JQ quantized 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

README.md

@@ -1,3 +1,311 @@
+# Deliverance Quantization
+
+This model directory was generated by Deliverance from a local source model.
+
+- Target dtype: `Q4`
+- Quantized tensors: `196`
+- Provenance manifest: `deliverance-quantization.json`
+
 ---
+
+---
+library_name: transformers
 license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model:
+- Qwen/Qwen3-0.6B-Base
 ---
+
+# Qwen3-0.6B
+<a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+
+## Qwen3 Highlights
+
+Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
+
+- **Uniquely support of seamless switching between thinking mode** (for complex logical reasoning, math, and coding) and **non-thinking mode** (for efficient, general-purpose dialogue) **within single model**, ensuring optimal performance across various scenarios.
+- **Significantly enhancement in its reasoning capabilities**, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
+- **Superior human preference alignment**, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
+- **Expertise in agent capabilities**, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
+- **Support of 100+ languages and dialects** with strong capabilities for **multilingual instruction following** and **translation**.
+
+## Model Overview
+
+**Qwen3-0.6B** has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining & Post-training
+- Number of Parameters: 0.6B
+- Number of Paramaters (Non-Embedding): 0.44B
+- Number of Layers: 28
+- Number of Attention Heads (GQA): 16 for Q and 8 for KV
+- Context Length: 32,768 
+
+For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+
+> [!TIP]
+> If you encounter significant endless repetitions, please refer to the [Best Practices](#best-practices) section for optimal sampling parameters, and set the ``presence_penalty`` to 1.5.
+
+## Quickstart
+
+The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
+
+With `transformers<4.51.0`, you will encounter the following error:
+```
+KeyError: 'qwen3'
+```
+
+The following contains a code snippet illustrating how to use the model generate content based on given inputs. 
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen3-0.6B"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
+```
+
+For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
+- SGLang:
+    ```shell
+    python -m sglang.launch_server --model-path Qwen/Qwen3-0.6B --reasoning-parser qwen3
+    ```
+- vLLM:
+    ```shell
+    vllm serve Qwen/Qwen3-0.6B --enable-reasoning --reasoning-parser deepseek_r1
+    ```
+
+For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
+
+## Switching Between Thinking and Non-Thinking Mode
+
+> [!TIP]
+> The `enable_thinking` switch is also available in APIs created by SGLang and vLLM. 
+> Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users.
+
+### `enable_thinking=True`
+
+By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode.
+
+```python
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True  # True is the default value for enable_thinking
+)
+```
+
+In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response.
+
+> [!NOTE]
+> For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
+
+
+### `enable_thinking=False`
+
+We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.
+
+```python
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=False  # Setting enable_thinking=False disables thinking mode
+)
+```
+
+In this mode, the model will not generate any think content and will not include a `<think>...</think>` block.
+
+> [!NOTE]
+> For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
+
+### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input
+
+We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
+
+Here is an example of a multi-turn conversation:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+class QwenChatbot:
+    def __init__(self, model_name="Qwen/Qwen3-0.6B"):
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModelForCausalLM.from_pretrained(model_name)
+        self.history = []
+
+    def generate_response(self, user_input):
+        messages = self.history + [{"role": "user", "content": user_input}]
+
+        text = self.tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True
+        )
+
+        inputs = self.tokenizer(text, return_tensors="pt")
+        response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
+        response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
+
+        # Update history
+        self.history.append({"role": "user", "content": user_input})
+        self.history.append({"role": "assistant", "content": response})
+
+        return response
+
+# Example Usage
+if __name__ == "__main__":
+    chatbot = QwenChatbot()
+
+    # First input (without /think or /no_think tags, thinking mode is enabled by default)
+    user_input_1 = "How many r's in strawberries?"
+    print(f"User: {user_input_1}")
+    response_1 = chatbot.generate_response(user_input_1)
+    print(f"Bot: {response_1}")
+    print("----------------------")
+
+    # Second input with /no_think
+    user_input_2 = "Then, how many r's in blueberries? /no_think"
+    print(f"User: {user_input_2}")
+    response_2 = chatbot.generate_response(user_input_2)
+    print(f"Bot: {response_2}") 
+    print("----------------------")
+
+    # Third input with /think
+    user_input_3 = "Really? /think"
+    print(f"User: {user_input_3}")
+    response_3 = chatbot.generate_response(user_input_3)
+    print(f"Bot: {response_3}")
+```
+
+> [!NOTE]
+> For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled.
+> When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block.
+
+## Agentic Use
+
+Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
+
+To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
+```python
+from qwen_agent.agents import Assistant
+
+# Define LLM
+llm_cfg = {
+    'model': 'Qwen3-0.6B',
+
+    # Use the endpoint provided by Alibaba Model Studio:
+    # 'model_type': 'qwen_dashscope',
+    # 'api_key': os.getenv('DASHSCOPE_API_KEY'),
+
+    # Use a custom endpoint compatible with OpenAI API:
+    'model_server': 'http://localhost:8000/v1',  # api_base
+    'api_key': 'EMPTY',
+
+    # Other parameters:
+    # 'generate_cfg': {
+    #         # Add: When the response content is `<think>this is the thought</think>this is the answer;
+    #         # Do not add: When the response has been separated by reasoning_content and content.
+    #         'thought_in_content': True,
+    #     },
+}
+
+# Define Tools
+tools = [
+    {'mcpServers': {  # You can specify the MCP configuration file
+            'time': {
+                'command': 'uvx',
+                'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
+            },
+            "fetch": {
+                "command": "uvx",
+                "args": ["mcp-server-fetch"]
+            }
+        }
+    },
+  'code_interpreter',  # Built-in tools
+]
+
+# Define Agent
+bot = Assistant(llm=llm_cfg, function_list=tools)
+
+# Streaming generation
+messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
+for responses in bot.run(messages=messages):
+    pass
+print(responses)
+```
+
+## Best Practices
+
+To achieve optimal performance, we recommend the following settings:
+
+1. **Sampling Parameters**:
+   - For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions.
+   - For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
+   - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
+
+2. **Adequate Output Length**: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
+
+3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
+   - **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
+   - **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
+
+4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
+
+### Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen3technicalreport,
+      title={Qwen3 Technical Report}, 
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388}, 
+}
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 40960,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

