Upload CDLM Open-Dcoder-0.5B trained on OpenCodeInstruct (CDLM code release)

.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 +1,63 @@
+---
+license: mit
+base_model: fredzzp/open-dcoder-0.5B
+datasets:
+- nvidia/OpenCodeInstruct
+language:
+- code
+pipeline_tag: text-generation
+tags:
+- masked-diffusion
+- diffusion-language-model
+- code
+- code-correction
+- cdlm
+---
+
+# Open-Dcoder-0.5B-CDLM-OpenCodeInstruct
+
+Open-dCoder-0.5B continued for 2,000 steps on [nvidia/OpenCodeInstruct](https://huggingface.co/datasets/nvidia/OpenCodeInstruct) with the CDLM corrective objective: absorbing (mask) corruption plus uniform replacement of 10% of the still-visible tokens, with a cross-entropy term on the replaced positions (weight 0.1). It is one of a matched pair; Shuibai12138/Open-Dcoder-0.5B-MDLM-OpenCodeInstruct is its matched MDLM control (absorbing-only objective, otherwise identical).
+
+This model is part of the code release of *Corrective Diffusion Language Models* (NeurIPS 2026). **It is not a model from the paper.** The paper's 0.5B models ([Shuibai12138/CDLM-0.5B](https://huggingface.co/Shuibai12138/CDLM-0.5B)) were trained on Nemotron-SFT-Code, which is gated and licensed for internal training only. This pair uses the same code and hyperparameters on a public, ungated corpus so that the recipe can be reproduced and compared by anyone. Results on it are not the paper's results.
+
+## Training
+
+| | |
+|---|---|
+| Initialisation | [fredzzp/open-dcoder-0.5B](https://huggingface.co/fredzzp/open-dcoder-0.5B) (revision `d0d86d5b9996`) |
+| Objective | `mixture_prob=0.1`, `noise_token_wt=0.1`, `clean_token_wt=0.0` |
+| Data | nvidia/OpenCodeInstruct, revision `8f3ba5bafe4d`, all 50 shards in sorted order, each row rendered as `"input: " + input + " output: " + output` (the text format of the paper's corpus), no filtering |
+| Steps | 2,000 (step 2,000 of a 20,345,053-step schedule, the same truncated long-horizon schedule as the paper's CDLM-0.5B) |
+| Optimiser | AdamW, peak lr 3e-4, cosine, 20,345 warmup steps (lr at step 2,000 = 2.95e-5), weight decay 0.01, grad clip 1.0, bf16 |
+| Batch | global 12 sequences x 4,096 packed tokens (micro 3 x 4 GPUs) |
+| Frozen | `lm_head`, `embed_tokens` |
+| Seed | 42 |
+| Hardware | 4 x A100-PCIE-40GB, about 19 minutes |
+| Code | [zhangshuibai/CDLM](https://github.com/zhangshuibai/CDLM), trained at commit `5e52812`; tag `v1.0-corrective-training` contains the same training code. Command: `ARM=cdlm bash training/scripts/train_0.5b_opencodeinstruct.sh` |
+
+`training_config.yaml` in this repository is the fully resolved configuration the trainer saved for this run.
+
+## Usage
+
+This is a masked diffusion language model with bidirectional attention. Loading it with `AutoModelForCausalLM` gives a causal Qwen2 model and wrong outputs. Use the evaluation pipeline of the [code repository](https://github.com/zhangshuibai/CDLM), which loads models whose name contains `open-dcoder` with the diffusion Qwen2 implementation (bidirectional attention, shifted logits):
+
+```bash
+git clone https://github.com/zhangshuibai/CDLM && cd CDLM
+# see README.md for the evaluation environment and commands, then pass
+#   --model_name Shuibai12138/Open-Dcoder-0.5B-CDLM-OpenCodeInstruct
+```
+
+## Licence and attribution
+
+Model weights: MIT. Trained on [nvidia/OpenCodeInstruct](https://huggingface.co/datasets/nvidia/OpenCodeInstruct) (CC BY 4.0, NVIDIA). Base model: [fredzzp/open-dcoder-0.5B](https://huggingface.co/fredzzp/open-dcoder-0.5B).
+
+## Citation
+
+```bibtex
+@inproceedings{zhang2026corrective,
+  title     = {Corrective Diffusion Language Models},
+  author    = {Zhang, Shuibai and Peng, Fred Zhangzhi and Zhang, Yiheng and Pan, Jin and Chrysos, Grigorios G.},
+  booktitle = {Advances in Neural Information Processing Systems},
+  year      = {2026}
+}
+```

