Add files using upload-large-folder tool

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 DeepSeek
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_module_list_cfg": [],
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

configuration_deepseek.py

@@ -0,0 +1,199 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.3"
+}

inference/README.md

@@ -0,0 +1,13 @@
+# DeepSeek V3.1
+
+First convert huggingface model weight files to the format of this project.
+```bash
+export EXPERTS=256
+python convert.py --hf-ckpt-path ${HF_CKPT_PATH} --save-path ${SAVE_PATH} --n-experts ${EXPERTS} --model-parallel ${MP}
+```
+
+Then chat with DeepSeek model at will!
+```bash
+export CONFIG=config_671B_v3.1.json
+torchrun --nproc-per-node ${MP} generate.py --ckpt-path ${SAVE_PATH} --config ${CONFIG} --interactive --temperature {T}
+```

inference/config_671B_v3.1.json

@@ -0,0 +1,23 @@
+{
+    "vocab_size": 129280,
+    "dim": 7168,
+    "inter_dim": 18432,
+    "moe_inter_dim": 2048,
+    "n_layers": 61,
+    "n_dense_layers": 3,
+    "n_heads": 128,
+    "n_routed_experts": 256,
+    "n_shared_experts": 1,
+    "n_activated_experts": 8,
+    "n_expert_groups": 8,
+    "n_limited_groups": 4,
+    "route_scale": 2.5,
+    "score_func": "sigmoid",
+    "q_lora_rank": 1536,
+    "kv_lora_rank": 512,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "v_head_dim": 128,
+    "dtype": "fp8",
+    "scale_fmt": "ue8m0"
+}

inference/convert.py

@@ -0,0 +1,96 @@
+import os
+import shutil
+from argparse import ArgumentParser
+from glob import glob
+from tqdm import tqdm, trange
+
+import torch
+from safetensors.torch import safe_open, save_file
+
+
+mapping = {
+    "embed_tokens": ("embed", 0),
+    "input_layernorm": ("attn_norm", None),
+    "post_attention_layernorm": ("ffn_norm", None),
+    "q_proj": ("wq", 0),
+    "q_a_proj": ("wq_a", None),
+    "q_a_layernorm": ("q_norm", None),
+    "q_b_proj": ("wq_b", 0),
+    "kv_a_proj_with_mqa": ("wkv_a", None),
+    "kv_a_layernorm": ("kv_norm", None),
+    "kv_b_proj": ("wkv_b", 0),
+    "o_proj": ("wo", 1),
+    "gate": ("gate", None),
+    "gate_proj": ("w1", 0),
+    "down_proj": ("w2", 1),
+    "up_proj": ("w3", 0),
+    "norm": ("norm", None),
+    "lm_head": ("head", 0),
+    "scale": ("scale", None),
+}
+
+
+def main(hf_ckpt_path, save_path, n_experts, mp):
+    """
+    Converts and saves model checkpoint files into a specified format.
+
+    Args:
+        hf_ckpt_path (str): Path to the directory containing the input checkpoint files.
+        save_path (str): Path to the directory where the converted checkpoint files will be saved.
+        n_experts (int): Total number of experts in the model.
+        mp (int): Model parallelism factor.
+        
+    Returns:
+        None
+    """
+    torch.set_num_threads(8)
+    n_local_experts = n_experts // mp
+    state_dicts = [{} for _ in range(mp)]
+
+    for file_path in tqdm(glob(os.path.join(hf_ckpt_path, "*.safetensors"))):
+        with safe_open(file_path, framework="pt", device="cpu") as f:
+            for name in f.keys():
+                if "model.layers.61" in name:
+                    continue
+                param: torch.Tensor = f.get_tensor(name)
+                if name.startswith("model."):
+                    name = name[len("model."):]
+                name = name.replace("self_attn", "attn")
+                name = name.replace("mlp", "ffn")
+                name = name.replace("weight_scale_inv", "scale")
+                name = name.replace("e_score_correction_bias", "bias")
+                key = name.split(".")[-2]
+                assert key in mapping, f"Key {key} not found in mapping"
+                new_key, dim = mapping[key]
+                name = name.replace(key, new_key)
+                for i in range(mp):
+                    new_param = param
+                    if "experts" in name and "shared_experts" not in name:
+                        idx = int(name.split(".")[-3])
+                        if idx < i * n_local_experts or idx >= (i + 1) * n_local_experts:
+                            continue
+                    elif dim is not None:
+                        assert param.size(dim) % mp == 0, f"Dimension {dim} must be divisible by {mp}"
+                        shard_size = param.size(dim) // mp
+                        new_param = param.narrow(dim, i * shard_size, shard_size).contiguous()
+                    state_dicts[i][name] = new_param
+
+    os.makedirs(save_path, exist_ok=True)
+
+    for i in trange(mp):
+        save_file(state_dicts[i], os.path.join(save_path, f"model{i}-mp{mp}.safetensors"))
+
+    for file_path in glob(os.path.join(hf_ckpt_path, "*token*")):
+        new_file_path = os.path.join(save_path, os.path.basename(file_path))
+        shutil.copyfile(file_path, new_file_path)
+
+
+if __name__ == "__main__":
+    parser = ArgumentParser()
+    parser.add_argument("--hf-ckpt-path", type=str, required=True)
+    parser.add_argument("--save-path", type=str, required=True)
+    parser.add_argument("--n-experts", type=int, required=True)
+    parser.add_argument("--model-parallel", type=int, required=True)
+    args = parser.parse_args()
+    assert args.n_experts % args.model_parallel == 0, "Number of experts must be divisible by model parallelism"
+    main(args.hf_ckpt_path, args.save_path, args.n_experts, args.model_parallel)

