Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ 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
+checkpoint-10000/pt_lora_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-11328/pt_lora_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+llmtf_eval/daru_treewayabstractive.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval/daru_treewayextractive.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval/darumeru_MultiQ.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval/darumeru_USE.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval/darumeru_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval/nlpcoreteam_enMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval/nlpcoreteam_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval/russiannlp_rucola_custom.jsonl filter=lfs diff=lfs merge=lfs -text
+pt_lora_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+base_model: RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init
+library_name: peft
+metrics:
+- accuracy
+tags:
+- generated_from_trainer
+model-index:
+- name: ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2
+
+This model is a fine-tuned version of [RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init](https://huggingface.co/RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4070
+- Accuracy: 0.5068
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 64
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 256
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|
+| No log        | 0.0001 | 1     | 5.8817          | 0.3107   |
+| 2.5884        | 0.1765 | 2000  | 2.4509          | 0.5014   |
+| 2.5525        | 0.3531 | 4000  | 2.4229          | 0.5046   |
+| 2.5286        | 0.5296 | 6000  | 2.4123          | 0.5061   |
+| 2.53          | 0.7062 | 8000  | 2.4078          | 0.5068   |
+| 2.528         | 0.8827 | 10000 | 2.4070          | 0.5067   |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.45.2
+- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
+- Datasets 2.18.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084aed85df91ebc784597f3c1e56d2dc149b191275677eb9a1df2801f6f74645
+size 632040248

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 147090,
+  "<tool_call>": 147089,
+  "<|box_end|>": 147081,
+  "<|box_start|>": 147080,
+  "<|endoftext|>": 147075,
+  "<|file_sep|>": 147096,
+  "<|fim_middle|>": 147092,
+  "<|fim_pad|>": 147094,
+  "<|fim_prefix|>": 147091,
+  "<|fim_suffix|>": 147093,
+  "<|im_end|>": 147077,
+  "<|im_start|>": 147076,
+  "<|image_pad|>": 147087,
+  "<|object_ref_end|>": 147079,
+  "<|object_ref_start|>": 147078,
+  "<|quad_end|>": 147083,
+  "<|quad_start|>": 147082,
+  "<|repo_name|>": 147095,
+  "<|video_pad|>": 147088,
+  "<|vision_end|>": 147085,
+  "<|vision_pad|>": 147086,
+  "<|vision_start|>": 147084
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9999558635300348,
+    "eval_accuracy": 0.5067761728139086,
+    "eval_loss": 2.4069583415985107,
+    "eval_runtime": 36.3165,
+    "eval_samples": 318,
+    "eval_samples_per_second": 8.756,
+    "eval_steps_per_second": 0.083,
+    "perplexity": 11.100146890382385,
+    "total_flos": 2.202782600225295e+20,
+    "train_loss": 2.5603223798301933,
+    "train_runtime": 24610.1089,
+    "train_samples": 2900094,
+    "train_samples_per_second": 117.842,
+    "train_steps_per_second": 0.46
+}

checkpoint-10000/pt_lora_model/README.md

@@ -0,0 +1,7 @@
+---
+base_model: RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init
+library_name: peft
+---
+### Framework versions
+
+- PEFT 0.9.0

checkpoint-10000/pt_lora_model/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-10000/pt_lora_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3914111b50e14351d0b6f4ba89be6ed990f095a0c8e1ebfd66ae79ad783a4e
+size 632040248

checkpoint-10000/pt_lora_model/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 147090,
+  "<tool_call>": 147089,
+  "<|box_end|>": 147081,
+  "<|box_start|>": 147080,
+  "<|endoftext|>": 147075,
+  "<|file_sep|>": 147096,
+  "<|fim_middle|>": 147092,
+  "<|fim_pad|>": 147094,
+  "<|fim_prefix|>": 147091,
+  "<|fim_suffix|>": 147093,
+  "<|im_end|>": 147077,
+  "<|im_start|>": 147076,
+  "<|image_pad|>": 147087,
+  "<|object_ref_end|>": 147079,
+  "<|object_ref_start|>": 147078,
+  "<|quad_end|>": 147083,
+  "<|quad_start|>": 147082,
+  "<|repo_name|>": 147095,
+  "<|video_pad|>": 147088,
+  "<|vision_end|>": 147085,
+  "<|vision_pad|>": 147086,
+  "<|vision_start|>": 147084
+}

