commit 940131f4577b8cf176123a5ebf036f7d10fb7f7a
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Fri Aug 21 01:11:17 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: jastorj/couchmind-v5.8_rl_cold_start-cw-26K-16bit
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..dffd833
--- /dev/null
+++ b/README.md
@@ -0,0 +1,242 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- text-to-sql
+- code
+- sql
+- fine-tuned
+- unsloth
+- lora
+base_model: Snowflake/Arctic-Text2SQL-R1-7B
+---
+
+# Snowflake/Arctic-Text2SQL-R1-7B Fine-tuned for NL2SQL++ v5.8_rl_cold_start
+
+This model is a fine-tuned version of [Snowflake/Arctic-Text2SQL-R1-7B](https://huggingface.co/Snowflake/Arctic-Text2SQL-R1-7B) on the NL2SQL++ v5.8_rl_cold_start dataset with code-with-thought reasoning.
+
+## Model Details
+
+- **Base Model**: Snowflake/Arctic-Text2SQL-R1-7B
+- **Task**: Text-to-SQL generation
+- **Dataset**: NL2SQL++ v5.8_rl_cold_start with code-with-thought reasoning
+- **Fine-tuning Method**: LoRA (Low-Rank Adaptation) with Unsloth
+- **Quantization**: 16-bit merged weights
+- **Training Dataset Size**: 2104 examples
+- **Validation Dataset Size**: 0 examples
+
+## Training Configuration
+
+- **output_dir**: ./saved_models
+- **per_device_train_batch_size**: 2
+- **num_train_epochs**: 3
+- **max_steps**: -1
+- **learning_rate**: 1e-05
+- **lr_scheduler_type**: SchedulerType.COSINE
+- **lr_scheduler_kwargs**: None
+- **warmup_steps**: 0.1
+- **optim**: OptimizerNames.ADAMW_TORCH_FUSED
+- **optim_args**: None
+- **weight_decay**: 0.01
+- **adam_beta1**: 0.9
+- **adam_beta2**: 0.999
+- **adam_epsilon**: 1e-08
+- **optim_target_modules**: None
+- **gradient_accumulation_steps**: 8
+- **average_tokens_across_devices**: True
+- **max_grad_norm**: 1.0
+- **label_smoothing_factor**: 0.0
+- **bf16**: True
+- **fp16**: False
+- **bf16_full_eval**: True
+- **fp16_full_eval**: False
+- **tf32**: None
+- **gradient_checkpointing**: True
+- **gradient_checkpointing_kwargs**: None
+- **torch_compile**: False
+- **torch_compile_backend**: None
+- **torch_compile_mode**: None
+- **use_liger_kernel**: False
+- **liger_kernel_config**: None
+- **use_cache**: False
+- **neftune_noise_alpha**: None
+- **torch_empty_cache_steps**: None
+- **auto_find_batch_size**: False
+- **logging_strategy**: IntervalStrategy.STEPS
+- **logging_steps**: 3
+- **logging_first_step**: False
+- **log_on_each_node**: True
+- **logging_nan_inf_filter**: True
+- **include_num_input_tokens_seen**: no
+- **log_level**: passive
+- **log_level_replica**: warning
+- **disable_tqdm**: False
+- **report_to**: ['wandb']
+- **run_name**: None
+- **project**: huggingface
+- **trackio_space_id**: trackio
+- **eval_strategy**: IntervalStrategy.STEPS
+- **eval_steps**: 50
+- **eval_delay**: 0
+- **per_device_eval_batch_size**: 5
+- **prediction_loss_only**: False
+- **eval_on_start**: False
+- **eval_do_concat_batches**: True
+- **eval_use_gather_object**: False
+- **eval_accumulation_steps**: 10
+- **include_for_metrics**: []
+- **batch_eval_metrics**: False
+- **save_only_model**: False
+- **save_strategy**: SaveStrategy.BEST
+- **save_steps**: 50
+- **save_on_each_node**: False
+- **save_total_limit**: 1
+- **enable_jit_checkpoint**: False
+- **push_to_hub**: False
+- **hub_token**: None
+- **hub_private_repo**: None
+- **hub_model_id**: None
+- **hub_strategy**: HubStrategy.EVERY_SAVE
+- **hub_always_push**: False
+- **hub_revision**: None
+- **load_best_model_at_end**: True
+- **metric_for_best_model**: eval_exec_accuracy
+- **greater_is_better**: True
+- **ignore_data_skip**: False
