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/qwen2.5/SHA256SUMS.ci

@@ -0,0 +1,6 @@
+cd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f *chat_template.jinja
+45134b857367fdcb97c0179199848c353fc28f8b95ac2244ac8f45cca448d864 *config.json
+e81e23e025c38e825dcf8375861e26a90e804276e4db9ee390122a4fdc95dae7 *generation_config.json
+bd86541d817978c896bd3579e69ae6d41b6382eaf1646accf83d6feb16acb703 *model.safetensors
+f7f96da3a872b5e901575b2067c744ad336c3a3d77a21584d20024557b1bd7f0 *tokenizer.json
+04b1682c59acbd057f4c9072297faa73d56fc9de053094c659cdb4c464f58f86 *tokenizer_config.json

tests/qwen2.5/SHA256SUMS.windows

@@ -0,0 +1,6 @@
+8aa40ce145adb73cb3a75194dc0224702a95850ec5275cabb728496bbd749fc6 *chat_template.jinja
+e8f2fcd2681eb92233c0902866441f79a207b235f0b03364d41ebf8c53df62a0 *config.json
+3fec6d7004e5ae311864de130b62e32dac87569874c91b3fe9c46e9309345c1c *generation_config.json
+bd86541d817978c896bd3579e69ae6d41b6382eaf1646accf83d6feb16acb703 *model.safetensors
+f7f96da3a872b5e901575b2067c744ad336c3a3d77a21584d20024557b1bd7f0 *tokenizer.json
+154e5ff1e7c152d964edf30da854ea62465c767719ac8e97e58babf2d4fa9079 *tokenizer_config.json

tests/qwen2.5/config.toml

@@ -0,0 +1,46 @@
+# This test case is for row_normalization="pre".
+# After any change related to it, this test should PASS.
+
+model = "tiny-random/qwen2.5"
+model_commit = "7a6a3128ee4137a248d6d1582824592b87a81647"
+
+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 = "pre"
+
+[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"