deliverance-quantization.json

@@ -0,0 +1,2809 @@
+{
+  "schemaVersion" : 1,
+  "createdAt" : "2026-06-22T23:33:14.207790Z",
+  "sourceDirectory" : "/Users/edward.capriolo/.deliverance/Qwen_Qwen3-0.6B",
+  "outputDirectory" : "/Users/edward.capriolo/.deliverance/Qwen_Qwen3-0.6B-JQ4.tmp-6dfbb64f-4c90-4dcc-87cc-6dfac58edcf2",
+  "targetType" : "Q4",
+  "sourceSizeBytes" : 1519196091,
+  "outputSizeBytes" : 913665075,
+  "tensorTransforms" : [ {
+    "name" : "model.layers.16.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.27.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.2.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.7.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.2.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.10.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.17.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.7.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.21.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.11.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.17.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.17.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.2.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.2.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.7.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.12.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.7.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.10.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.9.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.26.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.21.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.26.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.15.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.9.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.21.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.4.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.4.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.15.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.26.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.0.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.1.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.9.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.15.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.15.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.0.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.10.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.10.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.10.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.26.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.10.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.21.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.8.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.5.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.5.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.2.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.0.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.3.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.0.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.5.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.5.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.14.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.4.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.24.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.25.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.22.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.24.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.21.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.4.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.9.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.24.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.14.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "lm_head.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 151936, 1024 ],
+    "outputShape" : [ 151936, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.15.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.19.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.9.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.27.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.6.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.23.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.10.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.24.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.12.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.12.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.18.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.17.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.15.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.19.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.16.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.13.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.18.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.18.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.26.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.14.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.13.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.13.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.18.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.1.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.0.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.17.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.0.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.19.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.9.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.13.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.22.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.12.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.23.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.13.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.2.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.5.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.3.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.4.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.25.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.6.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.26.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.7.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.24.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.20.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.21.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.27.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.20.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.22.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.7.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.16.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.11.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.16.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.16.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.11.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.mlp.up_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.11.mlp.up_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.27.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.19.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.18.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.11.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.22.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.8.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.8.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.11.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.27.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.18.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.1.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.22.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.17.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.8.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.27.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.9.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.22.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.27.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.6.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.17.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.15.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.16.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.16.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.3.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.5.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.8.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.20.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.3.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.3.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.25.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.8.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.7.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.7.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.8.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.8.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.20.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.16.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.16.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.3.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.6.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.13.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.22.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.19.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.27.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.25.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.4.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.24.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.19.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.23.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.19.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.25.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.13.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.13.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.14.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.23.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.20.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.14.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.25.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.14.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.1.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.14.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.14.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.4.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.22.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.17.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.20.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.24.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.2.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.2.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.embed_tokens.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 151936, 1024 ],
+    "outputShape" : [ 151936, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.1.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.12.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.21.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.12.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.6.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.1.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.12.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.6.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.21.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.20.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.20.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.4.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.11.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.11.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.25.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.25.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.26.mlp.down_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 3072 ],
+    "outputShape" : [ 1024, 3072 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.26.mlp.down_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.9.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.1.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.15.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.self_attn.k_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.23.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.12.input_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.3.mlp.gate_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 3072, 1024 ],
+    "outputShape" : [ 3072, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.3.mlp.gate_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.18.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.18.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.10.self_attn.q_norm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 128 ],
+    "outputShape" : [ 1, 128 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.self_attn.q_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 2048, 1024 ],
+    "outputShape" : [ 2048, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.23.self_attn.q_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.23.self_attn.o_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 2048 ],
+    "outputShape" : [ 1024, 2048 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.23.self_attn.o_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.5.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.5.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.24.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.1.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.6.self_attn.k_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.6.self_attn.k_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.0.self_attn.v_proj.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "Q4",
+    "sourceShape" : [ 1024, 1024 ],
+    "outputShape" : [ 1024, 1024 ],
+    "quantized" : true,
+    "sidecars" : [ "model.layers.0.self_attn.v_proj.weight.qb" ],
+    "oneDimensionalToRowVector" : false
+  }, {
+    "name" : "model.layers.19.post_attention_layernorm.weight",
+    "sourceDType" : "BF16",
+    "outputDType" : "BF16",
+    "sourceShape" : [ 1, 1024 ],
+    "outputShape" : [ 1, 1024 ],
+    "quantized" : false,
+    "sidecars" : [ ],
+    "oneDimensionalToRowVector" : false
+  } ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c0421e29c5a70209a383ddecba7310660d1be55e0842cffabb472572811d0b
+size 897769097

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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 message.content is string 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.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.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        {{- 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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}