elliotthwang/Mistral-7B-Instruct-v0.2-tw-train_ouputs

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: elliotthwang/Ministral-4b-instruct-tw_1k
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 library_name: transformers
 model_name: outputs
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for outputs
 
-This model is a fine-tuned version of [elliotthwang/Ministral-4b-instruct-tw_1k](https://huggingface.co/elliotthwang/Ministral-4b-instruct-tw_1k).
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -34,10 +34,10 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.16.1
-- Transformers: 4.51.1
+- TRL: 0.18.1
+- Transformers: 4.52.2
 - Pytorch: 2.6.0+cu124
-- Datasets: 3.5.0
+- Datasets: 3.6.0
 - Tokenizers: 0.21.1
 
 ## Citations
@@ -49,7 +49,7 @@ 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},
+	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},

adapter_config.json

@@ -1,8 +1,9 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "elliotthwang/Ministral-4b-instruct-tw_1k",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
+  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -24,12 +25,13 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "gate_proj",
-    "q_proj",
+    "k_proj",
     "v_proj",
-    "k_proj"
+    "gate_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aacb936da69c016bd8269af3f4779c532230c31c50434b0eecf02d3db87e6d9a
-size 38839760
+oid sha256:52189c532977c742b7fe78a336a35b654c9e4470ce77f75b0a20f31ef6cc135f
+size 46179856

chat_template.jinja

@@ -0,0 +1,24 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
+        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- if loop.first and system_message is defined %}
+            {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }}
+        {%- else %}
+            {{- ' [INST] ' + message['content'] + ' [/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {{- ' ' + message['content'] + eos_token}}
+    {%- else %}
+        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
+    {%- endif %}
+{%- endfor %}

runs/May30_10-14-38_2a9f8f30fcd1/events.out.tfevents.1748600080.2a9f8f30fcd1.1234.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12c84ff1231c1288a827061b5c0e71a3ef9320ea0f1d0ff5e5b86bdacf0c704
+size 335322

special_tokens_map.json

@@ -13,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -30,14 +30,12 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '### User:\\n' + message['content'] + '\\n#### Assistant:\\n' }}{% elif message['role'] == 'system' %}{{ '### System:\\n' + message['content'] + '\\n' }}{% elif message['role'] == 'assistant' %}{{ message['content'] }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "padding_side": "right",
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82404c1bf537fc27d98e14da82fbebf16f5c7bb3d532cadb36de4fc1fba53217
+oid sha256:730426600dec18a000cbbe9011a0b4e35d040a9bdc822fcbf7ca8161a998bd37
 size 5560