fix: use W_org matrix only where needed (#398)

* fix: minor change

use `W_org` matrix where needed...

* Update model.py

* Update model.py

* fix: Windows hash, remove BOM marker

* docs: Add info about test cases

* feat: Tests for row_normalization PRE & NONE

* feat: CI hash files for row_normalization PRE & NONE models

* feat: Documentation instructions about test suite

* add recommendation

tests/minicpm5/SHA256SUMS.ci

@@ -0,0 +1,6 @@
+7451a05cf1e28a79d97d7c0bc951028c0b1915119bf9046acd06a0e3d931f47c *chat_template.jinja
+fe6fd41d9f2ce5d6486748cf0330b574f37bf7d4e915f7b39d1af1a185cac3c3 *config.json
+c4c2ef5ae4a4e2dd10655a3b99d801a8a50497286ddd042ba35bcfefc44ad349 *generation_config.json
+1535a9b7a91b2cb39ad280dbd9a940e2609a0b423d5b924df4d664e579912802 *model.safetensors
+ad92aaa8d3032c98a9158b8c5e8682bed10027ed6463e4fb1320fe5384210873 *tokenizer.json
+3ad32522c384dbe35192bb69de9befbf3f523e99d4bb3f95da757671d4c28281 *tokenizer_config.json

tests/minicpm5/SHA256SUMS.windows

@@ -0,0 +1,6 @@
+d8db3ff45c4c68a0ba9dee962ff1a0adde9a2be55e0895306f6bd2b2756f5adb *chat_template.jinja
+a9d6f64bb9d0c02b553119e475615153af625b5c2a16ccb8fb8b3c2cc348f465 *config.json
+0e7611a1e8fd0a06a139b0572b2c55b885ba9fb7db2022873c3508aebfb488aa *generation_config.json
+411d95f42d3e31aef41c28314c8f0431c980687a97904d32b4ef57c42199720f *model.safetensors
+ad92aaa8d3032c98a9158b8c5e8682bed10027ed6463e4fb1320fe5384210873 *tokenizer.json
+aa083f3da10340925734e876e41e235c459329294ecd35d7511ec5868c1f14e3 *tokenizer_config.json

tests/minicpm5/config.toml

@@ -0,0 +1,46 @@
+# This test case is for row_normalization="none".
+# After any change related to it, this test should PASS.
+
+model = "tiny-random/minicpm5"
+model_commit = "52270c5ae5dde31255029cd5958591db057bd377"
+
+seed = 12345
+print_debug_information = true
+
+batch_size = 2
+max_response_length = 10
+kl_divergence_target = 0
+n_trials = 2
+n_startup_trials = 1
+
+export_strategy = "merge"
+checkpoint_action = "restart"
+trial_index = 0
+model_action = "save"
+save_directory = "model"
+
+row_normalization = "none"
+
+[good_prompts]
+dataset = "mlabonne/harmless_alpaca"
+commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
+split = "train[:5]"
+column = "text"
+
+[bad_prompts]
+dataset = "mlabonne/harmful_behaviors"
+commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
+split = "train[:5]"
+column = "text"
+
+[good_evaluation_prompts]
+dataset = "mlabonne/harmless_alpaca"
+commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
+split = "test[:5]"
+column = "text"
+
+[bad_evaluation_prompts]
+dataset = "mlabonne/harmful_behaviors"
+commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
+split = "test[:5]"
+column = "text"