Add new SentenceTransformer model

.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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 3584,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": true,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,141 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+---
+
+# SentenceTransformer
+
+This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 3584-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 32768 tokens
+- **Output Dimensionality:** 3584 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 32768, 'do_lower_case': False}) with Transformer model: Qwen2Model 
+  (1): Pooling({'word_embedding_dimension': 3584, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("nomic-ai/qwen7b-coder-instruct-5M-last-token-causal-8e6-eos-token")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 3584]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.0
+- Transformers: 4.45.2
+- PyTorch: 2.4.1+cu121
+- Accelerate: 1.4.0
+- Datasets: 2.21.0
+- Tokenizers: 0.20.0
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

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 +1,29 @@
+{
+  "_name_or_path": "tmp",
+  "architectures": [
+    "Qwen2Model"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.0",
+    "transformers": "4.45.2",
+    "pytorch": "2.4.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33053439bc99e1fdc72a0ad6d9f0bae0b9afc84c34b51e0e8986dd769359eda
+size 4976686992

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ada145dd42a034de6267ad12d2cc02043b1bc41738590094ace97ed261e457
+size 4778621952

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d395d51ea31cd5b1551f9c15e836709f01f6af542d62089f06b7c06e709da0ff
+size 4932743600

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9090fd22409a92917dc4e14540979574c7aeaf2bac12e51402f8983d1536e4d1
+size 4932743624

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f212fd19c01b5e928fd5780257b2e4c9d617f4c3f5733294570eda2dcbe9972
+size 4998851880

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2742bab0012d717fda6e18f7efff1146f8e7f44d678dc04cac83bddca0331e8
+size 3662864928

model.safetensors.index.json

@@ -0,0 +1,345 @@
+{
+  "metadata": {
+    "total_size": 28282476544
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.26.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 32768,
+  "do_lower_case": false
+}

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 +1,207 @@
+{
+  "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        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\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\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}