name)) is not None:
+            n_experts = self.hparams["num_experts"]
+            layer_idx = int(m.group(1))
+            assert bid is None or bid == layer_idx
+
+            self._experts[layer_idx][name] = data_torch
+
+            expected = {
+                f"model.layers.{layer_idx}.mlp.experts.{xid}.{w_name}.weight"
+                for xid in range(n_experts)
+                for w_name in ("down_proj", "gate_proj", "up_proj")
+            }
+            if expected.issubset(self._experts[layer_idx]):
+                for w_name in ["down_proj", "gate_proj", "up_proj"]:
+                    datas: list[Tensor] = []
+
+                    for xid in range(n_experts):
+                        ename = f"model.layers.{layer_idx}.mlp.experts.{xid}.{w_name}.weight"
+                        datas.append(self._experts[layer_idx][ename])
+                        del self._experts[layer_idx][ename]
+
+                    data_torch = torch.stack(datas, dim=0)
+                    merged_name = f"model.layers.{layer_idx}.mlp.experts.{w_name}.weight"
+
+                    yield from super().modify_tensors(data_torch, merged_name, layer_idx)
+            return
+
+        yield from super().modify_tensors(data_torch, name, bid)
+
+    def prepare_tensors(self):
+        super().prepare_tensors()
+
+        experts = [k for d in self._experts for k in d.keys()]
+        if len(experts) > 0:
+            raise ValueError(f"Unprocessed experts: {experts}")