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 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": [],
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:423d1cf58770f2e2fbe15e2b63597cb94272bcec427f13118c84ea9e8a80bdf4
+size 645975704

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 +1,62 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "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,
+  "transformers_version": "5.10.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064,
+  "torch_dtype": "bfloat16"
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": 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|>"
+  ],
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,336 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 42,
+  "global_step": 42,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 1.458817720413208,
+      "learning_rate": 1e-05,
+      "loss": 1.83203125,
+      "step": 1
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 1.204423427581787,
+      "learning_rate": 9.986018985905901e-06,
+      "loss": 1.53271484375,
+      "step": 2
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.9860306978225708,
+      "learning_rate": 9.944154131125643e-06,
+      "loss": 1.29736328125,
+      "step": 3
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.2528539896011353,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 1.4521484375,
+      "step": 4
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 1.0723183155059814,
+      "learning_rate": 9.777864028930705e-06,
+      "loss": 1.25830078125,
+      "step": 5
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.7818373441696167,
+      "learning_rate": 9.654368743221022e-06,
+      "loss": 0.97021484375,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.7274077534675598,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.8818359375,
+      "step": 7
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.2297133207321167,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.17919921875,
+      "step": 8
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.8559923768043518,
+      "learning_rate": 9.131193871579975e-06,
+      "loss": 0.83837890625,
+      "step": 9
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.8592395186424255,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.84228515625,
+      "step": 10
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 1.0950394868850708,
+      "learning_rate": 8.665259359149132e-06,
+      "loss": 0.875,
+      "step": 11
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.5367376804351807,
+      "learning_rate": 8.400863688854598e-06,
+      "loss": 0.63134765625,
+      "step": 12
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 0.6109802722930908,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.649169921875,
+      "step": 13
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.4308861792087555,
+      "learning_rate": 7.81660029031811e-06,
+      "loss": 0.62451171875,
+      "step": 14
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.3806557059288025,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.611083984375,
+      "step": 15
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.3664940297603607,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.58203125,
+      "step": 16
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.24358318746089935,
+      "learning_rate": 6.8267051218319766e-06,
+      "loss": 0.5665283203125,
+      "step": 17
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.1669350415468216,
+      "learning_rate": 6.473775872054522e-06,
+      "loss": 0.513427734375,
+      "step": 18
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.18984302878379822,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.5347900390625,
+      "step": 19
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.09741250425577164,
+      "learning_rate": 5.745211330880872e-06,
+      "loss": 0.39990234375,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.10498647391796112,
+      "learning_rate": 5.373650467932122e-06,
+      "loss": 0.4908447265625,
+      "step": 21
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.12174811214208603,
+      "learning_rate": 5e-06,
+      "loss": 0.4842529296875,
+      "step": 22
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 0.1169494017958641,
+      "learning_rate": 4.626349532067879e-06,
+      "loss": 0.48822021484375,
+      "step": 23
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.09415657073259354,
+      "learning_rate": 4.254788669119127e-06,
+      "loss": 0.4603271484375,
+      "step": 24
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.09546365588903427,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.4552001953125,
+      "step": 25
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.10419897735118866,
+      "learning_rate": 3.526224127945479e-06,
+      "loss": 0.46697998046875,
+      "step": 26
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.0748233050107956,
+      "learning_rate": 3.173294878168025e-06,
+      "loss": 0.4425048828125,
+      "step": 27
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.07138227671384811,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.43017578125,
+      "step": 28
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.11345721781253815,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.499267578125,
+      "step": 29
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.08105748146772385,
+      "learning_rate": 2.1833997096818897e-06,
+      "loss": 0.427734375,
+      "step": 30
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.09030455350875854,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.48150634765625,
+      "step": 31
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.10306616872549057,
+      "learning_rate": 1.5991363111454023e-06,
+      "loss": 0.4969482421875,
+      "step": 32
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.07233192026615143,
+      "learning_rate": 1.3347406408508695e-06,
+      "loss": 0.4508056640625,
+      "step": 33
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.08430902659893036,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.4718017578125,
+      "step": 34
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.08449755609035492,
+      "learning_rate": 8.688061284200266e-07,
+      "loss": 0.504638671875,
+      "step": 35
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.08751299232244492,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.507568359375,
+      "step": 36
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.10116951167583466,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.489013671875,
+      "step": 37
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.08777820318937302,
+      "learning_rate": 3.4563125677897936e-07,
+      "loss": 0.504150390625,
+      "step": 38
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.08049055933952332,
+      "learning_rate": 2.2213597106929608e-07,
+      "loss": 0.4716796875,
+      "step": 39
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.09183614701032639,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.490234375,
+      "step": 40
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 0.05638575926423073,
+      "learning_rate": 5.584586887435739e-08,
+      "loss": 0.378662109375,
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.06774341315031052,
+      "learning_rate": 1.3981014094099354e-08,
+      "loss": 0.47076416015625,
+      "step": 42
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.453369140625,
+      "eval_runtime": 1.0024,
+      "eval_samples_per_second": 3.991,
+      "eval_steps_per_second": 0.998,
+      "step": 42
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 42,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.863673959279493e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}