Upload folder using huggingface_hub

.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

README.md

@@ -0,0 +1,49 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+base_model: infgrad/Jasper-Token-Compression-600M
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- text-embeddings
+- embeddings
+- retrieval
+- mteb
+- qwen3
+- onnx
+- onnxruntime
+- cpu
+- int-8
+---
+
+# Jasper Token Compression 600M — ONNX INT-8
+
+ONNX export of [infgrad/Jasper-Token-Compression-600M](https://huggingface.co/infgrad/Jasper-Token-Compression-600M).
+
+**Precision:** INT8 (Dynamic)  
+**Quantization:** Dynamic INT8  
+**Model size:** 583.56 MiB
+
+Dynamic INT8 ONNX export optimized for fast CPU inference. This is a text embedding model.
+
+## Benchmarks
+
+| Tokens | Median latency | Tokens/s |
+|---:|---:|---:|
+| 32 | 44.362 ms | 721.3 |
+| 128 | 48.609 ms | 2,633.3 |
+| 512 | 63.180 ms | 8,103.8 |
+| 1024 | 84.619 ms | 12,101.3 |
+
+## Fidelity
+
+Median cosine similarity versus FP32: ~0.988–0.992.
+
+## Attribution
+
+Original model: `infgrad/Jasper-Token-Compression-600M`

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "JasperV2Encoder"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModel": "modeling_qwen3_jasper.JasperV2Encoder"
+  },
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

config_sentence_transformers.json

@@ -0,0 +1,8 @@
+{
+  "prompts": {
+    "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: ",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

configuration.json

@@ -0,0 +1,5 @@
+{
+  "framework": "pytorch",
+  "task": "text-generation",
+  "allow_remote": true
+}

custom_st.py

@@ -0,0 +1,9 @@
+import torch
+from sentence_transformers.models import Transformer as BaseTransformer
+
+
+class JasperTransformer(BaseTransformer):
+    def forward(self, features: dict[str, torch.Tensor], **kwargs) -> dict[str, torch.Tensor]:
+        vectors = self.auto_model(**features, **kwargs)
+        features.update({"sentence_embedding": vectors})
+        return features

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2dfb2f44c38bf2a3db867a000b01a6bb58e0ea3893bea098e9e963a14452040
+size 611907051