inference/generate.py

@@ -0,0 +1,186 @@
+import os
+import json
+from argparse import ArgumentParser
+from typing import List
+
+import torch
+import torch.distributed as dist
+from transformers import AutoTokenizer
+from safetensors.torch import load_model
+
+from model import Transformer, ModelArgs
+
+
+def sample(logits, temperature: float = 1.0):
+    """
+    Samples a token from the logits using temperature scaling.
+
+    Args:
+        logits (torch.Tensor): The logits tensor for token predictions.
+        temperature (float, optional): Temperature for scaling logits. Defaults to 1.0.
+
+    Returns:
+        torch.Tensor: The sampled token.
+    """
+    logits = logits / max(temperature, 1e-5)
+    probs = torch.softmax(logits, dim=-1, dtype=torch.float32)
+    return probs.div_(torch.empty_like(probs).exponential_(1)).argmax(dim=-1)
+
+
+@torch.inference_mode()
+def generate(
+    model: Transformer,
+    prompt_tokens: List[List[int]],
+    max_new_tokens: int,
+    eos_id: int,
+    temperature: float = 1.0
+) -> List[List[int]]:
+    """
+    Generates new tokens based on the given prompt tokens using the specified model.
+
+    Args:
+        model (Transformer): The transformer model used for token generation.
+        prompt_tokens (List[List[int]]): A list of lists containing the prompt tokens for each sequence.
+        max_new_tokens (int): The maximum number of new tokens to generate.
+        eos_id (int): The end-of-sequence token ID.
+        temperature (float, optional): The temperature value for sampling. Defaults to 1.0.
+
+    Returns:
+        List[List[int]]: A list of lists containing the generated tokens for each sequence.
+    """
+    prompt_lens = [len(t) for t in prompt_tokens]
+    assert max(prompt_lens) <= model.max_seq_len, f"Prompt length exceeds model maximum sequence length (max_seq_len={model.max_seq_len})"
+    total_len = min(model.max_seq_len, max_new_tokens + max(prompt_lens))
+    tokens = torch.full((len(prompt_tokens), total_len), -1, dtype=torch.long, device="cuda")
+    for i, t in enumerate(prompt_tokens):
+        tokens[i, :len(t)] = torch.tensor(t, dtype=torch.long, device="cuda")
+    prev_pos = 0
+    finished = torch.tensor([False] * len(prompt_tokens), device="cuda")
+    prompt_mask = tokens != -1
+    for cur_pos in range(min(prompt_lens), total_len):
+        logits = model.forward(tokens[:, prev_pos:cur_pos], prev_pos)
+        if temperature > 0:
+            next_token = sample(logits, temperature)
+        else:
+            next_token = logits.argmax(dim=-1)
+        next_token = torch.where(prompt_mask[:, cur_pos], tokens[:, cur_pos], next_token)
+        tokens[:, cur_pos] = next_token
+        finished |= torch.logical_and(~prompt_mask[:, cur_pos], next_token == eos_id)
+        prev_pos = cur_pos
+        if finished.all():
+            break
+    completion_tokens = []
+    for i, toks in enumerate(tokens.tolist()):
+        toks = toks[prompt_lens[i]:prompt_lens[i]+max_new_tokens]
+        if eos_id in toks:
+            toks = toks[:toks.index(eos_id)]
+        completion_tokens.append(toks)
+    return completion_tokens
+
+
+def main(
+    ckpt_path: str,
+    config: str,
+    input_file: str = "",
+    interactive: bool = True,
+    max_new_tokens: int = 100,
+    temperature: float = 1.0,
+) -> None:
+    """
+    Main function to load the model and perform interactive or batch text generation.
+
+    Args:
+        ckpt_path (str): Path to the model checkpoint directory.
+        config (str): Path to the model configuration file.
+        input_file (str, optional): Path to a file containing input prompts. Defaults to "".
+        interactive (bool, optional): Whether to run in interactive mode. Defaults to True.
+        max_new_tokens (int, optional): Maximum number of new tokens to generate. Defaults to 100.
+        temperature (float, optional): Temperature for sampling. Defaults to 1.0.
+    """
+    world_size = int(os.getenv("WORLD_SIZE", "1"))
+    rank = int(os.getenv("RANK", "0"))
+    local_rank = int(os.getenv("LOCAL_RANK", "0"))
+    if world_size > 1:
+        dist.init_process_group("nccl")
+    global print
+    if rank != 0:
+        print = lambda *_, **__: None
+    torch.cuda.set_device(local_rank)
+    torch.set_default_dtype(torch.bfloat16)
+    torch.set_num_threads(8)
+    torch.manual_seed(33377335)
+    with open(config) as f:
+        args = ModelArgs(**json.load(f))
+    print(args)
+    with torch.device("cuda"):
+        model = Transformer(args)
+    tokenizer = AutoTokenizer.from_pretrained(ckpt_path)
+    print("load model")
+    load_model(model, os.path.join(ckpt_path, f"model{rank}-mp{world_size}.safetensors"))
+    print("I'm DeepSeek 👋")
+
+    if interactive:
+        messages = []
+        while True:
+            if world_size == 1:
+                prompt = input(">>> ")
+            elif rank == 0:
+                prompt = input(">>> ")
+                objects = [prompt]
+                dist.broadcast_object_list(objects, 0)
+            else:
+                objects = [None]
+                dist.broadcast_object_list(objects, 0)
+                prompt = objects[0]
+            if prompt == "/exit":
+                break
+            elif prompt == "/clear":
+                messages.clear()
+                continue
+            messages.append({"role": "user", "content": prompt})
+            prompt_tokens = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
+            completion_tokens = generate(model, [prompt_tokens], max_new_tokens, tokenizer.eos_token_id, temperature)
+            completion = tokenizer.decode(completion_tokens[0], skip_special_tokens=True)
+            print(completion)
+            messages.append({"role": "assistant", "content": completion})
+    else:
+        with open(input_file) as f:
+            prompts = f.read().split("\n\n")
+        assert len(prompts) <= args.max_batch_size, f"Number of prompts exceeds maximum batch size ({args.max_batch_size})"
+        prompt_tokens = [tokenizer.apply_chat_template([{"role": "user", "content": prompt}], add_generation_prompt=True) for prompt in prompts]
+        completion_tokens = generate(model, prompt_tokens, max_new_tokens, tokenizer.eos_token_id, temperature)
+        completions = tokenizer.batch_decode(completion_tokens, skip_special_tokens=True)
+        for prompt, completion in zip(prompts, completions):
+            print("Prompt:", prompt)
+            print("Completion:", completion)
+            print()
+
+    if world_size > 1:
+        dist.destroy_process_group()
+
+
+if __name__ == "__main__":
+    """
+    Command-line interface for distributed text generation.
+
+    Arguments:
+        --ckpt-path (str): Path to the model checkpoint directory.
+        --config (str): Path to the model configuration file.
+        --input-file (str, optional): File containing prompts for batch processing.
+        --interactive (bool, optional): Enable interactive mode for generating text.
+        --max-new-tokens (int, optional): Maximum number of new tokens to generate. Defaults to 200.
+        --temperature (float, optional): Temperature for sampling. Defaults to 0.2.
+
+    Raises:
+        AssertionError: If neither input-file nor interactive mode is specified.
+    """
+    parser = ArgumentParser()
+    parser.add_argument("--ckpt-path", type=str, required=True)
+    parser.add_argument("--config", type=str, required=True)
+    parser.add_argument("--input-file", type=str, default="")
+    parser.add_argument("--interactive", action="store_true")
+    parser.add_argument("--max-new-tokens", type=int, default=200)
+    parser.add_argument("--temperature", type=float, default=0.6)
+    args = parser.parse_args()
+    assert args.input_file or args.interactive, "Either input-file or interactive mode must be specified"
+    main(args.ckpt_path, args.config, args.input_file, args.interactive, args.max_new_tokens, args.temperature)

