Upload folder using huggingface_hub

README.md

@@ -0,0 +1,144 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: ByteDance-Seed/academic-ds-9B
+tags:
+- generated_from_trainer
+datasets:
+- allura-forge/inkmix-v3.1
+model-index:
+- name: mnt/persistent/ckpts
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.10.0.dev0`
+```yaml
+# === Model Configuration ===
+base_model: ByteDance-Seed/academic-ds-9B
+load_in_8bit: false
+load_in_4bit: false
+
+# === Training Setup ===
+num_epochs: 2
+micro_batch_size: 2
+gradient_accumulation_steps: 8
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+
+# === Hyperparameter Configuration ===
+optimizer: apollo_adamw
+# Apollo-mini configuration:
+optim_args: "proj=random,rank=1,scale=128.0,scale_type=tensor,update_proj_gap=200"
+# Regular Apollo configuration:
+# optim_args: 
+optim_target_modules: all_linear
+learning_rate: 1e-5
+lr_scheduler: rex
+weight_decay: 0.01
+warmup_ratio: 0
+max_grad_norm: 0.1
+
+# === Data Configuration ===
+datasets:
+  - path: allura-forge/inkmix-v3.1
+    type: chat_template
+    split: train
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+
+dataset_prepared_path: last_run_prepared
+chat_template_jinja: |
+  {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}
+  {{bos_token}}{% for message in messages %}
+    {{'<|im_start|>' + message['role'] + '
+    ' + message['content'] + '<|im_end|>' + '
+    '}}
+  {% endfor %}
+
+# === Plugins ===
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+#  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+# === Hardware Optimization ===
+gradient_checkpointing: unsloth
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+#cut_cross_entropy: true
+
+# === Wandb Tracking ===
+wandb_project: bytedance-ds-9b-inkmix-v3
+
+# === Checkpointing ===
+saves_per_epoch: 2
+save_total_limit: 3
+
+# === Advanced Settings ===
+output_dir: /mnt/persistent/ckpts
+bf16: auto
+flash_attention: true
+train_on_inputs: false
+group_by_length: false
+logging_steps: 1
+trust_remote_code: true
+tokens:
+  - '<|im_start|>'
+special_tokens:
+  eos_token: '<|im_end|>'
+
+```
+
+</details><br>
+
+# mnt/persistent/ckpts
+
+This model is a fine-tuned version of [ByteDance-Seed/academic-ds-9B](https://huggingface.co/ByteDance-Seed/academic-ds-9B) on the allura-forge/inkmix-v3.1 dataset.
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.APOLLO_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=proj=random,rank=1,scale=128.0,scale_type=tensor,update_proj_gap=200
+- lr_scheduler_type: cosine
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.1
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "ByteDance-Seed/academic-ds-9B--configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "ByteDance-Seed/academic-ds-9B--modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "ByteDance-Seed/academic-ds-9B--modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 0,
+  "eos_token_id": 128815,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.0125,
+  "intermediate_size": 10944,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 8192,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 1408,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "num_nextn_predict_layers": 1,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1024,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "transformers_version": "4.51.3",
+  "use_cache": false
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415c70456e4e4edd0133a1ba15284ebfdd9b0e0cb541ec75db101d251e40fe07
+size 4997133360

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e10b6f7a2db21cdb4fe91b3caf461bc89431233a1328cd617f40e61fc199853
+size 4994522208

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c683f7ce09160109b0d5df5e55d69839ad9a6ee0bacd2b5f6f09a64260f83851
+size 4997418376

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1c6895ff31b766cc1be06b99f5329e736697f1de0ce2297ea2a83b90d199f3
+size 3748241232

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}