+- **restore_callback_states_from_checkpoint**: False
+- **full_determinism**: False
+- **seed**: 42
+- **data_seed**: None
+- **use_cpu**: False
+- **accelerator_config**: AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)
+- **parallelism_config**: None
+- **dataloader_drop_last**: False
+- **dataloader_num_workers**: 0
+- **dataloader_pin_memory**: True
+- **dataloader_persistent_workers**: False
+- **dataloader_prefetch_factor**: None
+- **remove_unused_columns**: True
+- **label_names**: None
+- **train_sampling_strategy**: random
+- **length_column_name**: length
+- **ddp_find_unused_parameters**: None
+- **ddp_bucket_cap_mb**: None
+- **ddp_broadcast_buffers**: None
+- **ddp_backend**: None
+- **ddp_timeout**: 1800
+- **fsdp**: []
+- **fsdp_config**: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- **deepspeed**: None
+- **debug**: []
+- **skip_memory_metrics**: True
+- **do_train**: False
+- **do_eval**: True
+- **do_predict**: False
+- **resume_from_checkpoint**: None
+- **warmup_ratio**: 0.1
+- **logging_dir**: None
+- **local_rank**: -1
+- **model_init_kwargs**: None
+- **chat_template_path**: None
+- **dataset_text_field**: text
+- **dataset_kwargs**: None
+- **dataset_num_proc**: None
+- **eos_token**: None
+- **pad_token**: None
+- **max_length**: 26000
+- **packing**: False
+- **packing_strategy**: bfd
+- **padding_free**: False
+- **pad_to_multiple_of**: None
+- **eval_packing**: None
+- **completion_only_loss**: None
+- **assistant_only_loss**: False
+- **loss_type**: nll
+- **activation_offloading**: False
+- **vllm_sampling_params**: None
+- **unsloth_num_chunks**: -1
+- **unsloth_logit_chunk_multiplier**: None
+- **unsloth_grpo_mini_batch**: None
+- **max_seq_length**: 26000
+- **model_name**: Snowflake/Arctic-Text2SQL-R1-7B
+- **model_specs**: ModelSpecs(instruction_part='<|im_start|>user', response_part='<|im_start|>assistant', target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'], chat_template=None)
+- **lora_use_rslora**: True
+- **lora_r**: 64
+- **lora_alpha**: 128
+- **lora_dropout**: 0.1
+- **early_stopping_patience**: 5
+
+
+## Train Dataset Example
+```
+<|im_start|>system
+You are a helpful AI Assistant that provides well-reasoned and detailed responses. You first
+think about the reasoning process as an internal monologue and then provide the user with
+the answer. Respond in the following format: <think>
+...
+</think>
+<answer>
+...
+</answer>
+<|im_end|>
+<|im_start|>user
+You are a Couchbase SQL++ query expert. Given a database schema and a natural language question, generate a syntactically valid SQL++ query that precisely answers the question.
+
+Rules:
+- SELECT only the columns explicitly asked for — nothing more, nothing less
+- Use the exact bucket, scope, and collection names provided in the database schema
+
+Bucket Name:
+`nan`
+
+Scope Name:
+`nan`
+
+Database Schema:
+{}
+
+This schema describes the structure of the data in the specified bucket and scope. It includes information about the collections, fields, and their data types.
+
+Question:
+Build the special_flights list with two objects and return the values from each object.
+<|im_end|>
+<|im_start|>assistant
+<think>
+I start by noticing there is no schema at all. So this is not a normal “read from a collection” question. There are no buckets, scopes, collections, or existing fields to join together. That means I need to construct the data inline inside the query itself.
+
+The wording is: “Build the special_flights list with two objects and return the values from each object.”
+
+A few pieces matter here.
