nicoboss · nicoboss · Jul 9, 2025 · Jul 8, 2025 · Jul 8, 2025 · Jul 8, 2025
diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
@@ -818,6 +818,21 @@ def get_vocab_base_pre(self, tokenizer) -> str:
         if chkhsh == "7e57df22b1fe23a7b1e1c7f3dc4e3f96d43a4eb0836d0c6bdc3436d7b2f1c664":
             # ref: https://huggingface.co/tencent/Hunyuan-A13B-Instruct
             res = "hunyuan"
+        if chkhsh == "b0a6b1c0bd5998ebd9df08611efde34a4ff03faed45ae09c43e6b31ebd4b94cf":
+            # ref: https://huggingface.co/skt/A.X-4.0
+            res = "a.x-4.0"
+        if chkhsh == "a6b57017d60e6edb4d88ecc2845188e0eb333a70357e45dcc9b53964a73bbae6":
+            # ref: https://huggingface.co/tiiuae/Falcon-H1-0.5B-Base
+            res = "falcon-h1"
+        if chkhsh == "60476e1243776c4fb1b993dbd7a5f15ac22f83c80afdf425fa5ae01c8d44ef86":
+            # ref: https://huggingface.co/tiiuae/Falcon-H1-1B-Base
+            res = "falcon-h1"
+        if chkhsh == "3eda48b4c4dc7de733d1a8b3e3b4a85243dbbf704da2ee9d42c6beced8897896":
+            # ref: https://huggingface.co/tiiuae/Falcon-H1-7B-Base
+            res = "falcon-h1"
+        if chkhsh == "48f8e02c0359c0bbdd82f26909171fac1c18a457bb47573ed1fe3bbb2c1cfd4b":
+            # ref: https://huggingface.co/tiiuae/Falcon-H1-34B-Base
+            res = "falcon-h1"
 
         if res is None:
             logger.warning("\n")
@@ -4899,17 +4914,19 @@ def set_vocab(self):
     def set_gguf_parameters(self):
         d_model = self.find_hparam(["hidden_size", "d_model", "dim"])
         d_conv  = self.find_hparam(["conv_kernel",       "d_conv"],  optional=True) or 4
-        d_inner = self.find_hparam(["intermediate_size", "d_inner"], optional=True) or 2 * d_model
+        d_inner = self.find_hparam(["mamba_d_ssm", "intermediate_size", "d_inner"], optional=True) or 2 * d_model
         d_state = self.find_hparam(["state_size",        "d_state"], optional=True) or 128
-        head_dim = self.find_hparam(["head_dim"],                    optional=True) or 64
+        head_dim = self.find_hparam(["mamba_d_head", "head_dim"],    optional=True) or 64
         n_group = self.find_hparam(["n_groups"],                     optional=True) or 1
 
         rms_norm_eps = self.find_hparam(["layer_norm_epsilon", "rms_norm_eps"], optional=True) or 1e-5
 
         # Fail early for models which don't have a block expansion factor of 2
         # TODO: does this really matter?
-        assert d_inner == 2 * d_model
-        assert d_inner % head_dim == 0
+        # skip the assertion for FalconH1 Model
+        if self.model_arch != gguf.MODEL_ARCH.FALCON_H1:
+            assert d_inner == 2 * d_model
+            assert d_inner % head_dim == 0
 
         self.gguf_writer.add_context_length(2**20)  # arbitrary value; for those who use the default
         self.gguf_writer.add_embedding_length(d_model)
@@ -4946,7 +4963,7 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
             data_torch = data_torch.reshape((*data_torch.shape, 1))
         elif self.match_model_tensor_name(new_name, gguf.MODEL_TENSOR.SSM_NORM, bid):
             d_model = self.find_hparam(["hidden_size", "d_model", "dim"])
-            d_inner = self.find_hparam(["intermediate_size", "d_inner"], optional=True) or 2 * d_model
+            d_inner = self.find_hparam(["mamba_d_ssm", "intermediate_size", "d_inner"], optional=True) or 2 * d_model
             n_group = self.hparams.get("n_groups", 1)
             data_torch = data_torch.reshape((n_group, d_inner // n_group))
 
@@ -4957,6 +4974,123 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
         yield (new_name, data_torch)
 