inference/kernel.py

@@ -0,0 +1,274 @@
+import torch
+import tilelang
+import tilelang.language as T
+from typing import Tuple, Optional
+
+
+tilelang.set_log_level("WARNING")
+
+pass_configs = {
+    tilelang.PassConfigKey.TL_DISABLE_WARP_SPECIALIZED: True,
+    tilelang.PassConfigKey.TL_DISABLE_TMA_LOWER: True,
+    tilelang.PassConfigKey.TL_DISABLE_FAST_MATH: True,
+}
+
+FP8 = "float8_e4m3"
+BF16 = "bfloat16"
+FP32 = "float32"
+
+
+def fast_log2_ceil(x):
+    bits_x = T.reinterpret("uint32", x)
+    exp_x = (bits_x >> 23) & 0xFF
+    man_bits = bits_x & ((1 << 23) - 1)
+    return T.Cast("int32", exp_x - 127 + T.if_then_else(man_bits != 0, 1, 0))
+
+
+def fast_pow2(x):
+    bits_x = (x + 127) << 23
+    return T.reinterpret("float32", bits_x)
+
+
+def fast_round_scale(amax, fp8_max_inv):
+    return fast_pow2(fast_log2_ceil(amax * fp8_max_inv))
+
+
+@tilelang.jit(pass_configs=pass_configs)
+def act_quant_kernel(
+    N, in_dtype=BF16, out_dtype=FP8, scale_dtype=FP32, round_scale=False
+):
+    M = T.symbolic("M")
+    fp8_min = -448.0
+    fp8_max = 448.0
+    fp8_max_inv = 1 / fp8_max
+    num_stages = 0 if round_scale else 2
+    blk_m = 32
+    group_size = 128
+
+    @T.prim_func
+    def act_quant_kernel_(
+        X: T.Tensor[(M, N), in_dtype],
+        Y: T.Tensor[(M, N), out_dtype],
+        S: T.Tensor[(M, T.ceildiv(N, group_size)), scale_dtype],
+    ):
+        with T.Kernel(T.ceildiv(M, blk_m), T.ceildiv(N, group_size), threads=128) as (
+            pid_m,
+            pid_n,
+        ):
+            x_shared = T.alloc_shared((blk_m, group_size), in_dtype)
+            x_local = T.alloc_fragment((blk_m, group_size), in_dtype)
+            amax_local = T.alloc_fragment((blk_m,), scale_dtype)
+            s_local = T.alloc_fragment((blk_m,), scale_dtype)
+            y_local = T.alloc_fragment((blk_m, group_size), out_dtype)
+            y_shared = T.alloc_shared((blk_m, group_size), out_dtype)
+
+            for _ in T.Pipelined(1, num_stages=num_stages):
+                T.copy(X[pid_m * blk_m, pid_n * group_size], x_shared)
+                T.copy(x_shared, x_local)
+                T.reduce_absmax(x_local, amax_local, dim=1)
+                for i in T.Parallel(blk_m):
+                    amax_local[i] = T.max(amax_local[i], 1e-4)
+                    if round_scale:
+                        s_local[i] = fast_round_scale(amax_local[i], fp8_max_inv)
+                    else:
+                        s_local[i] = amax_local[i] * fp8_max_inv
+                for i, j in T.Parallel(blk_m, group_size):
+                    y_local[i, j] = T.clamp(
+                        x_local[i, j] / s_local[i], fp8_min, fp8_max
+                    )
+                for i in T.Parallel(blk_m):
+                    S[pid_m * blk_m + i, pid_n] = s_local[i]
+                T.copy(y_local, y_shared)
+                T.copy(y_shared, Y[pid_m * blk_m, pid_n * group_size])
+
+    return act_quant_kernel_
+
+
+def act_quant(
+    x: torch.Tensor, block_size: int = 128, scale_fmt: Optional[str] = None
+) -> Tuple[torch.Tensor, torch.Tensor]:
+    """
+    Quantizes the input tensor `x` using block-wise quantization.
+
+    Args:
+        x (torch.Tensor): The input tensor to be quantized. Must be contiguous and its last dimension size must be divisible by `block_size`.
+        block_size (int, optional): The size of the blocks to be used for quantization. Default is 128.
+        scale_fmt (Optional[str], optional): The format of the scale. Default is None.
+    Returns:
+        Tuple[torch.Tensor, torch.Tensor]: A tuple containing:
+            - The quantized tensor with dtype `torch.float8_e4m3fn`.
+            - A tensor of scaling factors with dtype `torch.float32`.
+    """
+    assert x.is_contiguous(), "Input tensor must be contiguous"
+    assert x.size(-1) % block_size == 0, (
+        f"Last dimension size must be divisible by block_size (block_size={block_size})"
+    )
+    N = x.size(-1)
+    y = torch.empty_like(x, dtype=torch.float8_e4m3fn)
+    s = x.new_empty(*x.size()[:-1], N // block_size, dtype=torch.float32)
+    kernel = act_quant_kernel(N, round_scale=scale_fmt is not None)
+    kernel(x.view(-1, N), y.view(-1, N), s.view(-1, N // block_size))
+    return y, s
+
+
+@tilelang.jit(pass_configs=pass_configs)
+def fp8_gemm_kernel(N, K, out_dtype=BF16, accum_dtype="float32"):
+    assert out_dtype in [BF16, "float32"]
+
+    M = T.symbolic("M")
+    group_size = 128
+    block_M = 32
+    block_N = 128
+    block_K = 128
+
+    @T.prim_func
+    def fp8_gemm_kernel_(
+        A: T.Tensor[(M, K), FP8],
+        B: T.Tensor[(N, K), FP8],
+        C: T.Tensor[(M, N), out_dtype],
+        scales_a: T.Tensor[(M, T.ceildiv(K, group_size)), FP32],
+        scales_b: T.Tensor[(T.ceildiv(N, group_size), T.ceildiv(K, group_size)), FP32],
+    ):
+        with T.Kernel(T.ceildiv(N, block_N), T.ceildiv(M, block_M), threads=128) as (
+            bx,
+            by,
+        ):
+            A_shared = T.alloc_shared((block_M, block_K), FP8)
+            B_shared = T.alloc_shared((block_N, block_K), FP8)
+            C_shared = T.alloc_shared((block_M, block_N), out_dtype)
+            Scale_C_shared = T.alloc_shared((block_M), FP32)
+            C_local = T.alloc_fragment((block_M, block_N), accum_dtype)
+            C_local_accum = T.alloc_fragment((block_M, block_N), accum_dtype)
+
+            # Improve L2 Cache
+            T.use_swizzle(panel_size=10)
+
+            T.clear(C_local)
+            T.clear(C_local_accum)
+            K_iters = T.ceildiv(K, block_K)
+            for k in T.Pipelined(K_iters, num_stages=4):
+                # Load A into shared memory
+                T.copy(A[by * block_M, k * block_K], A_shared)
+                # Load B into shared memory
+                T.copy(B[bx * block_N, k * block_K], B_shared)
+                # Load scale into shared memory
+                Scale_B = scales_b[bx * block_N // group_size, k]
+                for i in T.Parallel(block_M):
+                    Scale_C_shared[i] = scales_a[by * block_M + i, k] * Scale_B
+
+                T.gemm(A_shared, B_shared, C_local, transpose_B=True)
+                # Promote to enable 2xAcc
+                for i, j in T.Parallel(block_M, block_N):
+                    C_local_accum[i, j] += C_local[i, j] * Scale_C_shared[i]
+                T.clear(C_local)
+            # TMA store
+            T.copy(C_local_accum, C_shared)
+            T.copy(C_shared, C[by * block_M, bx * block_N])
+
+    return fp8_gemm_kernel_
+
+
+def fp8_gemm(
+    a: torch.Tensor, a_s: torch.Tensor, b: torch.Tensor, b_s: torch.Tensor
+) -> torch.Tensor:
+    """
+    Perform a matrix multiplication using FP8 precision.
+
+    Args:
+        a (torch.Tensor): The first input matrix, must be contiguous.
+        a_s (torch.Tensor): The scaling factor for the first input matrix, must be contiguous.
+        b (torch.Tensor): The second input matrix, must be contiguous.
+        b_s (torch.Tensor): The scaling factor for the second input matrix, must be contiguous.
+
+    Returns:
+        torch.Tensor: The result of the matrix multiplication.
+    """
+    assert a.is_contiguous() and b.is_contiguous(), "Input tensors must be contiguous"
+    assert a_s.is_contiguous() and b_s.is_contiguous(), (
+        "Scaling factor tensors must be contiguous"
+    )
+    K = a.size(-1)
+    M = a.numel() // K
+    N = b.size(0)
+    c = a.new_empty(*a.size()[:-1], N, dtype=torch.get_default_dtype())
+    kernel = fp8_gemm_kernel(N, K)
+    kernel(a.view(M, K), b, c.view(M, N), a_s.view(M, -1), b_s)
+    return c
+
+
+@tilelang.jit(out_idx=[4], pass_configs=pass_configs)
+def fp8_index_kernel(h: int, d: int):
+    b = T.symbolic("b")
+    m = T.symbolic("m")
+    n = T.symbolic("n")
+
+    blk_n1 = 512
+    blk_n2 = 128
+
+    @T.prim_func
+    def fp8_index_kernel_(
+        q: T.Tensor[(b, m, h, d), FP8],
+        q_s: T.Tensor[(b, m, h), FP32],
+        k: T.Tensor[(b, n, d), FP8],
+        k_s: T.Tensor[(b, n), FP32],
+        o: T.Tensor[(b, m, n), FP32],
+    ) -> None:
+        with T.Kernel(b, m, T.ceildiv(n, blk_n1)) as (i_b, i_m, i1_n):
+            q_smem = T.alloc_shared((h, d), FP8)
+            T.copy(q[i_b, i_m, 0, 0], q_smem)
+
+            q_s_frag = T.alloc_fragment(h, FP32)
+            T.copy(q_s[i_b, i_m, 0], q_s_frag)
+
+            for i2_n in T.Pipelined(blk_n1 // blk_n2, num_stages=2):
+                k_smem = T.alloc_shared((blk_n2, d), FP8)
+                T.copy(k[i_b, i1_n * blk_n1 + i2_n * blk_n2, 0], k_smem)
+
+                k_s_frag = T.alloc_fragment(blk_n2, FP32)
+                T.copy(k_s[i_b, i1_n * blk_n1 + i2_n * blk_n2], k_s_frag)
+
+                logits = T.alloc_fragment((blk_n2, h), FP32)
+                T.gemm(
+                    k_smem,
+                    q_smem,
+                    logits,
+                    transpose_A=False,
+                    transpose_B=True,
+                    clear_accum=True,
+                )
+
+                for i_h, i3_n in T.Parallel(h, blk_n2):
+                    logits[i3_n, i_h] = T.max(logits[i3_n, i_h], 0) * q_s_frag[i_h]
+
+                logits_sum = T.alloc_fragment(blk_n2, FP32)
+                T.reduce_sum(logits, logits_sum, dim=1)
+
+                for i3_n in T.Parallel(blk_n2):
+                    logits_sum[i3_n] *= k_s_frag[i3_n]
+
+                T.copy(logits_sum, o[i_b, i_m, i1_n * blk_n1 + i2_n * blk_n2])
+
+    return fp8_index_kernel_
+
+
+def fp8_index(
+    q: torch.Tensor,
+    q_s: torch.Tensor,
+    k: torch.Tensor,
+    k_s: torch.Tensor,
+) -> torch.Tensor:
+    """
+    Perform index score using FP8 precision.
+
+    Args:
+        q (torch.Tensor): The Q tensor, must be contiguous.
+        q_s (torch.Tensor): The scaling factor for Q (float), must be contiguous.
+        k (torch.Tensor): The K tensor, must be contiguous.
+        k_s (torch.Tensor): The scaling factor for K (e8m0 here), must be contiguous.
+
+        fp8 q @ fp8 k -> fp32 logits
+        relu(fp32 logits) * q_s (weights) -> fp32 logits
+        fp32 logits -> fp32 logits_sum
+        fp32 logits_sum * k_s (e8m0) -> fp32 index_score
+    """
+    return fp8_index_kernel(q.shape[2], q.shape[3])(q, q_s, k, k_s)

