End of training

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: deepseek-ai/deepseek-llm-7b-base
+base_model: deepseek-ai/deepseek-llm-7b-chat
 library_name: transformers
-model_name: SFT_FineTuned_DeepSeek-7B-v0.1
+model_name: SFT_FineTuned_DeepSeek-7B-chat-v0.1
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for SFT_FineTuned_DeepSeek-7B-v0.1
+# Model Card for SFT_FineTuned_DeepSeek-7B-chat-v0.1
 
-This model is a fine-tuned version of [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base).
+This model is a fine-tuned version of [deepseek-ai/deepseek-llm-7b-chat](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -27,7 +27,7 @@ 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/matansiva-anna-university/SFT_DEEPSEEKv1.1/runs/oyqljj01) 
+[<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/matansiva-anna-university/SFT_DEEPSEEKv1.1/runs/oaihj0ih) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "deepseek-ai/deepseek-llm-7b-base",
+  "base_model_name_or_path": "deepseek-ai/deepseek-llm-7b-chat",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -26,12 +26,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "down_proj",
     "k_proj",
     "o_proj",
-    "up_proj",
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32a61dc335bbcb885fcdb29afa597118c696a39ccc504b7b0a06ee3112e7d617
+oid sha256:1ef9953aa89a5e9432230d292318a48f483b5916a5b4283491e0ae749da4b621
 size 10073752920

tokenizer_config.json

@@ -125,6 +125,7 @@
     }
   },
   "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<｜end▁of▁sentence｜>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1b9223d1e8f892752b4d46fbef7f79d07b8a72201343939f08392395de8c301
+oid sha256:901a0d085a9a569d944f3538f5538d28d883ae77496fdd4b2c098d6f0b99680e
 size 5560