 
+@ModelBase.register("JambaForCausalLM")
+class JambaModel(TextModel):
+    model_arch = gguf.MODEL_ARCH.JAMBA
+
+    def get_vocab_base_pre(self, tokenizer) -> str:
+        del tokenizer  # unused
+
+        return "gpt-2"
+
+    def set_vocab(self):
+        if (self.dir_model / "tokenizer.model").is_file():
+            # Using Jamba's tokenizer.json causes errors on model load
+            # (something about "byte not found in vocab"),
+            # but there's a working tokenizer.model
+            self._set_vocab_sentencepiece()
+        else:
+            # Some Jamba models only have a tokenizer.json, which works.
+            self._set_vocab_gpt2()
+
+    def set_gguf_parameters(self):
+        d_model = self.find_hparam(["hidden_size", "mamba_d_model"])
+        d_conv  = self.find_hparam(["mamba_d_conv"],  optional=True) or 4
+        d_inner = self.hparams["mamba_expand"] * d_model
+        d_state = self.find_hparam(["mamba_d_state"], optional=True) or 16
+        # ceiling division
+        # ref: https://stackoverflow.com/a/17511341/22827863
+        # ref: https://github.com/state-spaces/mamba/blob/ce59daea3a090d011d6476c6e5b97f6d58ddad8b/mamba_ssm/modules/mamba_simple.py#L58
+        dt_rank      = self.find_hparam(["mamba_dt_rank"], optional=True) or -(d_model // -16)
+        rms_norm_eps = self.find_hparam(["layer_norm_epsilon", "rms_norm_eps"], optional=True) or 1e-6
+        n_kv_head = self.hparams["num_key_value_heads"]
+        attn_offset = self.hparams["attn_layer_offset"]
+        attn_period = self.hparams["attn_layer_period"]
+        n_kv_vec = [0 for _ in range(attn_offset)] + [
+            n_kv_head if (i - attn_offset) % attn_period == 0 else 0 for i in range(attn_offset, self.block_count)
+        ]
+
+        self.gguf_writer.add_block_count(self.block_count)
+        self.gguf_writer.add_context_length(self.find_hparam(["max_position_embeddings", "n_ctx"]))
+        self.gguf_writer.add_embedding_length(d_model)
+        self.gguf_writer.add_feed_forward_length(self.hparams["intermediate_size"])
+        self.gguf_writer.add_head_count(self.hparams["num_attention_heads"])
+        self.gguf_writer.add_head_count_kv(n_kv_vec)
+        self.gguf_writer.add_ssm_conv_kernel(d_conv)
+        self.gguf_writer.add_ssm_inner_size(d_inner)
+        self.gguf_writer.add_ssm_state_size(d_state)
+        self.gguf_writer.add_ssm_time_step_rank(dt_rank)
+        self.gguf_writer.add_layer_norm_rms_eps(rms_norm_eps)
+        self.gguf_writer.add_expert_count(self.hparams["num_experts"])
+        self.gguf_writer.add_expert_used_count(self.hparams["num_experts_per_tok"])
+        self.gguf_writer.add_file_type(self.ftype)
+
+    _experts: list[dict[str, Tensor]] | None = None
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+
+        # Mini-Jamba
+        name = name.replace(".moe.", ".feed_forward.")
+        if bid is not None:
+            moe_offset = self.hparams["expert_layer_offset"]
+            moe_period = self.hparams["expert_layer_period"]
+
+            if not (bid >= moe_offset and (bid - moe_offset) % moe_period == 0):
+                name = name.replace(".experts.0.", ".")
+
+        # process the experts separately
+        if ".feed_forward.experts." in name:
+            n_experts = self.hparams["num_experts"]
+
+            assert bid is not None
+
+            if self._experts is None:
+                self._experts = [{} for _ in range(self.block_count)]
+
+            self._experts[bid][name] = data_torch
+
+            if len(self._experts[bid]) >= n_experts * 3:
+
+                # merge the experts into a single 3d tensor
+                for wid in ["down_proj", "gate_proj", "up_proj"]:
+                    datas: list[Tensor] = []
+
+                    for xid in range(n_experts):
+                        ename = f"model.layers.{bid}.feed_forward.experts.{xid}.{wid}.weight"
+                        datas.append(self._experts[bid][ename])
+                        del self._experts[bid][ename]
+
+                    data_torch = torch.stack(datas, dim=0)
+
+                    # using the same merged name as qwen2moe
+                    merged_name = f"model.layers.{bid}.mlp.experts.{wid}.weight"
+
+                    new_name = self.map_tensor_name(merged_name)
+
+                    yield new_name, data_torch
+            return
+
+        new_name = self.map_tensor_name(name)
+
+        if self.match_model_tensor_name(new_name, gguf.MODEL_TENSOR.SSM_CONV1D, bid):
+            data_torch = data_torch.squeeze()
+
+        if name.endswith(".A_log"):
+            logger.debug("A_log --> A ==> " + new_name)
+            data_torch = -torch.exp(data_torch)
+
+        yield (new_name, data_torch)
+
+    def prepare_tensors(self):
+        super().prepare_tensors()
+
+        if self._experts is not None:
+            # flatten `list[dict[str, Tensor]]` into `list[str]`
+            experts = [k for d in self._experts for k in d.keys()]
+            if len(experts) > 0:
+                raise ValueError(f"Unprocessed experts: {experts}")
+
+
 @ModelBase.register("CohereForCausalLM")
 class CommandR2Model(TextModel):
     model_arch = gguf.MODEL_ARCH.COMMAND_R
@@ -6539,6 +6673,113 @@ def set_gguf_parameters(self):
         self.gguf_writer.add_audio_stack_factor(self.global_config["stack_factor"])
 