inference/model.py

@@ -0,0 +1,822 @@
+import math
+from dataclasses import dataclass
+from typing import Tuple, Optional, Literal
+
+import torch
+from torch import nn
+import torch.nn.functional as F
+import torch.distributed as dist
+
+from kernel import act_quant, fp8_gemm
+
+world_size = 1
+rank = 0
+block_size = 128
+
+@dataclass
+class ModelArgs:
+    """
+    Data class for defining model arguments and hyperparameters.
+
+    Attributes:
+        max_batch_size (int): Maximum batch size.
+        max_seq_len (int): Maximum sequence length.
+        dtype (Literal["bf16", "fp8"]): Data type for computations.
+        scale_fmt (Optional[str]): Format for quantization scale.
+        vocab_size (int): Vocabulary size.
+        dim (int): Model dimension.
+        inter_dim (int): Intermediate dimension for MLP layers.
+        moe_inter_dim (int): Intermediate dimension for MoE layers.
+        n_layers (int): Number of transformer layers.
+        n_dense_layers (int): Number of dense layers in the model.
+        n_heads (int): Number of attention heads.
+        n_routed_experts (int): Number of routed experts for MoE layers.
+        n_shared_experts (int): Number of shared experts for MoE layers.
+        n_activated_experts (int): Number of activated experts in MoE layers.
+        n_expert_groups (int): Number of expert groups.
+        n_limited_groups (int): Number of limited groups for MoE routing.
+        score_func (Literal["softmax", "sigmoid"]): Scoring function for MoE routing.
+        route_scale (float): Scaling factor for routing scores.
+        q_lora_rank (int): LoRA rank for query projections.
+        kv_lora_rank (int): LoRA rank for key-value projections.
+        qk_nope_head_dim (int): Dimension for query-key projections without positional embeddings.
+        qk_rope_head_dim (int): Dimension for query-key projections with rotary embeddings.
+        v_head_dim (int): Dimension for value projections.
+        original_seq_len (int): Original sequence length.
+        rope_theta (float): Base for rotary positional encoding.
+        rope_factor (float): Scaling factor for extended sequence lengths.
+        beta_fast (int): Fast beta correction factor.
+        beta_slow (int): Slow beta correction factor.
+        mscale (float): Scaling factor for extended attention.
+    """
+    max_batch_size: int = 8
+    max_seq_len: int = 4096 * 4
+    dtype: Literal["bf16", "fp8"] = "bf16"
+    scale_fmt: Optional[str] = None
+    vocab_size: int = 102400
+    dim: int = 2048
+    inter_dim: int = 10944
+    moe_inter_dim: int = 1408
+    n_layers: int = 27
+    n_dense_layers: int = 1
+    n_heads: int = 16
+    # moe
+    n_routed_experts: int = 64
+    n_shared_experts: int = 2
+    n_activated_experts: int = 6
+    n_expert_groups: int = 1
+    n_limited_groups: int = 1
+    score_func: Literal["softmax", "sigmoid"] = "softmax"
+    route_scale: float = 1.
+    # mla
+    q_lora_rank: int = 0
+    kv_lora_rank: int = 512
+    qk_nope_head_dim: int = 128
+    qk_rope_head_dim: int = 64
+    v_head_dim: int = 128
+    # yarn
+    original_seq_len: int = 4096
+    rope_theta: float = 10000.0
+    rope_factor: float = 40
+    beta_fast: int = 32
+    beta_slow: int = 1
+    mscale: float = 1.
+
+
+class ParallelEmbedding(nn.Module):
+    """
+    Embedding layer with parallelism support across distributed processes.
+
+    Args:
+        vocab_size (int): Vocabulary size.
+        dim (int): Embedding dimension.
+    """
+    def __init__(self, vocab_size: int, dim: int):
+        super().__init__()
+        self.vocab_size = vocab_size
+        self.dim = dim
+        assert vocab_size % world_size == 0, f"Vocabulary size must be divisible by world size (world_size={world_size})"
+        self.part_vocab_size = (vocab_size // world_size)
+        self.vocab_start_idx = rank * self.part_vocab_size
+        self.vocab_end_idx = self.vocab_start_idx + self.part_vocab_size
+        self.weight = nn.Parameter(torch.empty(self.part_vocab_size, self.dim))
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        """
+        Forward pass for parallel embedding layer.
+
+        Args:
+            x (torch.Tensor): Input tensor containing token indices.
+
+        Returns:
+            torch.Tensor: Embedded representations.
+
+        Raises:
+            ValueError: If `world_size` is not defined.
+        """
+        if world_size > 1:
+            mask = (x < self.vocab_start_idx) | (x >= self.vocab_end_idx)
+            x = x - self.vocab_start_idx
+            x[mask] = 0
+        y = F.embedding(x, self.weight)
+        if world_size > 1:
+            y[mask] = 0
+            dist.all_reduce(y)
+        return y
+
+
+def linear(x: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor] = None,
+           scale_fmt: Optional[str] = None) -> torch.Tensor:
+    """
+    Applies a linear transformation to the incoming data: y = xA^T + b.
+    This function supports specialized implementations based on quantization
+    and tensor formats.
+
+    Args:
+        x (torch.Tensor): The input tensor.
+        weight (torch.Tensor): The weight tensor. It may be quantized and
+            requires dequantization for certain cases.
+        bias (Optional[torch.Tensor]): The bias tensor to be added. Default is None.
+        scale_fmt (Optional[str]): The format of scaling factors.
+
+    Returns:
+        torch.Tensor: The result of the linear transformation, which may involve
+        quantization-aware computations depending on the input parameters.
+
+    Notes:
+        - If `weight` is quantized (e.g., `element_size() == 1`), a dequantized version
+          is used for computation.
+        - For other cases, the function applies quantization to `x` and uses `fp8_gemm` for computation.
+    """
+    assert bias is None
+
+    if weight.dtype != torch.float8_e4m3fn:
+        return F.linear(x, weight)
+    else:
+        x, scale = act_quant(x, block_size, scale_fmt)
+        return fp8_gemm(x, scale, weight, weight.scale)
+
+
+class Linear(nn.Module):
+    """
+    Custom linear layer with support for quantized weights and optional bias.
+
+    Args:
+        in_features (int): Number of input features.
+        out_features (int): Number of output features.
+        bias (bool): Whether to include a bias term. Defaults to False.
+        dtype (optional): Data type for the layer. Defaults to `torch.bfloat16`.
+    """
+    dtype = torch.bfloat16
+    scale_fmt: Optional[str] = None
+
+    def __init__(self, in_features: int, out_features: int, bias: bool = False, dtype = None):
+        super().__init__()
+        self.in_features = in_features
+        self.out_features = out_features
+        self.weight = nn.Parameter(torch.empty(out_features, in_features, dtype=dtype or Linear.dtype))
+        if self.weight.element_size() == 1:
+            scale_out_features = (out_features + block_size - 1) // block_size
+            scale_in_features = (in_features + block_size - 1) // block_size
+            self.weight.scale = self.scale = nn.Parameter(torch.empty(scale_out_features, scale_in_features, dtype=torch.float32))
+        else:
+            self.register_parameter("scale", None)
+        if bias:
+            self.bias = nn.Parameter(torch.empty(out_features))
+        else:
+            self.register_parameter("bias", None)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        """
+        Forward pass for the custom linear layer.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            torch.Tensor: Transformed tensor after linear computation.
+        """
+        return linear(x, self.weight, self.bias, self.scale_fmt)
+
+
+class ColumnParallelLinear(Linear):
+    """
+    Linear layer with column parallelism, splitting output features across distributed processes.
+
+    Args:
+        in_features (int): Number of input features.
+        out_features (int): Total number of output features.
+        bias (bool): Whether to include a bias term. Defaults to False.
+        dtype (optional): Data type for the layer. Defaults to `torch.bfloat16`.
+    """
+    def __init__(self, in_features: int, out_features: int, bias: bool = False, dtype = None):
+        assert out_features % world_size == 0, f"Output features must be divisible by world size (world_size={world_size})"
+        self.part_out_features = out_features // world_size
+        super().__init__(in_features, self.part_out_features, bias, dtype)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        """
