Add files using upload-large-folder tool

.gitattributes

@@ -1,35 +1,39 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+images/fenghe_evaluation_system.png filter=lfs diff=lfs merge=lfs -text
+images/fenghe.png filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text
+*.jinja filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,212 @@
+---
+license: mit
+language:
+  - zh
+  - en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+  - glm4_moe
+  - meteorology
+  - weather
+  - weather-service
+  - chinese
+  - conversational
+  - text-generation
+---
+
+# FengHe
+
+![FengHe Overview](images/fenghe.png)
+
+## Model Summary
+
+**FengHe** is a meteorological service domain large language model developed by the Public Meteorological Service Center of China Meteorological Administration based on GLM-4.5-Air. It is further trained with over **50 million tokens** of high-quality meteorological service corpus and **490,000** scenario-oriented instruction-tuning examples.
+
+FengHe is the first large language model in China specifically designed for the meteorological service domain. It is optimized for meteorological service requirement understanding, service-oriented content generation, meteorological reasoning and decision support, and meteorological service tool calling.
+
+## Model Availability
+
+This repository provides the complete FengHe model release, including the Model Card, model weights, configuration files, tokenizer files, training data description, and evaluation result visualizations.
+
+The model can be loaded directly with Transformers, vLLM, or SGLang.
+
+## Model Details
+
+| Item                 | Description                                                                                    |
+| -------------------- | ---------------------------------------------------------------------------------------------- |
+| Model name           | FengHe                                                                                         |
+| Model type           | Meteorological service domain large language model                                             |
+| Base model           | GLM-4.5-Air                                                                                          |
+| Architecture         | Mixture-of-Experts, Causal Language Model                                                      |
+| Total parameters     | 106B                                                                                           |
+| Activated parameters | 12B                                                                                            |
+| Context length       | 128K tokens                                                                                    |
+| Training precision   | BF16                                                                                           |
+| License              | MIT                                                                                            |
+| Languages            | Chinese, English                                                                               |
+| Domain               | Meteorological services, weather forecasting, warning services, decision support, tool calling |
+
+## Architecture
+
+FengHe inherits the MoE architecture and hybrid reasoning capability of GLM. It supports reasoning-oriented generation for complex tasks and direct-response generation for real-time interactions.
+
+| Parameter               | Value                |
+| ----------------------- | -------------------- |
+| Architecture            | `Glm4MoeForCausalLM` |
+| Model type              | `glm4_moe`           |
+| Number of hidden layers | 46                   |
+| Hidden size             | 4096                 |
+| Intermediate size       | 10944                |
+| MoE intermediate size   | 1408                 |
+| Attention heads         | 96                   |
+| Key-value heads         | 8                    |
+| Routed experts          | 128                  |
+| Shared experts          | 1                    |
+| Experts per token       | 8                    |
+| Head dimension          | 128                  |
+| Max position embeddings | 131072               |
+| Vocabulary size         | 151552               |
+| Activation function     | SiLU                 |
+| Normalization           | RMSNorm              |
+| RoPE theta              | 1000000              |
+| Torch dtype             | BF16                 |
+
+## Training Data
+
+FengHe is trained on a high-quality meteorological service corpus built from multiple professional data sources, including:
+
+* Meteorological books
+* Meteorological industry standards
+* National standards
+* Warning translation texts
+* Meteorological service reports
+* Meteorological news and information
+* Scenario-oriented meteorological question-answering instructions
+
+Based on these sources, we constructed a high-quality meteorological service corpus of over **50 million tokens** and manually annotated **490,000** scenario-oriented meteorological instruction examples. These data improve the model's professional expression, business understanding, reasoning, decision-support capability, and tool-calling ability in the meteorological service domain.
+
+## Capabilities
+
+FengHe is optimized for meteorological service scenarios, with improvements in the following capabilities:
+
+1. **Meteorological service requirement understanding**
+   Understands user needs in weather forecasting, severe weather, warning services, event support, public services, and decision-support scenarios.
+
+2. **Meteorological service content generation**
+   Generates service-oriented meteorological texts for the public, industry users, and decision makers, including weather briefings, service reports, risk alerts, and warning interpretations.
+
+3. **Meteorological reasoning and decision support**
+   Performs analysis, summarization, judgment, and decision-support reasoning based on meteorological facts, forecast information, disaster risks, and service scenarios.
+
+4. **Meteorological service tool calling**
+   Supports tool calling and workflow orchestration for meteorological query, data retrieval, product generation, warning services, and related tasks.
+
+## Evaluation
+
+We evaluate FengHe on **MetsEval-1k**, a meteorological service evaluation benchmark containing **1,076 questions** across 4 dimensions:
+
+* Meteorological service requirement understanding
+* Meteorological service content generation
+* Meteorological reasoning and decision support
+* Meteorological service tool calling
+
+![FengHe MetsEval-1k Evaluation](images/fenghe_evaluation_system.png)
+
+The results show that FengHe achieves a higher overall score on MetsEval-1k than other mainstream general-purpose large language models, demonstrating its domain-specific advantages in meteorological services.
+
+![FengHe MetsEval-1k Evaluation](images/fenghe_metseval_1k.png)
+
+## Quick Start
+
+### Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "PMSCCMA/FengHe"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+messages = [
+    {
+        "role": "user",
+        "content": "Please generate a public-facing risk advisory for heavy rainfall."
+    }
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device)
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=512,
+    temperature=0.6,
+    top_p=0.9,
+)
+
+response = tokenizer.decode(
+    outputs[0][inputs["input_ids"].shape[-1]:],
+    skip_special_tokens=True,
+)
+
+print(response)
+```
+
+### vLLM
+
+```bash
+vllm serve PMSCCMA/FengHe \
+  --tensor-parallel-size 8 \
+  --served-model-name fenghe
+```
+
+### SGLang
+
+```bash
+python3 -m sglang.launch_server \
+  --model-path PMSCCMA/FengHe \
+  --tp-size 8 \
+  --host 0.0.0.0 \
+  --port 30000 \
+  --served-model-name fenghe
+```
+
+Call the OpenAI-compatible API:
+
+```bash
+curl -X POST "http://localhost:30000/v1/chat/completions" \
+  -H "Content-Type: application/json" \
+  --data '{
+    "model": "fenghe",
+    "messages": [
+      {
+        "role": "user",
+        "content": "Please generate a meteorological service advisory for transportation under typhoon impacts."
+      }
+    ],
+    "temperature": 0.6,
+    "top_p": 0.9,
+    "max_tokens": 512
+  }'
+```
+
+## Usage Statement
+
+FengHe is released for meteorological services, research, industry application development, and agent system construction. Users should comply with applicable laws, regulations, industry standards, and meteorological service requirements. The model must not be used to generate fake warnings, misleading meteorological information, or any content that may pose public safety risks.
+
+## License
+
+This model is released under the **MIT License**. It can be used for research, commercial applications, and secondary development, subject to the terms of the MIT License.