 
+@ModelBase.register("FalconH1ForCausalLM")
+class FalconH1Model(Mamba2Model):
+    model_arch = gguf.MODEL_ARCH.FALCON_H1
+
+    def __init__(self, *args, **kwargs):
+        # Set the hparam prefixes for Falcon Mamba2
+        self.hparam_prefixes = ["mamba"]
+
+        # Initialize the base Mamba2Model
+        super().__init__(*args, **kwargs)
+
+        # Use Llama conversion for attention
+        self._transformer_model_class = LlamaModel
+
+        # n_group and d_inner are used during reshape_tensors for mamaba2
+        self.n_group = self.find_hparam(["n_groups"])
+        self.d_inner = self.find_hparam(["mamba_d_ssm"])
+        self.d_head = self.find_hparam(["d_head"])
+
+        # Initialize any Falcon Mamba2 specific attributes
+        self.has_attention = True  # Falcon Mamba2 has attention components
+
+        # Load Falcon-H1 multipliers from hyperparameters
+        self.attention_in_multiplier = self.find_hparam(["attention_in_multiplier"], optional=True)
+        self.attention_out_multiplier = self.find_hparam(["attention_out_multiplier"], optional=True)
+        self.ssm_in_multiplier = self.find_hparam(["ssm_in_multiplier"], optional=True)
+        self.ssm_out_multiplier = self.find_hparam(["ssm_out_multiplier"], optional=True)
+        self.mlp_multipliers = self.find_hparam(["mlp_multipliers"], optional=True)
+        self.ssm_multipliers = self.find_hparam(["ssm_multipliers"], optional=True)
+        self.intermediate_size = self.find_hparam(["intermediate_size"])
+        self.key_multiplier = self.find_hparam(["key_multiplier"], optional=True)
+
+    def find_hparam(self, keys: Iterable[str], *args, **kwargs) -> Any:
+        prefixed = []
+        for pfx in self.hparam_prefixes:
+            prefixed.extend(
+                "_".join([pfx, k])
+                for k in keys
+            )
+        keys = list(keys) + prefixed
+        return super().find_hparam(keys, *args, **kwargs)
+
+    def set_vocab(self):
+        self._set_vocab_gpt2()
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        tensors = list(super().modify_tensors(data_torch, name, bid))
+        tensor = tensors[0][1]
+
+        if "down_proj" in name:
+            tensor = tensor  * self.mlp_multipliers[1]
+        elif "gate_proj" in name:
+            tensor = tensor * self.mlp_multipliers[0]
+        elif "k_proj" in name:
+            tensor = tensor * self.key_multiplier * self.attention_in_multiplier
+        elif "q_proj" in name:
+            tensor = tensor * self.attention_in_multiplier
+        elif "v_proj" in name:
+            tensor = tensor * self.attention_in_multiplier
+        elif "o_proj" in name:
+            tensor = tensor * self.attention_out_multiplier
+        elif "out_proj" in name:
