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 +1,210 @@
+---
+base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-7b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.18.1

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-7b-instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36a1ad4987f8f2b5ebabb4c8fafab3db26882f667eaa2a6e7e34dbd2d687910
+size 323014168

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 %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7377d06ee92cbeaf2973793674ad9a31a640539270a606fd1f4ef967a74ff8fe
+size 164477509

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fbef07fe83f65b9a9b2dfe4cd16e244a21721410982d88a578d50c235f4409a
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "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": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,346 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8764721993974254,
+  "eval_steps": 200,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021911804984935633,
+      "grad_norm": 0.14338380098342896,
+      "learning_rate": 7.6e-05,
+      "loss": 0.578131914138794,
+      "step": 20
+    },
+    {
+      "epoch": 0.043823609969871266,
+      "grad_norm": 0.043006837368011475,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.3712817430496216,
+      "step": 40
+    },
+    {
+      "epoch": 0.0657354149548069,
+      "grad_norm": 0.05703941732645035,
+      "learning_rate": 0.00019994633460515538,
+      "loss": 0.3367295265197754,
+      "step": 60
+    },
+    {
+      "epoch": 0.08764721993974253,
+      "grad_norm": 0.04901430010795593,
+      "learning_rate": 0.00019944327493951773,
+      "loss": 0.3087886571884155,
+      "step": 80
+    },
+    {
+      "epoch": 0.10955902492467817,
+      "grad_norm": 0.06868838518857956,
+      "learning_rate": 0.00019841332314076855,
+      "loss": 0.3139586210250854,
+      "step": 100
+    },
+    {
+      "epoch": 0.1314708299096138,
+      "grad_norm": 0.07925613969564438,
+      "learning_rate": 0.00019686193632504338,
+      "loss": 0.28915910720825194,
+      "step": 120
+    },
+    {
+      "epoch": 0.15338263489454945,
+      "grad_norm": 0.07879550755023956,
+      "learning_rate": 0.00019479733438965667,
+      "loss": 0.2889900207519531,
+      "step": 140
+    },
+    {
+      "epoch": 0.17529443987948506,
+      "grad_norm": 0.06741970777511597,
+      "learning_rate": 0.00019223045646064212,
+      "loss": 0.27687640190124513,
+      "step": 160
+    },
+    {
+      "epoch": 0.1972062448644207,
+      "grad_norm": 0.062402546405792236,
+      "learning_rate": 0.00018917490293267973,
+      "loss": 0.2929875135421753,
+      "step": 180
+    },
+    {
+      "epoch": 0.21911804984935634,
+      "grad_norm": 0.07164579629898071,
+      "learning_rate": 0.00018564686340850708,
+      "loss": 0.2802800893783569,
+      "step": 200
+    },
+    {
+      "epoch": 0.21911804984935634,
+      "eval_loss": 0.2665560841560364,
+      "eval_runtime": 78.0807,
+      "eval_samples_per_second": 4.278,
+      "eval_steps_per_second": 1.076,
+      "step": 200
+    },
+    {
+      "epoch": 0.24102985483429198,
+      "grad_norm": 0.06281758099794388,
+      "learning_rate": 0.0001816650309196209,
+      "loss": 0.2850670576095581,
+      "step": 220
+    },
+    {
+      "epoch": 0.2629416598192276,
+      "grad_norm": 0.05580520257353783,
+      "learning_rate": 0.000177250502882765,
+      "loss": 0.2707890510559082,
+      "step": 240
+    },
+    {
+      "epoch": 0.28485346480416324,
+      "grad_norm": 0.0578630194067955,
+      "learning_rate": 0.0001724266693169772,
+      "loss": 0.2684861898422241,
+      "step": 260
+    },
+    {
+      "epoch": 0.3067652697890989,
+      "grad_norm": 0.056395046412944794,
+      "learning_rate": 0.0001672190889134691,
+      "loss": 0.27494494915008544,
+      "step": 280
+    },
+    {
+      "epoch": 0.3286770747740345,
+      "grad_norm": 0.06928149610757828,
+      "learning_rate": 0.00016165535361497218,
+      "loss": 0.27622313499450685,
+      "step": 300
+    },
+    {
+      "epoch": 0.35058887975897013,
+      "grad_norm": 0.06063492223620415,
+      "learning_rate": 0.00015576494242206508,
+      "loss": 0.26791768074035643,
+      "step": 320
+    },
+    {
+      "epoch": 0.3725006847439058,
+      "grad_norm": 0.052748970687389374,
+      "learning_rate": 0.00014957906520107845,
+      "loss": 0.2828014373779297,
+      "step": 340
+    },
+    {
+      "epoch": 0.3944124897288414,
+      "grad_norm": 0.05597842484712601,
+      "learning_rate": 0.00014313049732114715,
+      "loss": 0.27218098640441896,
+      "step": 360
+    },
+    {
+      "epoch": 0.416324294713777,
+      "grad_norm": 0.054700642824172974,
+      "learning_rate": 0.0001364534059965735,
+      "loss": 0.258621072769165,
+      "step": 380
+    },
+    {
+      "epoch": 0.4382360996987127,