chat_template.jinja

@@ -0,0 +1,103 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{{ visible_text(m.content) }}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "first_k_dense_replace": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1408,
+  "n_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.54.1"
+}

model-00001-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2abfa02607486ee45cd6e0f509e4f6416430286fbbfbe2a18596ebd7666b00c
+size 4991854888

model-00002-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0427641aab3d47603e1798de5fa33f6404c2adeafbc1450e297fcf3fa61dcfd
+size 4994465672

model-00003-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462665b25b502314e7e7f4fe49ce1ae29dd92a593e06e75c37de22123938d2a7
+size 4994465696

model-00004-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781a3188bcfff4b5191f92cfbc4b161bbc722b7a9aab7a475c1cbca95c37097d
+size 4994465696

model-00005-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac9839557a4c53a5ded62e404f2e07d8a5616c4059b3b86d732804120b695b8
+size 4994465696

model-00006-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16fe982240f5fcabe8d8f2b781c90141dcb702935bfc8add8398b1d0f0d29d8
+size 4974587952

model-00007-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6895b9baa85b821f9d2a54b097fdb4ecd9d4e63fac4e9ad3d09f68a64b67ff0
+size 4991318928

model-00008-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393ff9f46bff6dd287ce6abcf3d0b601c10541fc6345a804752cb2045d80f1fe
+size 4994465664

model-00009-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261d2ec1fa63b4769dd77f945ddd32f78bf389467b493daf1a7ea52cccfcb9d2
+size 4994465784

model-00010-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f82d648cd4957573ec7ba83ca5fc6f1633875f0ab7db488711e53c2680ed445
+size 4994466104

model-00011-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da98491f371e5745913172bb98fe4fcfdf859e2ba641634b05c851dd76793d19
+size 4994466104

model-00012-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db9989e9d2fd49d24bacd0faf5e128ee5a9750d155625e57bf17c6ebe5018a7
+size 4994466104

model-00013-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764fbce2d7af87fa631170f30f64fe3a47fe898d708e3704ce673ae92512bfa5
+size 4994466104