+            tensor = tensor * self.ssm_out_multiplier
+        elif "in_proj" in name:
+            tensor = tensor * self.ssm_in_multiplier
+            zxbcdt_multipliers = self.hparams["ssm_multipliers"]
+            intermediate_size = self.hparams["mamba_d_ssm"]
+            groups_time_state_size = self.hparams["mamba_n_groups"] * self.hparams["mamba_d_state"]
+            tensor[:intermediate_size, :] *= zxbcdt_multipliers[0]
+            tensor[intermediate_size:2 * intermediate_size, :] *= zxbcdt_multipliers[1]
+            tensor[2 * intermediate_size:2 * intermediate_size + groups_time_state_size, :] *= zxbcdt_multipliers[2]
+            tensor[2 * intermediate_size + groups_time_state_size:2 * intermediate_size + 2 * groups_time_state_size, :] *= zxbcdt_multipliers[3]
+            tensor[2 * intermediate_size + 2 * groups_time_state_size:, :] *= zxbcdt_multipliers[4]
+        elif "lm_head" in name:
+            tensor = tensor * self.hparams["lm_head_multiplier"]
+        elif "embed_tokens" in name:
+            tensor = tensor * self.hparams["embedding_multiplier"]
+        elif "mamba.norm" in name:
+            tensor = tensor.reshape(self.n_group, self.d_inner // self.n_group)
+
+        tensors = [(tensors[0][0], tensor)]
+        return tensors
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+
+        ## General Params ##
+        self.gguf_writer.add_vocab_size(self.hparams["vocab_size"])
+        # Override some Mamba2 defaults
+        self.gguf_writer.add_block_count(self.block_count)
+        self.gguf_writer.add_context_length(self.hparams.get("max_position_embeddings", 0))
+        self.gguf_writer.add_feed_forward_length(self.hparams["intermediate_size"])
+
+        ## Attention params ##
+        self.gguf_writer.add_head_count(self.hparams["num_attention_heads"]) # Override value 0 from Mamba2
+        self.gguf_writer.add_head_count_kv(self.hparams["num_key_value_heads"])
+        self.gguf_writer.add_key_length(self.hparams["head_dim"])
+        self.gguf_writer.add_value_length(self.hparams["head_dim"])
+
+        ## Validation ##
+        assert self.hparams.get("hidden_act") in [None, "silu"], "Only SILU activation supported"
+        assert self.d_inner % self.d_head == 0, f"SSM inner size {self.d_inner} not a multiple of head dim {self.d_head}"
+
+        # Add any other Falcon Mamba2 specific configuration
+        self.gguf_writer.add_rope_freq_base(self.find_hparam(["rope_theta"]))
+
+
 @ModelBase.register("HunYuanMoEV1ForCausalLM")
 class HunYuanMoEModel(TextModel):
     model_arch = gguf.MODEL_ARCH.HUNYUAN_MOE
@@ -6687,6 +6928,21 @@ def prepare_tensors(self):
             if len(experts) > 0:
                 raise ValueError(f"Unprocessed experts: {experts}")
 