+
+First, “build the special_flights list” suggests I should create a named list, not just throw an anonymous array into the SELECT. In SQL++ / N1QL, a clean way to do that is a WITH binding. So I want a common expression named special_flights.
+
+Second, it says “with two objects.” So special_flights should be an array containing exactly two object literals.
+
+Since there is no schema, I have to invent the object structure and values myself. The list name special_flights makes flight-oriented fields feel natural. I need a clear identifier for each object, so using a field named flight makes sense. I also want some time-like field; utc is a natural label for that. Then I can add one more descriptive field to each object to make them feel like richer objects rather than just two identical key sets.
+
+Now I need actual literal values. Because these are made-up demo rows, I want them to be memorable and obviously different. For the first one, a flight value like AI444 is easy to recognize, and I can pair it with a matching time-like string 4:44:44. For the extra descriptive field, codename with value green works well. For the second object, I can mirror that pattern with flight AI333 and utc 3:33:33, then use a different status-style key alert with value red. That also shows that the two objects do not have to share every non-core field, which is interesting for an object-values operation.
+
+So the array I am binding to special_flights is two objects:
+- one with flight AI444, utc 4:44:44, codename green
+- one with flight AI333, utc 3:33:33, alert red
+
+Next I need to “return the values from each object.” I should think about what that means in N1QL terms.
+
+One possibility is to UNNEST the array and call OBJECT_VALUES on each object individually, which would give one row per object. But the question says “build the special_flights list” first, and then “return the values from each object,” which sounds more like operating on the list as a whole rather than exploding it into separate rows. So I lean toward applying an object-values function to the list’s contents directly.
+
+The N1QL function for extracting an object’s values is OBJECT_VALUES. To apply it to the objects inside the array, I need the array-star form special_flights[*]. That notation refers to the objects in the list. Using OBJECT_VALUES on that expression gives me the values drawn from the objects in the list.
+
+Since the SELECT is just returning that one derived expression, I should give it an alias. A name like outer_values fits, because I am returning the values produced from the outer list binding.
+
+There is also no need for a FROM clause, because I am not querying any stored collection; everything comes from the WITH-defined array literal.
+
+So the final shape is: a WITH clause naming special_flights and assigning it the two-object array, then a SELECT that applies OBJECT_VALUES to special_flights[*] and aliases the result as outer_values.
+</think>
+
+<answer>
+WITH special_flights AS ([{"flight":"AI444","utc":"4:44:44","codename":"green"},{"flight":"AI333","utc":"3:33:33","alert":"red"}]) SELECT OBJECT_VALUES(special_flights[*]) AS outer_values;
+</answer>
+<|im_end|>
+
+```
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..bdf7919
--- /dev/null
+++ b/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 %}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..c511343
--- /dev/null
+++ b/config.json
@@ -0,0 +1,61 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "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": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "unsloth_version": "2026.6.9",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..e16f7a1
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151645
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151643,
+  "transformers_version": "5.5.0"
+}
diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors
new file mode 100644
index 0000000..92cf89a
--- /dev/null
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939092bd1695e96c0b6ab486dc8b45b511dcee6110aa3c3cbc03a6d4378f15b7
+size 4907182072
diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors
new file mode 100644
index 0000000..73d9206
--- /dev/null
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4a32765f2ae85acfff712b688148277b878fcd03dfb9b2e93afbf2d3a8ec85
+size 4947327992
diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors
new file mode 100644
index 0000000..f5706f9
--- /dev/null
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645f553babf1179d1c7b7267fe318cc7b1005f7dd9bff31bd94be4fd11408de8
+size 4910649832
diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors
new file mode 100644
index 0000000..2c9aeda