model-00014-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65985af103f7400ffc3dc69d53c64a534b001d8fed36a6c09fa794239e442469
+size 4994466104

model-00015-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f0093c6fdce9d790bf8d3dcff78b9646bd9932bb7451de0819162a753833f5
+size 4994466104

model-00016-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91437bf2a49b09701ad314533d45d37aa1b20b7a959a63aadda3447ca8583cf
+size 4994466104

model-00017-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6c86367bbb0e5fa1248e01267a11bb14085b029b9f70d432662c60c6f9b9bc
+size 4994466104

model-00018-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c52ef84bd4b9583a82704ebe3908f07d9bab1ab82c95aa1c4e405d920a9d4262
+size 4994466112

model-00019-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cfdc795ac1df95d6a9eb84f14fe20f00e7cf3a667df620251886f753eb8d425
+size 4994466120

model-00020-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b137afb14542ef7a93c1f284ceacbcbe05f81afa768d9a3b7dc3eaa16ccc0175
+size 4994466120

model-00021-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67633306b492fd70e044606121d45fb4cfcd5eb48abfc73cec565fab4505757e
+size 4992409992

model-00022-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d51ae7939ea583d1ad8e83f5004b38c2a835cfd4fb0a05bd61c94d9face545
+size 4996566656

model-00023-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc1d7f424ea1d44aab6cd483128171e7f566a070936610e2eda8836f7e278a2
+size 4994466088

model-00024-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d77445cfe665dfc38d3c4a271ca922380a9570da601ee1409c360d26fefb204
+size 4994466104

model-00025-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791eba325b431f409b48c788dba27274bff035e227a1ca9c9dd6789422bc7fba
+size 4994466104

model-00026-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4210416fcec7de9349add04c3099cd3f83c06e5f616204a63a032af273ab9c9
+size 4994466104

model-00027-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7262b763924fd9c6df5b8edead0357c6d6e6b569a9a328e444f87f5a6aa69b
+size 4994466104

model-00028-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc266f40ce468996054f68c13e88ea320c5dfe51ea4148ada02439455b768783
+size 4994466104

model-00029-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bbfa9c4d32d9d3edfc9a162c32b764ffb230b2edea247fce1376ef5aeaf71a
+size 4994466104

model-00030-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e9681d1bc782b5e58083fa34f0a3af4f7a4a0c43894d76a87e7ca3f21668486
+size 4994466104

model-00031-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b20d04250612722f321f604c197be9e12be0d3fd0549c4ddda93c84d661ba0
+size 4994466104

model-00032-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcebbd1f557888f20a356c7e7cc2093b6ecf4c3058b7bd5c46e434f342bdff5
+size 4994466104

model-00033-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa47edd1112527459b7f6daaba8d5e18bcd5a735ee5801410fb7cbd33368a69
+size 4994466112

model-00034-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eefc511cf5cd8965bf5d6306be6851be193e2e6be087bdcfc9dd5418535bbd2c
+size 4994466120

model-00035-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39074014c4dce6c7d7612acd18dc5fef22905e22604a8c2f36de5ac512786468
+size 4994466120

model-00036-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe378e71e84cc1f25816277fe2bbdb9c0ff1f070ff7601934594f89d2c62a53f
+size 4903256352

model-00037-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498e050f4e5bd309b1f3dbda7eaaef8f3fddc1b84f5a53f3a51e3a0e3d8b31f4
+size 4993444616

model-00038-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3c5aa4a1cce2f53816591c3323629468a4e4e7773e0c9f71641902ecf4888b
+size 4994466080

model-00039-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f71a6472eec04e25747d9bcb3ed3e4e851ddce0525e036a34ec638ba6ff7eb9
+size 4994466104

model-00040-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a92c117651a666244bd6e1a2f872bbf8d8a7c393a56e3d5c6428522f096f152
+size 4994466104

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
+size 19970700

tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151343": {
+      "content": "<|begin_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151344": {
+      "content": "<|end_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151345": {
+      "content": "<|begin_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151346": {
+      "content": "<|end_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151347": {
+      "content": "<|code_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151348": {
+      "content": "<|code_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151349": {
+      "content": "<|code_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151350": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151351": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151352": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151353": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151354": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151355": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151356": {
+      "content": "<arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151357": {
+      "content": "</arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151358": {
+      "content": "<arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151359": {
+      "content": "</arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151360": {
+      "content": "/nothink",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151361": {
+      "content": "<|begin_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151362": {
+      "content": "<|end_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151363": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151364": {
+      "content": "<|video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}