checkpoint-10000/pt_lora_model/special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|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|>",
+    "<tool_call>",
+    "</tool_call>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<|repo_name|>",
+    "<|file_sep|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10000/pt_lora_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b9483a1bfb5b8bb09b0269429a5e7fd89ee2868eb31cc70d5f695b64b95852
+size 12441282

checkpoint-10000/pt_lora_model/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "147075": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147076": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147077": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147078": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147079": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147080": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147081": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147082": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147083": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147084": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147085": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147086": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147087": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147088": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147089": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147090": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147091": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147092": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147093": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147094": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147095": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147096": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|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|>",
+    "<tool_call>",
+    "</tool_call>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<|repo_name|>",
+    "<|file_sep|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '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 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",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-11328/pt_lora_model/README.md

@@ -0,0 +1,202 @@
+---
+base_model: RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init
+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 0.9.0

checkpoint-11328/pt_lora_model/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-11328/pt_lora_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084aed85df91ebc784597f3c1e56d2dc149b191275677eb9a1df2801f6f74645
+size 632040248

checkpoint-11328/pt_lora_model/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 147090,
+  "<tool_call>": 147089,
+  "<|box_end|>": 147081,
+  "<|box_start|>": 147080,
+  "<|endoftext|>": 147075,
+  "<|file_sep|>": 147096,
+  "<|fim_middle|>": 147092,
+  "<|fim_pad|>": 147094,
+  "<|fim_prefix|>": 147091,
+  "<|fim_suffix|>": 147093,
+  "<|im_end|>": 147077,
+  "<|im_start|>": 147076,
+  "<|image_pad|>": 147087,
+  "<|object_ref_end|>": 147079,
+  "<|object_ref_start|>": 147078,
+  "<|quad_end|>": 147083,
+  "<|quad_start|>": 147082,
+  "<|repo_name|>": 147095,
+  "<|video_pad|>": 147088,
+  "<|vision_end|>": 147085,
+  "<|vision_pad|>": 147086,
+  "<|vision_start|>": 147084
+}

checkpoint-11328/pt_lora_model/special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|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|>",
+    "<tool_call>",
+    "</tool_call>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<|repo_name|>",
+    "<|file_sep|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-11328/pt_lora_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b9483a1bfb5b8bb09b0269429a5e7fd89ee2868eb31cc70d5f695b64b95852
+size 12441282

checkpoint-11328/pt_lora_model/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "147075": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147076": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147077": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147078": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147079": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147080": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147081": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147082": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147083": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147084": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147085": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147086": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147087": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147088": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147089": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147090": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147091": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147092": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147093": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147094": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147095": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147096": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|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|>",
+    "<tool_call>",
+    "</tool_call>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<|repo_name|>",
+    "<|file_sep|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '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 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",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.9999558635300348,
+    "eval_accuracy": 0.5067761728139086,
+    "eval_loss": 2.4069583415985107,
+    "eval_runtime": 36.3165,
+    "eval_samples": 318,
+    "eval_samples_per_second": 8.756,
+    "eval_steps_per_second": 0.083,
+    "perplexity": 11.100146890382385
+}

llmtf_eval/daru_treewayabstractive.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62cf31a7dc24dba64d5b3b18b757fa07cf94bffb313ea372c7dc018c9c61f90a
+size 15970230