modeling_qwen3_jasper.py

@@ -0,0 +1,145 @@
+import random
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from transformers import Qwen3PreTrainedModel, Qwen3Config, Qwen3Model
+from transformers.models.qwen3.modeling_qwen3 import Qwen3MLP
+
+
+class TokenCompressor(nn.Module):
+    """
+    Adaptive Token Compression Module
+    For sequences exceeding the threshold length, use adaptive_avg_pool1d for compression
+    Compressed length = threshold + excess_part * compression_ratio
+    """
+
+    def __init__(self, length_threshold: int = 512, compression_ratio: float = 0.3):
+        super().__init__()
+        self.length_threshold = length_threshold
+        self.compression_ratio = compression_ratio
+
+    def forward(
+            self, token_embeddings: torch.Tensor, attention_mask: torch.Tensor
+    ) -> tuple[torch.Tensor, torch.Tensor]:
+        """
+        Perform adaptive compression on token embeddings
+        Args:
+            token_embeddings: [batch_size, seq_len, hidden_size]
+            attention_mask: [batch_size, seq_len]
+        Returns:
+            compressed_embeddings: Compressed embeddings
+            compressed_mask: Compressed attention mask
+        """
+        padding_side = 'right' if (attention_mask[:, -1] == 0).any() else 'left'
+
+        compressed_embeddings_list = []
+        compressed_masks_list = []
+        for text_idx in range(token_embeddings.shape[0]):
+            # Get the effective length of current sample
+            real_length = int(attention_mask[text_idx].sum().item())
+            if real_length <= self.length_threshold:
+                # Extract valid token embeddings based on padding direction
+                if padding_side == 'left':
+                    # Left padding: valid tokens are on the right
+                    valid_embeddings = token_embeddings[text_idx:text_idx + 1, -real_length:, :]
+                else:
+                    # Right padding: valid tokens are on the left
+                    valid_embeddings = token_embeddings[text_idx:text_idx + 1, :real_length, :]
+                compressed_embeddings_list.append(valid_embeddings)
+                compressed_masks_list.append([1] * real_length)
+            else:
+                target_length = int(
+                    self.length_threshold + (real_length - self.length_threshold) * self.compression_ratio
+                )
+                # Extract valid token embeddings based on padding direction
+                if padding_side == 'left':
+                    # Left padding: valid tokens are on the right
+                    valid_embeddings = token_embeddings[text_idx:text_idx + 1, -real_length:, :]
+                else:
+                    # Right padding: valid tokens are on the left
+                    valid_embeddings = token_embeddings[text_idx:text_idx + 1, :real_length, :]
+
+                # Use adaptive_avg_pool1d for compression
+                compressed_embeddings_list.append(
+                    F.adaptive_avg_pool1d(
+                        valid_embeddings.transpose(1, 2), target_length
+                    ).transpose(1, 2)
+                )
+                # print("valid_embeddings.shape,target_length,compressed_embeddings_list[-1].shape",valid_embeddings.shape,target_length,compressed_embeddings_list[-1].shape)
+                compressed_masks_list.append([1] * target_length)
+
+        # Reassemble token_embeddings and attention_mask
+        new_seq_len = max((len(_mask) for _mask in compressed_masks_list))
+        new_attention_mask = torch.tensor(
+            [
+                _mask + [0] * (new_seq_len - len(_mask))
+                if padding_side == "right"
+                else
+                [0] * (new_seq_len - len(_mask)) + _mask
+                for _mask in compressed_masks_list
+            ],
+            dtype=torch.long,
+            device=token_embeddings.device
+        )
+
+        # Generate new token_embeddings
+        batch_size = token_embeddings.shape[0]
+        hidden_size = token_embeddings.shape[2]
+        new_token_embeddings = torch.zeros(
+            batch_size, new_seq_len, hidden_size,
+            dtype=token_embeddings.dtype,
+            device=token_embeddings.device
+        )
+
+        for idx, compressed_emb in enumerate(compressed_embeddings_list):
+            seq_len = compressed_emb.shape[1]
+            if padding_side == "right":
+                new_token_embeddings[idx, :seq_len, :] = compressed_emb.squeeze(0)
+            else:
+                # print("new_token_embeddings.shape,compressed_emb.shape",new_token_embeddings.shape,compressed_emb.shape)
+                new_token_embeddings[idx, -seq_len:, :] = compressed_emb.squeeze(0)
+
+        return new_token_embeddings, new_attention_mask
+
+
+class JasperV2Encoder(Qwen3PreTrainedModel):
+
+    def __init__(self, config: Qwen3Config):
+        super().__init__(config)
+        self.model = Qwen3Model(config)
+        self.jasper_mlp = Qwen3MLP(config=config)
+        self.linear_1 = nn.Linear(in_features=config.hidden_size, out_features=2048, bias=True)
+        self.token_compressor = TokenCompressor(length_threshold=80, compression_ratio=0.5)
+        self.post_init()
+
+    def forward(
+            self,
+            input_ids: torch.Tensor,
+            attention_mask: torch.Tensor,
+            *args,
+            **kwargs
+    ) -> torch.Tensor:
+        # token_embeddings.shape batch_size*seq_len*hidden_size
+        token_embeddings = self.model.embed_tokens(input_ids)
+        token_embeddings = self.jasper_mlp(token_embeddings)
+
+        self.token_compressor.compression_ratio = kwargs.get(
+            "compression_ratio",
+            self.token_compressor.compression_ratio
+        )
+        compressed_token_embeddings, attention_mask = self.token_compressor(token_embeddings, attention_mask)
+        compressed_token_embeddings = self.model(
+            inputs_embeds=compressed_token_embeddings, attention_mask=attention_mask
+        )["last_hidden_state"]
+
+        # Generate sentence vector
+        input_mask_expanded = (
+            attention_mask.unsqueeze(-1).expand(compressed_token_embeddings.size()).to(
+                compressed_token_embeddings.dtype)
+        )
+        sum_embeddings = torch.sum(compressed_token_embeddings * input_mask_expanded, 1)
+        sum_mask = input_mask_expanded.sum(1)
+        sum_mask = torch.clamp(sum_mask, min=1e-9)
+        vector = sum_embeddings / sum_mask
+        return self.linear_1(vector)

modules.json

@@ -0,0 +1,17 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "custom_st.JasperTransformer",
+    "kwargs": [
+      "compression_ratio"
+    ]
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,7 @@
+{
+    "max_seq_length": 32768,
+    "do_lower_case": false,
+    "tokenizer_args": {
+        "padding_side": "left"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
+size 11423705

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "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
+}