--- /dev/null
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d837f343c70bff2938eaeca2d260011e7f0bc6c10a0fef7836619e3c6cec08
+size 466111952
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..5f3e831
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00001-of-00004.safetensors"
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..cdc5d0d
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872cb482fb462eb1874ecef4caed88eebb3a21135e27ae5ef18f6630ae0e7edb
+size 11422433
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..95cd746
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    }
+  },
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}
\ No newline at end of file
diff --git a/train_conf.json b/train_conf.json
new file mode 100644
index 0000000..89d5ebe
--- /dev/null
+++ b/train_conf.json
@@ -0,0 +1,147 @@
+{
+  "output_dir": "./saved_models",
+  "per_device_train_batch_size": 2,
+  "num_train_epochs": 3,
+  "max_steps": -1,
+  "learning_rate": 1e-05,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_steps": 0.1,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "weight_decay": 0.01,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "optim_target_modules": null,
+  "gradient_accumulation_steps": 8,
+  "average_tokens_across_devices": true,
+  "max_grad_norm": 1.0,
+  "label_smoothing_factor": 0.0,
+  "bf16": true,
+  "fp16": false,
+  "bf16_full_eval": true,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "use_cache": false,
+  "neftune_noise_alpha": null,
+  "torch_empty_cache_steps": null,
+  "auto_find_batch_size": false,
+  "logging_strategy": "steps",
+  "logging_steps": 3,
+  "logging_first_step": false,
+  "log_on_each_node": true,
+  "logging_nan_inf_filter": true,
+  "include_num_input_tokens_seen": "no",
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "disable_tqdm": false,
+  "report_to": [
+    "wandb"
+  ],
+  "run_name": null,
+  "project": "huggingface",
+  "trackio_space_id": "trackio",
+  "eval_strategy": "steps",
+  "eval_steps": 50,
+  "eval_delay": 0,
+  "per_device_eval_batch_size": 5,
+  "prediction_loss_only": false,
+  "eval_on_start": false,
+  "eval_do_concat_batches": true,
+  "eval_use_gather_object": false,
+  "eval_accumulation_steps": 10,
+  "include_for_metrics": [],
+  "batch_eval_metrics": false,
+  "save_only_model": false,
+  "save_strategy": "best",
+  "save_steps": 50,
+  "save_on_each_node": false,
+  "save_total_limit": 1,
+  "enable_jit_checkpoint": false,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_always_push": false,
+  "hub_revision": null,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "eval_exec_accuracy",
+  "greater_is_better": true,
+  "ignore_data_skip": false,
+  "restore_callback_states_from_checkpoint": false,
+  "full_determinism": false,
+  "seed": 42,
+  "data_seed": null,
+  "use_cpu": false,
+  "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)",
+  "parallelism_config": null,
+  "dataloader_drop_last": false,
+  "dataloader_num_workers": 0,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "dataloader_prefetch_factor": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "train_sampling_strategy": "random",
+  "length_column_name": "length",
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_backend": null,
+  "ddp_timeout": 1800,
+  "fsdp": [],
+  "fsdp_config": {
+    "min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_v2": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "deepspeed": null,
+  "debug": [],
+  "skip_memory_metrics": true,
+  "do_train": false,
+  "do_eval": true,
+  "do_predict": false,
+  "resume_from_checkpoint": null,
+  "warmup_ratio": 0.1,
+  "logging_dir": null,
+  "local_rank": -1,
+  "model_init_kwargs": null,
+  "chat_template_path": null,
+  "dataset_text_field": "text",
+  "dataset_kwargs": null,
+  "dataset_num_proc": null,
+  "eos_token": null,
+  "pad_token": null,
+  "max_length": 26000,
+  "packing": false,
+  "packing_strategy": "bfd",
+  "padding_free": false,
+  "pad_to_multiple_of": null,
+  "eval_packing": null,
+  "completion_only_loss": null,
+  "assistant_only_loss": false,
+  "loss_type": "nll",
+  "activation_offloading": false,
+  "vllm_sampling_params": null,
+  "unsloth_num_chunks": -1,
+  "unsloth_logit_chunk_multiplier": null,
+  "unsloth_grpo_mini_batch": null,
+  "max_seq_length": 26000,
+  "model_name": "Snowflake/Arctic-Text2SQL-R1-7B",
+  "model_specs": "ModelSpecs(instruction_part='<|im_start|>user', response_part='<|im_start|>assistant', target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'], chat_template=None)",
+  "lora_use_rslora": true,
+  "lora_r": 64,
+  "lora_alpha": 128,
+  "lora_dropout": 0.1,
+  "early_stopping_patience": 5
+}
\ No newline at end of file