Training in progress, step 488

README.md

@@ -0,0 +1,59 @@
+---
+base_model: Ba2han/phi-transation
+library_name: transformers
+model_name: phi-transation-2
+tags:
+- generated_from_trainer
+- trl
+- sft
+- unsloth
+licence: license
+---
+
+# Model Card for phi-transation-2
+
+This model is a fine-tuned version of [Ba2han/phi-transation](https://huggingface.co/Ba2han/phi-transation).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Ba2han/phi-transation-2", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/blr1e1p4) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.23.1
+- Transformers: 5.0.0rc0
+- Pytorch: 2.9.0+cu128
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}<｜hy_begin▁of▁sentence｜>{{ system_message }}<｜hy_place▁holder▁no▁3｜>{% else %}{% set loop_messages = messages %}<｜hy_begin▁of▁sentence｜>{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}<｜hy_User｜>{{ message['content'] }}{% elif message['role'] == 'assistant' %}<｜hy_Assistant｜>{{ message['content'] }}<｜hy_place▁holder▁no▁2｜>{% endif %}{% endfor %}{% if add_generation_prompt %}<｜hy_Assistant｜>{% else %}<｜hy_place▁holder▁no▁8｜>{% endif %}

config.json

@@ -0,0 +1,62 @@
+{
+  "add_classification_head": false,
+  "architectures": [
+    "HunYuanDenseV1ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_head_dim": 128,
+  "bos_token_id": 120000,
+  "cla_share_factor": 2,
+  "class_num": 0,
+  "dense_list": [
+    2048,
+    0
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 120020,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "im_end_id": 5,
+  "im_newline_id": 11,
+  "im_start_id": 4,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "mask_init_id": 12,
+  "max_position_embeddings": 262144,
+  "mlp_bias": false,
+  "model_type": "hunyuan_v1_dense",
+  "norm_type": "rms",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "org_vocab_size": 120818,
+  "pad_id": 120002,
+  "pad_token_id": 120002,
+  "pool_type": "last",
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "alpha": 1000.0,
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 1.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "rope_theta": 10000.0,
+    "rope_type": "dynamic",
+    "type": "dynamic"
+  },
+  "sep_token_id": 120007,
+  "text_end_id": 7,
+  "text_start_id": 6,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0rc0",
+  "unsloth_version": "2026.1.3",
+  "use_cache": false,
+  "use_cla": false,
+  "use_qk_norm": true,
+  "use_rotary_pos_emb": true,
+  "vocab_size": 120821
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 120000,
+  "do_sample": true,
+  "eos_token_id": [
+    120020,
+    120001
+  ],
+  "max_length": 262144,
+  "pad_token_id": 120002,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.0.0rc0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db3a62c1819bacbea34efe1f5ee87aa9e2b7d38b490e4bb8c67fdc8c28b4c90
+size 3582214344

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<｜hy_begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<｜hy_place▁holder▁no▁2｜>",
+  "extra_special_tokens": [
+    "<|source|>",
+    "<|translation|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "<｜hy_▁pad▁｜>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c85d0c7760119d16a5d1e1c7079a4db56d9d1a5d60b496db06591ca0556bfdf3
+size 5713