llmtf_eval/daru_treewayabstractive_params.jsonl

@@ -0,0 +1,57 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                147075,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 512,
+            "pad_token_id": 147075,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.45.2"
+        },
+        "conversation_template": {
+            "system_message_template": "{content}\n",
+            "user_message_template": "{content}\n",
+            "bot_message_template": "{content}\n\n",
+            "bot_message_template_incomplete": "{content}",
+            "user_role": "user",
+            "bot_role": "bot",
+            "system_role": "system",
+            "suffix": "",
+            "add_special_tokens": false,
+            "eos_token": [
+                "\n",
+                "\n\n"
+            ],
+            "global_prefix": ""
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": false,
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 5,
+        "batch_size": 8,
+        "max_sample_per_dataset": 500,
+        "method": "generate"
+    }
+}

llmtf_eval/daru_treewayabstractive_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "daru/treewayabstractive",
+    "results": {
+        "rouge1": 0.2503995223034589,
+        "rouge2": 0.08558468876095006
+    },
+    "leaderboard_result": 0.16799210553220448
+}

llmtf_eval/daru_treewayextractive.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901cb262bf1b627347fd7fd87afa52181c0b7c6344bb96ec9cf5d69e6421fdfb
+size 211780847

llmtf_eval/daru_treewayextractive_params.jsonl

@@ -0,0 +1,57 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                147075,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 1,
+            "pad_token_id": 147075,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.45.2"
+        },
+        "conversation_template": {
+            "system_message_template": "{content}\n",
+            "user_message_template": "{content}\n",
+            "bot_message_template": "{content}\n\n",
+            "bot_message_template_incomplete": "{content}",
+            "user_role": "user",
+            "bot_role": "bot",
+            "system_role": "system",
+            "suffix": "",
+            "add_special_tokens": false,
+            "eos_token": [
+                "\n",
+                "\n\n"
+            ],
+            "global_prefix": ""
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": false,
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 5,
+        "batch_size": 8,
+        "max_sample_per_dataset": 500,
+        "method": "calculate_logsoftmax"
+    }
+}

llmtf_eval/daru_treewayextractive_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "daru/treewayextractive",
+    "results": {
+        "r-prec": 0.3766208513708514
+    },
+    "leaderboard_result": 0.3766208513708514
+}

llmtf_eval/darumeru_MultiQ.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3c9f27bdee462bc2a78f640ed98450f328e9cebe967f0c5c87faf160788fb9
+size 21484898

llmtf_eval/darumeru_MultiQ_params.jsonl

@@ -0,0 +1,57 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                147075,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 147075,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.45.2"
+        },
+        "conversation_template": {
+            "system_message_template": "{content}\n",
+            "user_message_template": "{content}\n",
+            "bot_message_template": "{content}\n\n",
+            "bot_message_template_incomplete": "{content}",
+            "user_role": "user",
+            "bot_role": "bot",
+            "system_role": "system",
+            "suffix": "",
+            "add_special_tokens": false,
+            "eos_token": [
+                "\n",
+                "\n\n"
+            ],
+            "global_prefix": ""
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": false,
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 5,
+        "batch_size": 8,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval/darumeru_MultiQ_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/MultiQ",
+    "results": {
+        "f1": 0.4759256275303807,
+        "em": 0.3030592734225621
+    },
+    "leaderboard_result": 0.3894924504764714
+}

llmtf_eval/darumeru_PARus_params.jsonl

@@ -0,0 +1,57 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                147075,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 147075,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.45.2"
+        },
+        "conversation_template": {
+            "system_message_template": "{content}\n",
+            "user_message_template": "{content}\n",
+            "bot_message_template": "{content}\n\n",
+            "bot_message_template_incomplete": "{content}",
+            "user_role": "user",
+            "bot_role": "bot",
+            "system_role": "system",
+            "suffix": "",
+            "add_special_tokens": false,
+            "eos_token": [
+                "\n",
+                "\n\n"
+            ],
+            "global_prefix": ""
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": false,
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 5,
+        "batch_size": 8,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval/darumeru_PARus_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/PARus",
+    "results": {
+        "acc": 0.39
+    },
+    "leaderboard_result": 0.39
+}

