amakura/gcfree_model_final_64k

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/phi-3-mini-4k-instruct-bnb-4bit
+base_model: unsloth/phi-3.5-mini-instruct-bnb-4bit
 library_name: transformers
 model_name: code_model
 tags:
@@ -12,7 +12,7 @@ licence: license
 
 # Model Card for code_model
 
-This model is a fine-tuned version of [unsloth/phi-3-mini-4k-instruct-bnb-4bit](https://huggingface.co/unsloth/phi-3-mini-4k-instruct-bnb-4bit).
+This model is a fine-tuned version of [unsloth/phi-3.5-mini-instruct-bnb-4bit](https://huggingface.co/unsloth/phi-3.5-mini-instruct-bnb-4bit).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +28,7 @@ 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/amura-n-a/huggingface/runs/7y3mu85e) 
+[<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/amura-n-a/huggingface/runs/jrg7lvn4) 
 
 
 This model was trained with SFT.
@@ -36,10 +36,10 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.13.0
-- Transformers: 4.46.3
+- Transformers: 4.47.1
 - Pytorch: 2.5.1+cu121
 - Datasets: 3.2.0
-- Tokenizers: 0.20.3
+- Tokenizers: 0.21.0
 
 ## Citations
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/phi-3-mini-4k-instruct-bnb-4bit",
+  "base_model_name_or_path": "unsloth/phi-3.5-mini-instruct-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
     "gate_proj",
-    "o_proj",
-    "up_proj",
-    "down_proj",
     "q_proj",
-    "k_proj"
+    "up_proj",
+    "o_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a43f9cb92717682e4076e1053dc4abc3066ca1cdec21c63bc28f4a9762160d
+oid sha256:b74b7ae3dba999ab6787f7bd69c6ec97ff1f7ed025e261aafa558acd89e07d16
 size 119597408

runs/Jan06_09-56-32_81f15d1fc8dd/events.out.tfevents.1736157410.81f15d1fc8dd.1246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65e8c8264dd23de5878e095c02c03d4ba9c62ab965ee4c802910e5bf462c100
+size 11129

special_tokens_map.json

@@ -17,7 +17,7 @@
     "content": "<|placeholder6|>",
     "lstrip": false,
     "normalized": false,
-    "rstrip": false,
+    "rstrip": true,
     "single_word": false
   },
   "unk_token": {

tokenizer.json

@@ -121,7 +121,7 @@
       "content": "<|placeholder6|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },

tokenizer_config.json

@@ -103,7 +103,7 @@
       "content": "<|placeholder6|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -117,11 +117,12 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
   "legacy": false,
-  "model_max_length": 4096,
+  "model_max_length": 131072,
   "pad_token": "<|placeholder6|>",
   "padding_side": "left",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05533f8bf6a569bdaa671c2d5cf1d43248fe71d50f597af3338f72699460c2f9
+oid sha256:16ac76af50a8ef123a0fcda39fc57a69425e0d7288d8d36356a11b9f05aaba55
 size 5560