+
+@ModelBase.register("SmolLM3ForCausalLM")
+class SmolLM3Model(LlamaModel):
+    model_arch = gguf.MODEL_ARCH.SMOLLM3
+
+    def set_vocab(self):
+        super().set_vocab()
+        # remove unsupported array slicing in chat template
+        # ref: https://huggingface.co/ggml-org/SmolLM3-3B-GGUF/discussions/1
+        from transformers import AutoTokenizer
+        tokenizer = AutoTokenizer.from_pretrained(self.dir_model)
+        if tokenizer.chat_template is not None:
+            chat_template = tokenizer.chat_template.replace("[:]", "")
+            self.gguf_writer.add_chat_template(chat_template)
+
 ###### CONVERSION LOGIC ######
 
 

diff --git a/convert_hf_to_gguf_update.py b/convert_hf_to_gguf_update.py
@@ -128,6 +128,7 @@ class TOKENIZER_TYPE(IntEnum):
     {"name": "llama4",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct", },
     {"name": "pixtral",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mistral-community/pixtral-12b", },
     {"name": "seed-coder",       "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Base", },
+    {"name": "a.x-4.0",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/skt/A.X-4.0", },
 ]
 
 # some models are known to be broken upstream, so we will skip them as exceptions
@@ -138,6 +139,11 @@ class TOKENIZER_TYPE(IntEnum):
     {"name": "glm4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/THUDM/glm-4-9b-hf", "chkhsh": "a1336059768a55c99a734006ffb02203cd450fed003e9a71886c88acf24fdbc2"},
     {"name": "minerva-7b", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/sapienzanlp/Minerva-7B-base-v1.0", "chkhsh": "1431a23e583c97432bc230bff598d103ddb5a1f89960c8f1d1051aaa944d0b35"},
     {"name": "hunyuan", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tencent/Hunyuan-A13B-Instruct", "chkhsh": "7e57df22b1fe23a7b1e1c7f3dc4e3f96d43a4eb0836d0c6bdc3436d7b2f1c664"},
+    # falcon-h1 series uses 4 different tokenizers across model sizes (0.5b - 34b), hence we need to define 4 different hashes
+    {"name": "falcon-h1", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/Falcon-H1-0.5B-Base", "chkhsh": "a6b57017d60e6edb4d88ecc2845188e0eb333a70357e45dcc9b53964a73bbae6"},
+    {"name": "falcon-h1", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/Falcon-H1-1B-Base", "chkhsh": "60476e1243776c4fb1b993dbd7a5f15ac22f83c80afdf425fa5ae01c8d44ef86"},
+    {"name": "falcon-h1", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/Falcon-H1-7B-Base", "chkhsh": "3eda48b4c4dc7de733d1a8b3e3b4a85243dbbf704da2ee9d42c6beced8897896"},
+    {"name": "falcon-h1", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/Falcon-H1-34B-Base", "chkhsh": "48f8e02c0359c0bbdd82f26909171fac1c18a457bb47573ed1fe3bbb2c1cfd4b"},
 ]
 
 

diff --git a/docs/development/HOWTO-add-model.md b/docs/development/HOWTO-add-model.md
@@ -83,20 +83,22 @@ NOTE: Tensor names must end with `.weight` or `.bias` suffixes, that is the conv
 
 ### 2. Define the model architecture in `llama.cpp`
 
-The model params and tensors layout must be defined in `llama.cpp`:
-1. Define a new `llm_arch`
-2. Define the tensors layout in `LLM_TENSOR_NAMES`
-3. Add any non-standard metadata in `llm_load_hparams`
-4. Create the tensors for inference in `llm_load_tensors`
-5. If the model has a RoPE operation, add the rope type in `llama_rope_type`
+The model params and tensors layout must be defined in `llama.cpp` source files:
+1. Define a new `llm_arch` enum value in `src/llama-arch.h`.
+2. In `src/llama-arch.cpp`:
+    - Add the architecture name to the `LLM_ARCH_NAMES` map.
+    - Add the tensor mappings to the `LLM_TENSOR_NAMES` map.
+3. Add any non-standard metadata loading in the `llama_model_loader` constructor in `src/llama-model-loader.cpp`.
+4. If the model has a RoPE operation, add a case for the architecture in `llama_model_rope_type` function in `src/llama-model.cpp`.
 
 NOTE: The dimensions in `ggml` are typically in the reverse order of the `pytorch` dimensions.
 
 ### 3. Build the GGML graph implementation
 
-This is the funniest part, you have to provide the inference graph implementation of the new model architecture in `llama_build_graph`.
-
-Have a look at existing implementations like `build_llama`, `build_dbrx` or `build_bert`.
+This is the funniest part, you have to provide the inference graph implementation of the new model architecture in `src/llama-model.cpp`.
+Create a new struct that inherits from `llm_graph_context` and implement the graph-building logic in its constructor.
+Have a look at existing implementations like `llm_build_llama`, `llm_build_dbrx` or `llm_build_bert`.
+Then, in the `llama_model::build_graph` method, add a case for your architecture to instantiate your new graph-building struct.
 
 Some `ggml` backends do not support all operations. Backend implementations can be added in a separate PR.
 

diff --git a/ggml/include/ggml.h b/ggml/include/ggml.h
@@ -1297,6 +1297,19 @@ extern "C" {
             struct ggml_tensor  * a,
             float                 s);
 
+    // x = s * a + b
+    GGML_API struct ggml_tensor * ggml_scale_bias(
+        struct ggml_context * ctx,
+        struct ggml_tensor  * a,
+        float                 s,
+        float                 b);
+
+    GGML_API struct ggml_tensor * ggml_scale_bias_inplace(
+        struct ggml_context * ctx,
+        struct ggml_tensor  * a,
+        float                 s,
+        float                 b);
+
     // b -> view(a,offset,nb1,nb2,3), return modified a
     GGML_API struct ggml_tensor * ggml_set(
             struct ggml_context * ctx,