Add files using upload-large-folder tool

.gitattributes

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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,98 @@
+{
+  "architectures": [
+    "RewardModelForAutoModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "hf_reward_model.RewardModelConfig",
+    "AutoModel": "hf_reward_model.RewardModelForAutoModel"
+  },
+  "backbone_config": {
+    "_attn_implementation_autoset": true,
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 151645,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "max_window_layers": 28,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 28,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "sep_token_id": null,
+    "sliding_window": 4096,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.50.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+  },
+  "backbone_model_name_or_path": null,
+  "hidden_size": 3584,
+  "model_type": "prm_reward_model",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "trust_remote_code": true
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.50.0"
+}

hf_reward_model.py

@@ -0,0 +1,168 @@
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Dict, Optional, Tuple
+
+import torch
+from torch import nn
+from huggingface_hub import hf_hub_download
+from transformers import AutoConfig, AutoModelForCausalLM, PreTrainedModel, PretrainedConfig
+from transformers.modeling_outputs import ModelOutput
+
+
+@dataclass
+class RewardModelOutput(ModelOutput):
+    pred_scalar: torch.FloatTensor = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    past_key_values: Optional[Tuple[Tuple[torch.FloatTensor, ...], ...]] = None
+
+
+class RewardModelConfig(PretrainedConfig):
+    model_type = "prm_reward_model"
+
+    def __init__(
+        self,
+        backbone_model_name_or_path: Optional[str] = None,
+        backbone_config: Optional[Dict[str, Any]] = None,
+        hidden_size: Optional[int] = None,
+        trust_remote_code: bool = True,
+        **kwargs,
+    ) -> None:
+        super().__init__(**kwargs)
+        self.backbone_model_name_or_path = backbone_model_name_or_path
+        self.backbone_config = backbone_config or {}
+        self.hidden_size = hidden_size
+        self.trust_remote_code = trust_remote_code
+
+
+class RewardModelForAutoModel(PreTrainedModel):
+    config_class = RewardModelConfig
+    base_model_prefix = "backbone"
+    _tied_weights_keys = {}
+
+    def __init__(
+        self,
+        config: RewardModelConfig,
+        backbone: Optional[PreTrainedModel] = None,
+    ) -> None:
+        super().__init__(config)
+        if backbone is None:
+            if config.backbone_config:
+                backbone_cfg_dict = dict(config.backbone_config)
+                backbone_model_type = backbone_cfg_dict.pop("model_type", None)
+                if backbone_model_type is None:
+                    raise ValueError("backbone_config must contain `model_type`.")
+                backbone_cfg = AutoConfig.for_model(backbone_model_type, **backbone_cfg_dict)
+            elif config.backbone_model_name_or_path:
+                backbone_cfg = AutoConfig.from_pretrained(
+                    config.backbone_model_name_or_path,
+                    trust_remote_code=config.trust_remote_code,
+                )
+            else:
+                raise ValueError("Missing backbone config and backbone model path.")
+            backbone = AutoModelForCausalLM.from_config(
+                backbone_cfg,
+                trust_remote_code=config.trust_remote_code,
+            )
+        self.backbone = backbone
+
+        hidden = config.hidden_size or self.backbone.config.hidden_size
+        self.reward_mlp = nn.Sequential(
+            nn.Linear(hidden, hidden // 2),
+            nn.Tanh(),
+            nn.Linear(hidden // 2, 1),
+        ).float()
+        # Required by recent transformers versions to register tied-weights metadata.
+        self.post_init()
+        if not hasattr(self, "all_tied_weights_keys"):
+            self.all_tied_weights_keys = {}
+
+    def forward(
+        self,
+        input_ids: torch.LongTensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        **kwargs,
+    ) -> RewardModelOutput:
+        kwargs.pop("output_hidden_states", None)
+        kwargs.pop("return_dict", None)
+        outputs = self.backbone(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            output_hidden_states=True,
+            return_dict=True,
+            **kwargs,
+        )
