anyiwang/mistral_4

README.md

@@ -27,17 +27,18 @@ print(output["generated_text"])
 
 ## Training procedure
 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.1
-- Transformers: 4.46.2
+- TRL: 0.13.0
+- Transformers: 4.47.1
 - Pytorch: 2.1.0+cu118
-- Datasets: 3.1.0
-- Tokenizers: 0.20.3
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
 
 ## Citations
 

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,14 +23,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
     "q_proj",
-    "o_proj",
-    "v_proj",
+    "k_proj",
+    "lm_head",
     "up_proj",
-    "down_proj",
-    "lm_head"
+    "v_proj",
+    "o_proj",
+    "gate_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 sha256:9c2e34ba60229c57d14e64291516a24d8568a33307e583e25cc67df9301dafdf
+oid sha256:271ccaaf4a588fe9d0d16b982cd1950befc5e2068d8e224316c02497189c38dc
 size 694431312

tokenizer_config.json

@@ -33,6 +33,7 @@
   "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6e97fdbce8c0d2e2e113e20b76b698a69b3d78297aec90be2b9a3328d8d3c1
-size 5496
+oid sha256:ce616ed5cf59c52861396a564fc65ae638d6771cd3ecdd2b8fe56255abb796e0
+size 5560