+        Forward pass for column parallel linear layer.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            torch.Tensor: Transformed tensor with column-parallel computation.
+        """
+        y = linear(x, self.weight, self.bias, self.scale_fmt)
+        return y
+
+
+class RowParallelLinear(Linear):
+    """
+    Linear layer with row parallelism, splitting input features across distributed processes.
+
+    Args:
+        in_features (int): Total number of input features.
+        out_features (int): Number of output features.
+        bias (bool): Whether to include a bias term. Defaults to False.
+        dtype (optional): Data type for the layer. Defaults to `torch.bfloat16`.
+    """
+    def __init__(self, in_features: int, out_features: int, bias: bool = False, reduce_output = True, dtype = None):
+        assert in_features % world_size == 0, f"Input features must be divisible by world size (world_size={world_size})"
+        self.part_in_features = in_features // world_size
+        self.reduce_output = reduce_output
+        super().__init__(self.part_in_features, out_features, bias, dtype)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        """
+        Forward pass for row parallel linear layer.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            torch.Tensor: Transformed tensor with row-parallel computation.
+        """
+        y = linear(x, self.weight, None, self.scale_fmt)
+        if self.reduce_output and world_size > 1:
+            y = y.float()
+            dist.all_reduce(y)
+        if self.bias is not None:
+            y += self.bias
+        return y.type_as(x)
+
+
+class RMSNorm(nn.Module):
+    """
+    Root Mean Square Layer Normalization (RMSNorm).
+
+    Args:
+        dim (int): Dimension of the input tensor.
+        eps (float): Epsilon value for numerical stability. Defaults to 1e-6.
+    """
+    def __init__(self, dim: int, eps: float = 1e-6):
+        super().__init__()
+        self.dim = dim
+        self.eps = eps
+        self.weight = nn.Parameter(torch.ones(dim, dtype=torch.float32))
+
+    def forward(self, x: torch.Tensor, residual: Optional[torch.Tensor] = None):
+        """
+        Forward pass for RMSNorm.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            torch.Tensor: Normalized tensor with the same shape as input.
+        """
+        dtype = x.dtype
+        if residual is None:
+            x = x.float()
+            var = x.pow(2).mean(-1, keepdim=True)
+            x = x * torch.rsqrt(var + self.eps)
+            return (self.weight * x).to(dtype)
+        else:
+            x = residual = x.float() + residual.float()
+            var = x.pow(2).mean(-1, keepdim=True)
+            x = x * torch.rsqrt(var + self.eps)
+            return (self.weight * x).to(dtype), residual.to(dtype)
+
+
+def precompute_freqs_cis(args: ModelArgs) -> torch.Tensor:
+    """
+    Precomputes frequency-based complex exponential values for rotary positional embeddings.
+
+    Args:
+        args (ModelArgs): Model arguments containing positional embedding parameters.
+
+    Returns:
+        torch.Tensor: Precomputed complex exponential values for positional embeddings.
+    """
+    dim = args.qk_rope_head_dim
+    seqlen = args.max_seq_len
+    beta_fast = args.beta_fast
+    beta_slow = args.beta_slow
+    base = args.rope_theta
+    factor = args.rope_factor
+
+    def find_correction_dim(num_rotations, dim, base, max_seq_len):
+        """
+        Computes the correction dimension for a given number of rotations in the rotary positional embedding.
+
+        Args:
+            num_rotations (float): Number of rotations to compute the correction for.
+            dim (int): Dimensionality of the embedding space.
+            base (float): Base value for the exponential computation.
+            max_seq_len (int): Maximum sequence length.
+
+        Returns:
+            float: The correction dimension based on the input parameters.
+        """
+        return dim * math.log(max_seq_len / (num_rotations * 2 * math.pi)) / (2 * math.log(base))
+
+    def find_correction_range(low_rot, high_rot, dim, base, max_seq_len):
+        """
+        Computes the range of correction dimensions for rotary positional embeddings.
+
+        Args:
+            low_rot (float): Lower bound for the number of rotations.
+            high_rot (float): Upper bound for the number of rotations.
+            dim (int): Dimensionality of the embedding space.
+            base (float): Base value for the exponential computation.
+            max_seq_len (int): Maximum sequence length.
+
+        Returns:
+            Tuple[int, int]: The range of correction dimensions (low, high), clamped to valid indices.
+        """
+        low = math.floor(find_correction_dim(low_rot, dim, base, max_seq_len))
+        high = math.ceil(find_correction_dim(high_rot, dim, base, max_seq_len))
+        return max(low, 0), min(high, dim-1)
+
+    def linear_ramp_factor(min, max, dim):
+        """
+        Computes a linear ramp function used to smooth values between a minimum and maximum range.
+
+        Args:
+            min (float): Minimum value for the ramp function.
+            max (float): Maximum value for the ramp function.
+            dim (int): Dimensionality of the ramp tensor.
+
+        Returns:
+            torch.Tensor: A tensor of shape (dim,) with values linearly interpolated between 0 and 1,
+                clamped to the range [0, 1].
+        """
+        if min == max:
+            max += 0.001
+        linear_func = (torch.arange(dim, dtype=torch.float32) - min) / (max - min)
+        ramp_func = torch.clamp(linear_func, 0, 1)
+        return ramp_func
+
+    freqs = 1.0 / (base ** (torch.arange(0, dim, 2, dtype=torch.float32) / dim))
+    if seqlen > args.original_seq_len:
+        low, high = find_correction_range(beta_fast, beta_slow, dim, base, args.original_seq_len)
+        smooth = 1 - linear_ramp_factor(low, high, dim // 2)
+        freqs = freqs / factor * (1 - smooth) + freqs * smooth
+
+    t = torch.arange(seqlen)
+    freqs = torch.outer(t, freqs)
+    freqs_cis = torch.polar(torch.ones_like(freqs), freqs)
+    return freqs_cis
+
+
+def apply_rotary_emb(x: torch.Tensor, freqs_cis: torch.Tensor) -> torch.Tensor:
+    """
+    Applies rotary positional embeddings to the input tensor.
+
+    Args:
+        x (torch.Tensor): Input tensor with positional embeddings to be applied.
+        freqs_cis (torch.Tensor): Precomputed complex exponential values for positional embeddings.
+
+    Returns:
+        torch.Tensor: Tensor with rotary embeddings applied.
+    """
+    dtype = x.dtype
+    x = torch.view_as_complex(x.float().view(*x.shape[:-1], -1, 2))
+    freqs_cis = freqs_cis.view(1, x.size(1), 1, x.size(-1))
+    y = torch.view_as_real(x * freqs_cis).flatten(3)
+    return y.to(dtype)
+
+
+def weight_dequant(weight, scale):
+    original_shape = weight.shape
+    assert weight.dim() == 2
+    weight = weight.view(original_shape[0] // block_size, block_size, original_shape[1] // block_size, block_size).transpose(1, 2).contiguous().view(-1, block_size * block_size)
+    weight = (weight.float() * scale.view(-1, 1).float()).to(torch.get_default_dtype()).view(original_shape[0] // block_size, original_shape[1] // block_size, block_size, block_size).transpose(1, 2).contiguous().view(original_shape)
+    return weight
+
+
+class MLA(nn.Module):
+    """
+    Multi-Head Latent Attention (MLA) Layer.
+
+    Attributes:
+        dim (int): Dimensionality of the input features.
+        n_heads (int): Number of attention heads.
+        n_local_heads (int): Number of local attention heads for distributed systems.
+        q_lora_rank (int): Rank for low-rank query projection.
+        kv_lora_rank (int): Rank for low-rank key/value projection.
+        qk_nope_head_dim (int): Dimensionality of non-positional query/key projections.
+        qk_rope_head_dim (int): Dimensionality of rotary-positional query/key projections.
+        qk_head_dim (int): Total dimensionality of query/key projections.
+        v_head_dim (int): Dimensionality of value projections.
+        softmax_scale (float): Scaling factor for softmax in attention computation.
+    """
+    def __init__(self, args: ModelArgs):
+        super().__init__()
+        self.dim = args.dim
+        self.n_heads = args.n_heads
+        self.n_local_heads = args.n_heads // world_size
+        self.q_lora_rank = args.q_lora_rank
+        self.kv_lora_rank = args.kv_lora_rank
+        self.qk_nope_head_dim = args.qk_nope_head_dim