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<M>": 151665,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '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 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 +1,55 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae362eb296006bcd139234967bcc5503296b7912261fda337b867d44713acd4
+size 1260367448

special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<M>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3ead5ffbb2abfb9e51757b104af5174f59c994ff3b2ca715d344dc66ee1f4e
+size 11422076

tokenizer_config.json

@@ -0,0 +1,217 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<M>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<M>",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_config.yaml

@@ -0,0 +1,99 @@
+# Fully resolved training configuration of this run (saved by the trainer as veomni_cli.yaml).
+# Paths replaced by placeholders. World size 4 (4 x A100-PCIE-40GB), gradient accumulation 1.
+data:
+  chat_template: default
+  data_name: null
+  data_tag: default
+  data_type: plaintext
+  dataloader_type: native
+  datasets_type: iterable
+  drop_last: true
+  image_keys: images
+  max_seq_len: 4096
+  num_workers: 2
+  pin_memory: true
+  prefetch_factor: 2
+  text_keys: text
+  train_path: ${OCI_TEXT_DIR}/000,...,${OCI_TEXT_DIR}/049  # the 50 rendered shards in sorted order (train_path.txt written by prepare_opencodeinstruct.py)
+  train_size: 1000000000000
+model:
+  attn_implementation: flash_attention_2
+  basic_modules: []
+  config_path: fredzzp/open-dcoder-0.5B
+  decoders: {}
+  encode_target: false
+  encoders: {}
+  input_encoder: encoder
+  model_path: fredzzp/open-dcoder-0.5B
+  moe_implementation: null
+  output_encoder: decoder
+  tokenizer_path: fredzzp/open-dcoder-0.5B
+train:
+  activation_gpu_limit: 0.0
+  auto_resume: true
+  bsz_warmup_init_mbtoken: 200
+  bsz_warmup_ratio: 0.0
+  ckpt_manager: dcp
+  clean_token_wt: 0.0
+  context_parallel_size: 1
+  data_parallel_mode: ddp
+  dyn_bsz: true
+  dyn_bsz_buffer_size: 100
+  dyn_bsz_margin: 0
+  empty_cache_steps: 1000
+  enable_activation_offload: false
+  enable_forward_prefetch: true
+  enable_fsdp_offload: false
+  enable_full_determinism: false
+  enable_full_shard: false
+  enable_gradient_checkpointing: false
+  enable_manual_eager: false
+  enable_masking: true
+  enable_mixed_precision: false
+  enable_profiling: false
+  enable_reentrant: false
+  eval_batch_size: 10
+  eval_before_train: false
+  eval_every: 0
+  expert_parallel_size: 1
+  freeze_layers: lm_head,embed_tokens
+  global_batch_size: 12
+  init_device: cuda
+  load_checkpoint_path: ''
+  lr: 0.0003
+  lr_decay_ratio: 1.0
+  lr_decay_style: cosine
+  lr_min: 3.0e-06
+  lr_start: 0.0
+  lr_warmup_ratio: 0.001
+  max_grad_norm: 1.0
+  max_steps: null
+  micro_batch_size: 3
+  mixture_prob: 0.1
+  noise_token_wt: 0.1
+  num_train_epochs: 1
+  optimizer: adamw
+  output_dir: ${OUTPUT_DIR}/open-dcoder-0.5B-oci-cdlm-seed42-step2000  # placeholder
+  pipeline_parallel_size: 1
+  profile_end_step: 2
+  profile_profile_memory: true
+  profile_record_shapes: true
+  profile_start_step: 1
+  profile_trace_dir: ./trace
+  profile_with_stack: true
+  repr_align_wt: 0.0
+  rmpad: false
+  rmpad_with_pos_ids: true
+  save_epochs: 1
+  save_hf_weights: true
+  save_steps: 2000
+  save_time_interval_minutes: 0
+  seed: 42
+  tensor_parallel_size: 1
+  ulysses_parallel_size: 1
+  use_doptim: false
+  use_wandb: true
+  wandb_entity: ''
+  wandb_name: open-dcoder-0.5B-oci-cdlm-seed42-step2000
+  wandb_project: Qwen2.5-Coder-0.5B
+  weight_decay: 0.01