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 +1,49 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-3B-Instruct
+library_name: peft
+tags:
+  - competitive-programming
+  - codeforces
+  - qlora
+datasets:
+  - open-r1/codeforces-cots
+---
+
+# Ladder-3B (unevaluated)
+
+A QLoRA adapter for `Qwen2.5-Coder-3B-Instruct`, trained on verified Codeforces
+reasoning traces with [Ladder](https://github.com/NiLabs-Models/ladder).
+
+> **This model has not been evaluated.** There is no pass@1 for it, and none is
+> claimed. It is stored here so the weights are not stranded on a temporary
+> disk, and so any GPU can pick it up and score it. The repository stays private
+> until there are measured numbers to publish with it.
+
+## Training
+
+| | |
+| --- | --- |
+| Base | `unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit` |
+| Method | QLoRA, 4-bit, rank 32, loss on the assistant turn only |
+| Data | 2,271 traces, each verified by executing its solution against the problem's own tests |
+| Steps | 150, effective batch 16, context 8,192 |
+| Hardware | Tesla T4, 5.05 h, 594.9 tok/s, peak VRAM 6.78 GB |
+
+## Evaluating it
+
+```bash
+git clone https://github.com/NiLabs-Models/ladder
+ladder eval --config configs/ladder-3b-kaggle.yaml                  # base
+ladder eval --config configs/ladder-3b-kaggle.yaml --adapter <this> # tuned
+```
+
+Scoring runs generated programs against real Codeforces test cases. No
+model-as-judge, no similarity metric.
+
+## Known limitations
+
+- Python only; most competitive programming is C++.
+- Trained on the 30% of the corpus short enough to fit 8,192 tokens. The median
+  trace is ~13,770 tokens, so the hardest problems are disproportionately absent.
+- Codeforces `checker` and interactive problems are excluded from evaluation.

adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "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-Coder-3B-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": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": 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 sha256:9226b3df264d076d04548e01a41203cd86d7640a7e7c5e906188abe89aa66465
+size 239536272

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 %}

run_config.json

@@ -0,0 +1,81 @@
+{
+  "name": "ladder-3b-kaggle",
+  "data": {
+    "dataset": "open-r1/codeforces-cots",
+    "config_name": "solutions_py_decontaminated",
+    "split": "train",
+    "max_tokens": 8192,
+    "min_tokens": 256,
+    "min_rating": null,
+    "max_rating": null,
+    "require_finish_reason": "stop",
+    "dedup_by_problem": true,
+    "verify_solutions": true,
+    "verify_max_tests": 4,
+    "verify_timeout": 5.0,
+    "verify_memory_limit_mb": 1024,
+    "verify_workers": 8,
+    "verify_keep_unverifiable": true,
+    "val_fraction": 0.04,
+    "seed": 17,
+    "max_samples": 0
+  },
+  "model": {
+    "base_model": "unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit",
+    "max_seq_length": 8192,
+    "load_in_4bit": true,
+    "lora_r": 32,
+    "lora_alpha": 32,
+    "lora_dropout": 0.0,
+    "target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "gate_proj",
+      "up_proj",
+      "down_proj"
+    ],
+    "use_gradient_checkpointing": "unsloth"
+  },
+  "train": {
+    "output_dir": "/kaggle/working/outputs/ladder-3b-kaggle",
+    "per_device_train_batch_size": 1,
+    "gradient_accumulation_steps": 16,
+    "num_train_epochs": 1.0,
+    "max_steps": 150,
+    "learning_rate": 0.0001,
+    "warmup_ratio": 0.03,
+    "lr_scheduler_type": "cosine",
+    "weight_decay": 0.01,
+    "optim": "adamw_8bit",
+    "max_grad_norm": 0.5,
+    "logging_steps": 5,
+    "save_steps": 75,
+    "save_total_limit": 2,
+    "eval_steps": 100,
+    "seed": 17,
+    "train_on_completions_only": true,
+    "hub_model_id": null,
+    "push_to_hub": false
+  },
+  "eval": {
+    "dataset": "open-r1/codeforces-cots",
+    "config_name": "solutions_py_decontaminated",
+    "split": "train",
+    "num_problems": 40,
+    "samples_per_problem": 1,
+    "problem_types": [
+      "diff"
+    ],
+    "max_new_tokens": 4096,
+    "temperature": 0.0,
+    "top_p": 0.95,
+    "seed": 17,
+    "timeout_seconds": 8.0,
+    "memory_limit_mb": 1024,
+    "max_tests_per_problem": 12,
+    "case_sensitive": false,
+    "results_path": "/kaggle/working/outputs/eval/results.json"
+  }
+}

throughput.json

@@ -0,0 +1,14 @@
+{
+  "train_runtime_seconds": 18178.6,
+  "train_runtime_hours": 5.05,
+  "n_examples": 2271,
+  "total_tokens": 10813978,
+  "tokens_per_second": 594.9,
+  "seconds_per_example": 8.005,
+  "mean_tokens_per_example": 4762,
+  "peak_vram_gb": 6.78,
+  "max_seq_length": 8192,
+  "effective_batch": 16,
+  "max_steps": 150,
+  "gpu": "Tesla T4"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "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
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}