End of training

README.md

@@ -1,9 +1,58 @@
 ---
-license: mit
-base_model:
-- deepseek-ai/DeepSeek-V3
-pipeline_tag: text-generation
+base_model: tonyshark/deepdeek-v3-1b
 library_name: transformers
+model_name: deepdeek-v3-1b
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
 ---
-# DeepSeek V3 1B Test
-This model is randomly initialized for testing implementations, it's **not** a trained model and it will only generate random tokens.
+
+# Model Card for deepdeek-v3-1b
+
+This model is a fine-tuned version of [tonyshark/deepdeek-v3-1b](https://huggingface.co/tonyshark/deepdeek-v3-1b).
+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="tonyshark/deepdeek-v3-1b", 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/tonyshark365-aixblock/huggingface/runs/fd6g1fre) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.13.0
+- Transformers: 4.47.1
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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 Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

config.json

@@ -1,14 +1,14 @@
 {
-  "_name_or_path": "deepseek-v3-1b",
+  "_name_or_path": "tonyshark/deepdeek-v3-1b",
   "architectures": [
     "DeepseekV3ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
-    "AutoModel": "modeling_deepseek.DeepseekV3Model",
-    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+    "AutoConfig": "tonyshark/deepdeek-v3-1b--configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "tonyshark/deepdeek-v3-1b--modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "tonyshark/deepdeek-v3-1b--modeling_deepseek.DeepseekV3ForCausalLM"
   },
   "aux_loss_alpha": 0.001,
   "bos_token_id": 0,
@@ -54,7 +54,7 @@
   "tie_word_embeddings": false,
   "topk_group": 4,
   "topk_method": "noaux_tc",
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.47.1",
   "use_cache": true,
   "v_head_dim": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9db5309afa023828200507bbe04d1aaff8667510b47b24ac999f340876da1ee
-size 2099235336
+oid sha256:98055ce78ca046c4d239892034abb11415818575dff3fccd3effe00d4bd8067e
+size 4198331024

runs/Jan06_14-42-19_568fc3dd2737/events.out.tfevents.1736174543.568fc3dd2737.2792.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7bfc97850606cfd2502d6e5c08af8c2744ea1d1f27c56e4c42aa5c8578fb6b
+size 6390

runs/Jan06_15-00-00_568fc3dd2737/events.out.tfevents.1736175601.568fc3dd2737.2792.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965874718edfee6555923e5222f0a60f41d85d93ae0e55e74ecfc0f33672aa01
+size 6390

runs/Jan06_15-00-57_568fc3dd2737/events.out.tfevents.1736175658.568fc3dd2737.2792.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c24676654cbafecb33796eaa7cbe8fccda6d1dcdf42b5e25a402bb1c961d03ef
+size 6390

runs/Jan06_15-01-12_568fc3dd2737/events.out.tfevents.1736175673.568fc3dd2737.2792.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269299b06f43c7be46a8b3211e95c4859e0d2a6cf34784ed6381c453b3c77f70
+size 6390

runs/Jan06_15-05-48_568fc3dd2737/events.out.tfevents.1736175949.568fc3dd2737.2792.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2e5c25c9d5f2e6ba1ab78cb7aeb9394e342df03d94eca47813d62466ffd202
+size 12519

runs/Jan06_15-28-47_568fc3dd2737/events.out.tfevents.1736177328.568fc3dd2737.2792.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c362b0ff8146487b3771ced01c8db20e0ccdb8dfa4b60b590cd964d55de79e74
+size 12519

tokenizer.json

@@ -7419,6 +7419,12 @@
           "id": "A",
           "type_id": 0
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "<｜end▁of▁sentence｜>",
+          "type_id": 0
+        }
       }
     ],
     "pair": [
@@ -7434,6 +7440,12 @@
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "<｜end▁of▁sentence｜>",
+          "type_id": 0
+        }
+      },
       {
         "SpecialToken": {
           "id": "<｜begin▁of▁sentence｜>",
@@ -7445,6 +7457,12 @@
           "id": "B",
           "type_id": 1
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "<｜end▁of▁sentence｜>",
+          "type_id": 1
+        }
       }
     ],
     "special_tokens": {
@@ -7456,6 +7474,15 @@
         "tokens": [
           "<｜begin▁of▁sentence｜>"
         ]
+      },
+      "<｜end▁of▁sentence｜>": {
+        "id": "<｜end▁of▁sentence｜>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "<｜end▁of▁sentence｜>"
+        ]
       }
     }
   },

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
+  "add_eos_token": true,
   "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0480284713e598a4a5c2a8cea0dfb8e429e3e644cefc1bb93573453da3a97573
+size 5560