+        self.qk_rope_head_dim = args.qk_rope_head_dim
+        self.qk_head_dim = args.qk_nope_head_dim + args.qk_rope_head_dim
+        self.v_head_dim = args.v_head_dim
+
+        if self.q_lora_rank == 0:
+            self.wq = ColumnParallelLinear(self.dim, self.n_heads * self.qk_head_dim)
+        else:
+            self.wq_a = Linear(self.dim, self.q_lora_rank)
+            self.q_norm = RMSNorm(self.q_lora_rank)
+            self.wq_b = ColumnParallelLinear(self.q_lora_rank, self.n_heads * self.qk_head_dim)
+        self.wkv_a = Linear(self.dim, self.kv_lora_rank + self.qk_rope_head_dim)
+        self.kv_norm = RMSNorm(self.kv_lora_rank)
+        self.wkv_b = ColumnParallelLinear(self.kv_lora_rank, self.n_heads * (self.qk_nope_head_dim + self.v_head_dim))
+        self.wo = RowParallelLinear(self.n_heads * self.v_head_dim, self.dim)
+        self.softmax_scale = self.qk_head_dim ** -0.5
+        if args.max_seq_len > args.original_seq_len:
+            mscale = 0.1 * args.mscale * math.log(args.rope_factor) + 1.0
+            self.softmax_scale = self.softmax_scale * mscale * mscale
+
+        self.register_buffer("kv_cache", torch.zeros(args.max_batch_size, args.max_seq_len, self.kv_lora_rank), persistent=False)
+        self.register_buffer("pe_cache", torch.zeros(args.max_batch_size, args.max_seq_len, self.qk_rope_head_dim), persistent=False)
+        self.dequant_wkv_b = None
+
+    def forward(self, x: torch.Tensor, start_pos: int, freqs_cis: torch.Tensor, mask: Optional[torch.Tensor]):
+        """
+        Forward pass for the Multi-Head Latent Attention (MLA) Layer.
+
+        Args:
+            x (torch.Tensor): Input tensor of shape (batch_size, seq_len, dim).
+            start_pos (int): Starting position in the sequence for caching.
+            freqs_cis (torch.Tensor): Precomputed complex exponential values for rotary embeddings.
+            mask (Optional[torch.Tensor]): Mask tensor to exclude certain positions from attention.
+
+        Returns:
+            torch.Tensor: Output tensor with the same shape as the input.
+        """
+        bsz, seqlen, _ = x.size()
+        end_pos = start_pos + seqlen
+        if self.q_lora_rank == 0:
+            q = self.wq(x)
+        else:
+            q = self.wq_b(self.q_norm(self.wq_a(x)))
+        q = q.view(bsz, seqlen, self.n_local_heads, self.qk_head_dim)
+        q_nope, q_pe = torch.split(q, [self.qk_nope_head_dim, self.qk_rope_head_dim], dim=-1)
+        q_pe = apply_rotary_emb(q_pe, freqs_cis)
+        kv = self.wkv_a(x)
+        kv, k_pe = torch.split(kv, [self.kv_lora_rank, self.qk_rope_head_dim], dim=-1)
+        kv = self.kv_norm(kv)
+        k_pe = apply_rotary_emb(k_pe.unsqueeze(2), freqs_cis)
+        self.kv_cache[:bsz, start_pos:end_pos] = kv
+        self.pe_cache[:bsz, start_pos:end_pos] = k_pe.squeeze(2)
+        if mask is not None:    # MHA prefill
+            q = torch.cat([q_nope, q_pe], dim=-1)
+            kv = self.wkv_b(kv)
+            kv = kv.view(bsz, seqlen, self.n_local_heads, self.qk_nope_head_dim + self.v_head_dim)
+            k_nope, v = torch.split(kv, [self.qk_nope_head_dim, self.v_head_dim], dim=-1)
+            k = torch.cat([k_nope, k_pe.expand(-1, -1, self.n_local_heads, -1)], dim=-1)
+            scores = torch.einsum("bshd,bthd->bsht", q, k) * self.softmax_scale
+            scores += mask.unsqueeze(1)
+            scores = scores.softmax(dim=-1, dtype=torch.float32)
+            x = torch.einsum("bsht,bthd->bshd", scores.type_as(x), v)
+        else:                   # MHA decode
+            if self.dequant_wkv_b is None and self.wkv_b.scale is not None:
+                self.dequant_wkv_b = weight_dequant(self.wkv_b.weight, self.wkv_b.scale)
+            wkv_b = self.wkv_b.weight if self.dequant_wkv_b is None else self.dequant_wkv_b
+            wkv_b = wkv_b.view(self.n_local_heads, -1, self.kv_lora_rank)
+            q_nope = torch.einsum("bshd,hdc->bshc", q_nope, wkv_b[:, :self.qk_nope_head_dim])
+            scores = (torch.einsum("bshc,btc->bsht", q_nope, self.kv_cache[:bsz, :end_pos]) +
+                      torch.einsum("bshr,btr->bsht", q_pe, self.pe_cache[:bsz, :end_pos])) * self.softmax_scale
+            scores = scores.softmax(dim=-1, dtype=torch.float32)
+            x = torch.einsum("bsht,btc->bshc", scores.type_as(x), self.kv_cache[:bsz, :end_pos])
+            x = torch.einsum("bshc,hdc->bshd", x, wkv_b[:, -self.v_head_dim:])
+        x = self.wo(x.flatten(2))
+        return x
+
+
+class MLP(nn.Module):
+    """
+    Multi-Layer Perceptron (MLP) used as a feed-forward layer.
+
+    Attributes:
+        w1 (nn.Module): Linear layer for input-to-hidden transformation.
+        w2 (nn.Module): Linear layer for hidden-to-output transformation.
+        w3 (nn.Module): Additional linear layer for feature transformation.
+    """
+    def __init__(self, dim: int, inter_dim: int, reduce_output: bool = True):
+        """
+        Initializes the MLP layer.
+
+        Args:
+            dim (int): Input and output dimensionality.
+            inter_dim (int): Hidden layer dimensionality.
+        """
+        super().__init__()
+        self.w1 = ColumnParallelLinear(dim, inter_dim)
+        self.w2 = RowParallelLinear(inter_dim, dim, reduce_output=reduce_output)
+        self.w3 = ColumnParallelLinear(dim, inter_dim)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        """
+        Forward pass for the MLP layer.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            torch.Tensor: Output tensor after MLP computation.
+        """
+        return self.w2((F.silu(self.w1(x).float()) * self.w3(x).float()).type_as(x))
+
+
+class Gate(nn.Module):
+    """
+    Gating mechanism for routing inputs in a mixture-of-experts (MoE) model.
+
+    Attributes:
+        dim (int): Dimensionality of input features.
+        topk (int): Number of top experts activated for each input.
+        n_groups (int): Number of groups for routing.
+        topk_groups (int): Number of groups to route inputs to.
+        score_func (str): Scoring function ('softmax' or 'sigmoid').
+        route_scale (float): Scaling factor for routing weights.
+        weight (torch.nn.Parameter): Learnable weights for the gate.
+        bias (Optional[torch.nn.Parameter]): Optional bias term for the gate.
+    """
+    def __init__(self, args: ModelArgs):
+        """
+        Initializes the Gate module.
+
+        Args:
+            args (ModelArgs): Model arguments containing gating parameters.
+        """
+        super().__init__()
+        self.dim = args.dim
+        self.topk = args.n_activated_experts
+        self.n_groups = args.n_expert_groups
+        self.topk_groups = args.n_limited_groups
+        self.score_func = args.score_func
+        self.route_scale = args.route_scale
+        self.weight = nn.Parameter(torch.empty(args.n_routed_experts, args.dim))
+        self.bias = nn.Parameter(torch.empty(args.n_routed_experts, dtype=torch.float32)) if self.dim == 7168 else None
+
+    def forward(self, x: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
+        """
+        Forward pass for the gating mechanism.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            Tuple[torch.Tensor, torch.Tensor]: Routing weights and selected expert indices.
+        """
+        scores = linear(x.float(), self.weight.float())
+        if self.score_func == "softmax":
+            scores = scores.softmax(dim=-1)
+        else:
+            scores = scores.sigmoid()
+        original_scores = scores
+        if self.bias is not None:
+            scores = scores + self.bias
+        if self.n_groups > 1:
+            scores = scores.view(x.size(0), self.n_groups, -1)
+            if self.bias is None:
+                group_scores = scores.amax(dim=-1)
+            else:
+                group_scores = scores.topk(2, dim=-1)[0].sum(dim=-1)
+            indices = group_scores.topk(self.topk_groups, dim=-1)[1]
+            mask = scores.new_ones(x.size(0), self.n_groups, dtype=bool).scatter_(1, indices, False)
+            scores = scores.masked_fill_(mask.unsqueeze(-1), float("-inf")).flatten(1)
+        indices = scores.topk(self.topk, dim=-1)[1]
+        weights = original_scores.gather(1, indices)
+        if self.score_func == "sigmoid":
+            weights /= weights.sum(dim=-1, keepdim=True)
+        weights *= self.route_scale
+        return weights, indices
+
+
+class Expert(nn.Module):
+    """
+    Expert layer for Mixture-of-Experts (MoE) models.
+
+    Attributes:
+        w1 (nn.Module): Linear layer for input-to-hidden transformation.