+        hidden = outputs.hidden_states[-1]
+        pred_scalar = self.reward_mlp(hidden.float()).squeeze(-1)
+        return RewardModelOutput(
+            pred_scalar=pred_scalar,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+            past_key_values=getattr(outputs, "past_key_values", None),
+        )
+
+    def generate(self, *args, **kwargs):
+        return self.backbone.generate(*args, **kwargs)
+
+    def prepare_inputs_for_generation(self, *args, **kwargs):
+        return self.backbone.prepare_inputs_for_generation(*args, **kwargs)
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs):
+        user_wants_loading_info = kwargs.pop("output_loading_info", False)
+        kwargs["output_loading_info"] = True
+        model, loading_info = super().from_pretrained(
+            pretrained_model_name_or_path,
+            *model_args,
+            **kwargs,
+        )
+
+        missing = loading_info.get("missing_keys", [])
+        reward_missing = [k for k in missing if k.startswith("reward_mlp.")]
+        reward_head_load_source = "checkpoint_weights"
+        if reward_missing:
+            reward_path = cls._resolve_reward_head_path(pretrained_model_name_or_path, kwargs)
+            if reward_path is not None:
+                state = torch.load(str(reward_path), map_location="cpu")
+                if any(k.startswith("reward_mlp.") for k in state.keys()):
+                    state = {k.replace("reward_mlp.", "", 1): v for k, v in state.items()}
+                incompatible = model.reward_mlp.load_state_dict(state, strict=False)
+                if incompatible.missing_keys or incompatible.unexpected_keys:
+                    raise RuntimeError(
+                        "Incompatible reward_mlp.pt: "
+                        f"missing={incompatible.missing_keys}, "
+                        f"unexpected={incompatible.unexpected_keys}"
+                    )
+                reward_head_load_source = f"reward_mlp.pt:{reward_path}"
+                loading_info["missing_keys"] = [k for k in missing if not k.startswith("reward_mlp.")]
+            else:
+                raise RuntimeError(
+                    "reward_mlp weights are missing from model weights and reward_mlp.pt was not found."
+                )
+
+        model._reward_head_load_source = reward_head_load_source
+        loading_info["reward_head_load_source"] = reward_head_load_source
+
+        if user_wants_loading_info:
+            return model, loading_info
+        return model
+
+    @staticmethod
+    def _resolve_reward_head_path(pretrained_model_name_or_path, kwargs):
+        local_candidate = Path(str(pretrained_model_name_or_path)) / "reward_mlp.pt"
+        if local_candidate.exists():
+            return local_candidate
+
+        if str(pretrained_model_name_or_path).startswith("/"):
+            return None
+
+        try:
+            return hf_hub_download(
+                repo_id=str(pretrained_model_name_or_path),
+                filename="reward_mlp.pt",
+                revision=kwargs.get("revision", None),
+                token=kwargs.get("token", None),
+                subfolder=kwargs.get("subfolder", None),
+            )
+        except Exception:
+            return None

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ede2bb7b2397085ef39832dee25ccb8208bdc51d938db194bb0c4dc1864844
+size 4877661712

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f601303eb32ff915bb369acecea1918144059bec6db300d2f3ec651be1edd2
+size 4932752112

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c52f93abbc9bfd693439f0b2670783078db937b229261479713e30100f1c1c88
+size 4330866208

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f90ae2aee512627c6075b23b66695fd2ca8450f41d85e0098ae7eda2346b4c
+size 1115699684

model.safetensors.index.json

@@ -0,0 +1,350 @@
+{
+  "metadata": {
+    "total_size": 15256937476
+  },
+  "weight_map": {
+    "backbone.lm_head.weight": "model-00004-of-00004.safetensors",
+    "backbone.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "backbone.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "backbone.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "backbone.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "backbone.model.norm.weight": "model-00003-of-00004.safetensors",
+    "reward_mlp.0.bias": "model-00004-of-00004.safetensors",
+    "reward_mlp.0.weight": "model-00004-of-00004.safetensors",
+    "reward_mlp.2.bias": "model-00004-of-00004.safetensors",
+    "reward_mlp.2.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}