llmtf_eval/darumeru_RCB_params.jsonl

@@ -0,0 +1,57 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                147075,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 147075,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.45.2"
+        },
+        "conversation_template": {
+            "system_message_template": "{content}\n",
+            "user_message_template": "{content}\n",
+            "bot_message_template": "{content}\n\n",
+            "bot_message_template_incomplete": "{content}",
+            "user_role": "user",
+            "bot_role": "bot",
+            "system_role": "system",
+            "suffix": "",
+            "add_special_tokens": false,
+            "eos_token": [
+                "\n",
+                "\n\n"
+            ],
+            "global_prefix": ""
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": false,
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 5,
+        "batch_size": 8,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval/darumeru_RCB_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/RCB",
+    "results": {
+        "acc": 0.41363636363636364,
+        "f1_macro": 0.3966762193460725
+    },
+    "leaderboard_result": 0.40515629149121807
+}

llmtf_eval/darumeru_RWSD_params.jsonl

@@ -0,0 +1,57 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                147075,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 147075,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.45.2"
+        },
+        "conversation_template": {
+            "system_message_template": "{content}\n",
+            "user_message_template": "{content}\n",
+            "bot_message_template": "{content}\n\n",
+            "bot_message_template_incomplete": "{content}",
+            "user_role": "user",
+            "bot_role": "bot",
+            "system_role": "system",
+            "suffix": "",
+            "add_special_tokens": false,
+            "eos_token": [
+                "\n",
+                "\n\n"
+            ],
+            "global_prefix": ""
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": false,
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 5,
+        "batch_size": 8,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval/darumeru_RWSD_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/RWSD",
+    "results": {
+        "acc": 0.43137254901960786
+    },
+    "leaderboard_result": 0.43137254901960786
+}

llmtf_eval/darumeru_USE.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47aaeb6166bc4d68b97606f1b829db0fbe8ca3dcfe6fe1a992eeee25e5615b1
+size 10585233

llmtf_eval/darumeru_USE_params.jsonl

@@ -0,0 +1,57 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                147075,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 147075,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.45.2"
+        },
+        "conversation_template": {
+            "system_message_template": "{content}\n",
+            "user_message_template": "{content}\n",
+            "bot_message_template": "{content}\n\n",
+            "bot_message_template_incomplete": "{content}",
+            "user_role": "user",
+            "bot_role": "bot",
+            "system_role": "system",
+            "suffix": "",
+            "add_special_tokens": false,
+            "eos_token": [
+                "\n",
+                "\n\n"
+            ],
+            "global_prefix": ""
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": false,
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 5,
+        "batch_size": 8,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval/darumeru_USE_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/USE",
+    "results": {
+        "grade_norm": 0.042156862745098035
+    },
+    "leaderboard_result": 0.042156862745098035
+}

llmtf_eval/darumeru_cp_para_en_params.jsonl

@@ -0,0 +1,57 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                147075,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 1024,
+            "pad_token_id": 147075,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.45.2"
+        },
+        "conversation_template": {
+            "system_message_template": "{content}\n",
+            "user_message_template": "{content}\n",
+            "bot_message_template": "{content}\n\n",
+            "bot_message_template_incomplete": "{content}",
+            "user_role": "user",
+            "bot_role": "bot",
+            "system_role": "system",
+            "suffix": "",
+            "add_special_tokens": false,
+            "eos_token": [
+                "\n",
+                "\n\n"
+            ],
+            "global_prefix": ""
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": false,
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 5,
+        "batch_size": 8,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval/darumeru_cp_para_en_total.jsonl

@@ -0,0 +1,9 @@
+{
+    "task_name": "darumeru/cp_para_en",
+    "results": {
+        "symbol_per_token": 4.43961628016479,
+        "len": 0.9907918582197385,
+        "lcs": 1.0
+    },
+    "leaderboard_result": 1.0
+}