+        w2 (nn.Module): Linear layer for hidden-to-output transformation.
+        w3 (nn.Module): Additional linear layer for feature transformation.
+    """
+    def __init__(self, dim: int, inter_dim: int):
+        """
+        Initializes the Expert layer.
+
+        Args:
+            dim (int): Input and output dimensionality.
+            inter_dim (int): Hidden layer dimensionality.
+        """
+        super().__init__()
+        self.w1 = Linear(dim, inter_dim)
+        self.w2 = Linear(inter_dim, dim)
+        self.w3 = Linear(dim, inter_dim)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        """
+        Forward pass for the Expert layer.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            torch.Tensor: Output tensor after expert computation.
+        """
+        return self.w2((F.silu(self.w1(x).float()) * self.w3(x).float()).type_as(x))
+
+
+class MoE(nn.Module):
+    """
+    Mixture-of-Experts (MoE) module.
+
+    Attributes:
+        dim (int): Dimensionality of input features.
+        n_routed_experts (int): Total number of experts in the model.
+        n_local_experts (int): Number of experts handled locally in distributed systems.
+        n_activated_experts (int): Number of experts activated for each input.
+        gate (nn.Module): Gating mechanism to route inputs to experts.
+        experts (nn.ModuleList): List of expert modules.
+        shared_experts (nn.Module): Shared experts applied to all inputs.
+    """
+    def __init__(self, args: ModelArgs):
+        """
+        Initializes the MoE module.
+
+        Args:
+            args (ModelArgs): Model arguments containing MoE parameters.
+        """
+        super().__init__()
+        self.dim = args.dim
+        assert args.n_routed_experts % world_size == 0, f"Number of experts must be divisible by world size (world_size={world_size})"
+        self.n_routed_experts = args.n_routed_experts
+        self.n_local_experts = args.n_routed_experts // world_size
+        self.n_activated_experts = args.n_activated_experts
+        self.experts_start_idx = rank * self.n_local_experts
+        self.experts_end_idx = self.experts_start_idx + self.n_local_experts
+        self.gate = Gate(args)
+        self.experts = nn.ModuleList([Expert(args.dim, args.moe_inter_dim) if self.experts_start_idx <= i < self.experts_end_idx else None
+                                      for i in range(self.n_routed_experts)])
+        self.shared_experts = MLP(args.dim, args.n_shared_experts * args.moe_inter_dim, reduce_output=False)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        """
+        Forward pass for the MoE module.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            torch.Tensor: Output tensor after expert routing and computation.
+        """
+        shape = x.size()
+        x = x.view(-1, self.dim)
+        weights, indices = self.gate(x)
+        y = torch.zeros_like(x, dtype=torch.float32)
+        counts = torch.bincount(indices.flatten(), minlength=self.n_routed_experts).tolist()
+        for i in range(self.experts_start_idx, self.experts_end_idx):
+            if counts[i] == 0:
+                continue
+            expert = self.experts[i]
+            idx, top = torch.where(indices == i)
+            y[idx] += expert(x[idx]) * weights[idx, top, None]
+        y += self.shared_experts(x)
+        if world_size > 1:
+            dist.all_reduce(y)
+        return y.type_as(x).view(shape)
+
+
+class Block(nn.Module):
+    """
+    Transformer block combining attention and feed-forward layers.
+
+    Attributes:
+        attn (nn.Module): Attention layer (MLA).
+        ffn (nn.Module): Feed-forward network (MLP or MoE).
+        attn_norm (nn.Module): Layer normalization for attention.
+        ffn_norm (nn.Module): Layer normalization for feed-forward network.
+    """
+    def __init__(self, layer_id: int, args: ModelArgs):
+        """
+        Initializes the Transformer block.
+
+        Args:
+            layer_id (int): Layer index in the transformer.
+            args (ModelArgs): Model arguments containing block parameters.
+        """
+        super().__init__()
+        self.attn = MLA(args)
+        self.ffn = MLP(args.dim, args.inter_dim) if layer_id < args.n_dense_layers else MoE(args)
+        self.attn_norm = RMSNorm(args.dim)
+        self.ffn_norm = RMSNorm(args.dim)
+
+    def forward(self, x: torch.Tensor, residual: torch.Tensor, start_pos: int, freqs_cis: torch.Tensor, mask: Optional[torch.Tensor]) -> torch.Tensor:
+        """
+        Forward pass for the Transformer block.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+            start_pos (int): Starting position in the sequence.
+            freqs_cis (torch.Tensor): Precomputed complex exponential values for rotary embeddings.
+            mask (Optional[torch.Tensor]): Mask tensor to exclude certain positions from attention.
+
+        Returns:
+            torch.Tensor: Output tensor after block computation.
+        """
+        if residual is None:
+            x, residual = self.attn_norm(x), x
+        else:
+            x, residual = self.attn_norm(x, residual)
+        x = self.attn(x, start_pos, freqs_cis, mask)
+        x, residual = self.ffn_norm(x, residual)
+        x = self.ffn(x)
+        return x, residual
+
+
+class Transformer(nn.Module):
+    """
+    Transformer model with positional embeddings, multiple layers, and output projection.
+
+    Attributes:
+        max_seq_len (int): Maximum sequence length for the transformer.
+        embed (nn.Module): Embedding layer for input tokens.
+        layers (torch.nn.ModuleList): List of transformer blocks.
+        norm (nn.Module): Layer normalization applied after all blocks.
+        head (nn.Module): Output projection layer mapping to vocabulary size.
+        freqs_cis (torch.Tensor): Precomputed complex exponential values for rotary embeddings.
+    """
+    def __init__(self, args: ModelArgs):
+        """
+        Initializes the Transformer model.
+
+        Args:
+            args (ModelArgs): Model arguments containing transformer parameters.
+        """
+        global world_size, rank
+        world_size = dist.get_world_size() if dist.is_initialized() else 1
+        rank = dist.get_rank() if dist.is_initialized() else 0
+        Linear.dtype = torch.float8_e4m3fn if args.dtype == "fp8" else torch.bfloat16
+        Linear.scale_fmt = args.scale_fmt
+        super().__init__()
+        self.max_seq_len = args.max_seq_len
+        self.embed = ParallelEmbedding(args.vocab_size, args.dim)
+        self.layers = torch.nn.ModuleList()
+        for layer_id in range(args.n_layers):
+            self.layers.append(Block(layer_id, args))
+        self.norm = RMSNorm(args.dim)
+        # lm_head in the checkpoint is stored in bf16, while the parameter here is stored in fp32 for easier computation of logits later.
+        self.head = ColumnParallelLinear(args.dim, args.vocab_size, dtype=torch.float32)
+        self.register_buffer("freqs_cis", precompute_freqs_cis(args), persistent=False)
+
+    @torch.inference_mode()
+    def forward(self, tokens: torch.Tensor, start_pos: int = 0):
+        """
+        Forward pass for the Transformer model.
+
+        Args:
+            tokens (torch.Tensor): Input tensor of token IDs with shape (batch_size, seq_len).
+            start_pos (int, optional): Starting position in the sequence for rotary embeddings. Defaults to 0.
+
+        Returns:
+            torch.Tensor: Logits tensor of shape (batch_size, vocab_size).
+        """
+        seqlen = tokens.size(1)
+        freqs_cis = self.freqs_cis[start_pos:start_pos+seqlen]
+        mask = torch.full((seqlen, seqlen), float("-inf"), device=tokens.device).triu_(1) if seqlen > 1 else None
+        h, residual = self.embed(tokens), None
+        for layer in self.layers:
+            h, residual = layer(h, residual, start_pos, freqs_cis, mask)
+        h, _ = self.norm(h, residual)
+        logits = self.head(h[:, -1].float())
+        if world_size > 1:
+            all_logits = [torch.empty_like(logits) for _ in range(world_size)]
+            dist.all_gather(all_logits, logits)
+            logits = torch.cat(all_logits, dim=-1)
+        return logits
+
+
+if __name__ == "__main__":
+    torch.set_default_dtype(torch.bfloat16)
+    torch.set_default_device("cuda")
+    torch.manual_seed(0)
+    args = ModelArgs()
+    x = torch.randint(0, args.vocab_size, (2, 128))
+    model = Transformer(args)
+    print(model(x).size())

