Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+base_model: XGenerationLab/XiYanSQL-QwenCoder-7B-2504
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- text-generation
+- quantized
+- awq
+- w4a16
+- llmcompressor
+datasets:
+- birdsql/bird-critic-1.0-open
+---
+
+# XiYanSQL-QwenCoder-7B-2504 W4A16 AWQ
+
+Quantized model derived from `XGenerationLab/XiYanSQL-QwenCoder-7B-2504`.
+
+This repository contains a locally generated quantized checkpoint ready to be uploaded to the Hugging Face Hub. The folder includes the quantized weights, tokenizer files, and the exact quantization settings used to produce this artifact.
+
+## Format
+
+- Quantization type: AWQ
+- Bits: 4-bit weights / 16-bit activations
+- Calibration dataset: `birdsql/bird-critic-1.0-open`
+- Tested backend: Transformers
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "your-hf-username/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    trust_remote_code=False,
+)
+```
+
+## About LLMToys
+
+This quantizer is hosted in the LLMToys repository: https://github.com/CyberCastle/LLMToys.
+LLMToys is a collection of practical LLM tools and experiments maintained in a single codebase. It groups reusable components for local model execution, quantization workflows, runtime tuning, and structured generation pipelines such as natural-language-to-SQL.
+
+## Quantization Configuration
+
+| Setting | Value |
+| --- | --- |
+| Base model | XGenerationLab/XiYanSQL-QwenCoder-7B-2504 |
+| Output folder | XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ |
+| Quantization scheme | AWQ |
+| Weight / activation format | W4A16 |
+| Model architecture | qwen2 |
+| Calibration dataset | birdsql/bird-critic-1.0-open |
+| Calibration split | open |
+| Dataset configuration | n/a |
+| Calibration samples used | 256 |
+| Max sequence length | 2048 |
+| Max GPU memory budget | 12.0 GiB |
+| Sequential onloading | yes |
+| Requested sequential targets | safe-auto |
+| Effective sequential targets | Qwen2Attention, Qwen2MLP |
+| Sequential targets per subgraph | 1 |
+| trust_remote_code | no |
+| Memory preflight mode | off |
+| vLLM smoke test requested | no |
+
+## Toolchain
+
+| Setting | Value |
+| --- | --- |
+| Generated at (UTC) | 2026-05-03T21:28:14Z |
+| Runner entrypoint | uv run quantizer/run.py |
+| llmcompressor | 0.10.1.dev127+g76b28ce7 |
+| transformers | 5.6.2 |
+| torch | 2.11.0+cu130 |
+| compressed-tensors | 0.15.1a20260428 |
+
+## Notes
+
+- This README is generated automatically by the quantizer so the artifact keeps its execution context.
+- Review the original base model license and any upstream usage restrictions before publishing this checkpoint.
+- If you rerun the quantizer with different settings, regenerate and upload the full output directory again.

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,98 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "group",
+          "symmetric": false,
+          "type": "int",
+          "zp_dtype": "torch.int8"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.15.1.a20260428"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "eos_token_id": 151645,
+  "max_new_tokens": 512,
+  "pad_token_id": 151643,
+  "transformers_version": "5.6.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccfbb7af34eb5360054144c9563df6674fce7da82422ac6a5652e87de59d027
+size 5570857504

recipe.yaml

@@ -0,0 +1,24 @@
+default_stage:
+  default_modifiers:
+    AWQModifier:
+      mappings:
+      - smooth_layer: re:.*input_layernorm$
+        balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*v_proj$
+        balance_layers: ['re:.*o_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*post_attention_layernorm$
+        balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*up_proj$
+        balance_layers: ['re:.*down_proj$']
+        activation_hook_target: null
+      offload_device: !!python/object/apply:torch.device [cpu]
+      duo_scaling: both
+      n_grid: 20
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: [lm_head]
+      scheme: W4A16_ASYM
+      bypass_divisibility_checks: false

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2b7649a086fbb9771cd78ec5b7ffa7069e16a82424a382950fedfa1e057861
+size 11421991

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 10240,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}