+      "grad_norm": 0.06639006733894348,
+      "learning_rate": 0.00012958316925461085,
+      "loss": 0.26321959495544434,
+      "step": 400
+    },
+    {
+      "epoch": 0.4382360996987127,
+      "eval_loss": 0.25228193402290344,
+      "eval_runtime": 76.7593,
+      "eval_samples_per_second": 4.351,
+      "eval_steps_per_second": 1.094,
+      "step": 400
+    },
+    {
+      "epoch": 0.4601479046836483,
+      "grad_norm": 0.04828259348869324,
+      "learning_rate": 0.00012255618848785378,
+      "loss": 0.2582087993621826,
+      "step": 420
+    },
+    {
+      "epoch": 0.48205970966858397,
+      "grad_norm": 0.09414570778608322,
+      "learning_rate": 0.0001154096955844091,
+      "loss": 0.26802127361297606,
+      "step": 440
+    },
+    {
+      "epoch": 0.5039715146535196,
+      "grad_norm": 0.06418801099061966,
+      "learning_rate": 0.00010818155565775443,
+      "loss": 0.2587978601455688,
+      "step": 460
+    },
+    {
+      "epoch": 0.5258833196384552,
+      "grad_norm": 0.059086013585329056,
+      "learning_rate": 0.0001009100664215028,
+      "loss": 0.26389484405517577,
+      "step": 480
+    },
+    {
+      "epoch": 0.5477951246233909,
+      "grad_norm": 0.05814081430435181,
+      "learning_rate": 9.363375527207111e-05,
+      "loss": 0.2642557144165039,
+      "step": 500
+    },
+    {
+      "epoch": 0.5697069296083265,
+      "grad_norm": 0.060968417674303055,
+      "learning_rate": 8.639117515439248e-05,
+      "loss": 0.2558141708374023,
+      "step": 520
+    },
+    {
+      "epoch": 0.5916187345932621,
+      "grad_norm": 0.04676595702767372,
+      "learning_rate": 7.92207002922618e-05,
+      "loss": 0.25071308612823484,
+      "step": 540
+    },
+    {
+      "epoch": 0.6135305395781978,
+      "grad_norm": 0.055148206651210785,
+      "learning_rate": 7.216032286562122e-05,
+      "loss": 0.25150718688964846,
+      "step": 560
+    },
+    {
+      "epoch": 0.6354423445631334,
+      "grad_norm": 0.05283847823739052,
+      "learning_rate": 6.524745171207339e-05,
+      "loss": 0.2621228933334351,
+      "step": 580
+    },
+    {
+      "epoch": 0.657354149548069,
+      "grad_norm": 0.05972014740109444,
+      "learning_rate": 5.851871411918743e-05,
+      "loss": 0.262609076499939,
+      "step": 600
+    },
+    {
+      "epoch": 0.657354149548069,
+      "eval_loss": 0.24315646290779114,
+      "eval_runtime": 76.7442,
+      "eval_samples_per_second": 4.352,
+      "eval_steps_per_second": 1.095,
+      "step": 600
+    },
+    {
+      "epoch": 0.6792659545330046,
+      "grad_norm": 0.0542420968413353,
+      "learning_rate": 5.20097617577839e-05,
+      "loss": 0.24464335441589355,
+      "step": 620
+    },
+    {
+      "epoch": 0.7011777595179403,
+      "grad_norm": 0.05391804128885269,
+      "learning_rate": 4.5755081784446306e-05,
+      "loss": 0.23991961479187013,
+      "step": 640
+    },
+    {
+      "epoch": 0.7230895645028759,
+      "grad_norm": 0.067460797727108,
+      "learning_rate": 3.978781411411705e-05,
+      "loss": 0.25521044731140136,
+      "step": 660
+    },
+    {
+      "epoch": 0.7450013694878116,
+      "grad_norm": 0.060182541608810425,
+      "learning_rate": 3.413957583094358e-05,
+      "loss": 0.25919690132141116,
+      "step": 680
+    },
+    {
+      "epoch": 0.7669131744727472,
+      "grad_norm": 0.05970674753189087,
+      "learning_rate": 2.8840293667720653e-05,
+      "loss": 0.25497357845306395,
+      "step": 700
+    },
+    {
+      "epoch": 0.7888249794576828,
+      "grad_norm": 0.05807078629732132,
+      "learning_rate": 2.3918045441521718e-05,
+      "loss": 0.2616193532943726,
+      "step": 720
+    },
+    {
+      "epoch": 0.8107367844426184,
+      "grad_norm": 0.07185934484004974,
+      "learning_rate": 1.9398911285660816e-05,
+      "loss": 0.25238714218139646,
+      "step": 740
+    },
+    {
+      "epoch": 0.832648589427554,
+      "grad_norm": 0.05691298842430115,
+      "learning_rate": 1.5306835466219738e-05,
+      "loss": 0.25438358783721926,
+      "step": 760
+    },
+    {
+      "epoch": 0.8545603944124898,
+      "grad_norm": 0.05606130138039589,
+      "learning_rate": 1.1663499515294762e-05,
+      "loss": 0.23820433616638184,
+      "step": 780
+    },
+    {
+      "epoch": 0.8764721993974254,
+      "grad_norm": 0.05140916630625725,
+      "learning_rate": 8.488207353155986e-06,
+      "loss": 0.26239197254180907,
+      "step": 800
+    },
+    {
+      "epoch": 0.8764721993974254,
+      "eval_loss": 0.23945921659469604,
+      "eval_runtime": 76.7615,
+      "eval_samples_per_second": 4.351,
+      "eval_steps_per_second": 1.094,
+      "step": 800
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 913,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.475205602097205e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8a97d3e6475c1d773d3dbe9946a270643635d978dff4a6385add4e04eb83b6
+size 5713