inference/requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers
+safetensors
+tilelang==0.1.6.post1

model-00001-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6140e58b5e9c4c2bded0b7a5c13c1a5601eeda5977b4d1d85c63be4fde00c48d
+size 5234241729

model-00002-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18056b701a75d11ec123573be29414222c22b1b7b64f814d98ec03df739a7030
+size 4302383966

model-00004-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69efff813da01cca14d97f4f0a9629da7c9dfb3d0517290e4b4a063ab0c24ce2
+size 4302382760

model-00005-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83dd2b06fc9a1c507b30715fc5930a09be483d004afc0a1b9080ae4f4b1de08b
+size 4302384154

model-00006-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1641062ff86a782238632431b038047e9e2a909573fa04e6b20bd613dde5b70
+size 4372106366

model-00007-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a947b03266f71f9b01b25fd007ee0a5b5ca97271ee4abb60e8f2da22de9f41
+size 4306080097

model-00008-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f219fc5097f1c7ae9bd74d9128a9d631141d79541e3c3ffc040845b7a70b9f
+size 4302384356

model-00010-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e6176a77199fba2f9418d7549f0a1da111585909ed482d2f7a1598bce08aad
+size 4302383960

model-00011-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548c7ce458921ac0707cbfe8a4483caf82b39c485cfd69ab49cca0de393d221e
+size 4302384375

model-00012-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb6adeb76bbf794e90d3f04ca5289b77b5a4b5c28b01ebe9d98a839b0d6fa17
+size 1321612611

model-00013-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c657d8f1cceb557dce5459e4635dc77cb0c04fdaaecdfa318729aae66e238ad0
+size 4302321338

model-00014-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0897fca2011cc006cfbf131b1a7edc5b7455af82b735ed775d5f5072e3a41edd
+size 4302384328

model-00015-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:469d5a28be557bcc8f4d328bbc9670093a2f059590f486c5d1919ded3fe2b7f0
+size 4302382982

model-00016-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ff6716edb896cefa13c32e420f9787c56ab46a4fe9fa1875a95f640e5615e8
+size 4302383932

model-00017-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff57950923a935810125b6358b3c8eed9351570a8acbaeaae61cb653eb166d8f
+size 4302384377

model-00019-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c2b80c31d669d196476d5100c297b76d66a1a3a50f2347685a957c944eff4a
+size 4302384124

model-00023-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dcfaeb9a21afdc824b745e0cabb52d2f5fdea7129b04a7b09863af7aea992f1
+size 4302383572

model-00024-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3f77ec7623b9237737690970fbe5b30314641c39573f9f82600b7170ec4d27
+size 4302384504

model-00025-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f060310a2586c53eaf84bdea780e03c69e87f483e113a33f22a3e148c9ec0d
+size 4302384961

model-00026-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9d0b302fa7a5f8132ba634fdbc05931e0770c9369eccf3eeec99bab171ee1c
+size 4302383384

model-00027-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90763946ff5ba7c5ab8145f0ba0e1155f8ff6123c8762114ce226f52c495b20c
+size 4302384692

model-00028-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92394afebca8edff5ec040dbd38bc7d9e38d92bb421a86cd6ef29b49d24f394f
+size 4302384963

model-00029-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77036922f1abda7d779c1787c001540d2cebd57914b703d207a8411a6cac32e6
+size 4302383212

model-00030-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f136b1509d30045c6c0db6dbd44007d90c6836353f93b42e33a925c6e7fe047
+size 4302384884

model-00031-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a93e7c380c5df0caa2ef52bffb1c1169e7c3dd1b6430d772e8a4ba54e077361
+size 4302383588

model-00032-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50edb64a3101ad5c67c6faeacdef9dc263094e7d1c21b0ac35f09875798b3380
+size 4302384488

model-00033-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc08322d21ff7038d0f5e1bba6f9ce9588d75632652beab2636430995a93c81
+size 4302384963

model-00034-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001cb7d92e64af6d7244abbca174dbe8670a70d35e3eacfe23e690c8fbd7ca38
+size 1747446144

model-00035-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08b2003c703566a172cb8fcf49a994c8902e2f190bcd3833eb763894fc637f8
+size 4302321911

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if not thinking is defined %}{% set thinking = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- if ns.is_last_user %}{{'<｜Assistant｜></think>'}}{%- endif %}{%- set ns.is_last_user = false -%}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>'+ tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}{%- else %}{{message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'<｜tool▁call▁begin｜>'+ tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}{%- if ns.is_last_user %}{{'<｜Assistant｜>'}}{%- if message['prefix'] is defined and message['prefix'] and thinking %}{{'<think>'}}  {%- else %}{{'</think>'}}{%- endif %}{%- endif %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{%- set content = message['content'] -%}{%- if '</think>' in content %}{%- set content = content.split('</think>', 1)[1] -%}{%- endif %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{{'<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endfor -%}{%- if add_generation_prompt and ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{%- if not thinking %}{{'</think>'}}{%- else %}{{'<think>'}}{%- endif %}{% endif %}"
+}