ready for LF lora training

.gitignore

@@ -151,3 +151,4 @@ dmypy.json
 /llama.cpp
 /llama-factory/saves
 /llama-factory/saves-1
+/llama-factory/config/models

llama-factory/config/mac_template.yaml

@@ -0,0 +1,42 @@
+### model
+model_name_or_path: ORG_NAME/MODEL_NAME
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: alpaca_mac
+template: CHAT_TEMPLATE
+cutoff_len: 1024
+max_samples: 4528
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/MODEL_NAME
+logging_steps: 5
+save_steps: 35
+plot_loss: true
+# overwrite_output_dir: true
+
+### train
+per_device_train_batch_size: 16
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-4
+num_train_epochs: 6.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+
+### eval
+val_size: 0.01
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 35
+
+report_to: wandb
+run_name: MODEL_NAME_lora_sft

llama-factory/data/alpaca_mac.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1fbf6e56f123addd35f9b89a29227e138e776bb9bdb69c00b1b2014927cf61
+size 3281784

llama-factory/data/dataset_info.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e816fa8e7c69a3075e041f10e322958c2bb4ef705606d471616c509c8290ad9
+size 13692

llm_toolkit/setup_lf.py

@@ -0,0 +1,60 @@
+import os, json, sys, yaml
+from dotenv import find_dotenv, load_dotenv
+
+found_dotenv = find_dotenv(".env")
+
+if len(found_dotenv) == 0:
+    found_dotenv = find_dotenv(".env.example")
+print(f"loading env vars from: {found_dotenv}")
+load_dotenv(found_dotenv, override=False)
+
+path = os.path.dirname(found_dotenv)
+print(f"Adding {path} to sys.path")
+sys.path.append(path)
+
+from llm_toolkit.llm_utils import *
+from llm_toolkit.translation_utils import *
+
+org_name = os.getenv("ORG_NAME")
+model_name = os.getenv("MODEL_NAME")
+chat_template = os.getenv("CHAT_TEMPLATE")
+filename = os.getenv("YAML")
+data_path = os.getenv("DATA_PATH")
+
+print(org_name, model_name, chat_template, filename, data_path)
+
+if not filename:
+    print("Error: Environment variable YAML not set")
+    sys.exit(1)
+
+if not os.path.exists(filename):
+    print(f"Error: File {filename} not found")
+    sys.exit(1)
+
+file = open(filename)
+yaml_content = file.read()
+file.close()
+
+keys = ["ORG_NAME", "MODEL_NAME", "CHAT_TEMPLATE"]
+for key in keys:
+    yaml_content = yaml_content.replace(key, os.getenv(key))
+
+# print(f"YAML content:\n{yaml_content}")
+parts = filename.split("/")
+parts[-1] = "models"
+parts.append(f"{os.getenv('MODEL_NAME')}.yaml")
+filename = "/".join(parts)
+print(f"Writing to {filename}")
+
+# Create the parent directory if it doesn't exist
+os.makedirs(os.path.dirname(filename), exist_ok=True)
+
+file = open(filename, "w")
+file.write(yaml_content)
+file.close()
+
+y = yaml.safe_load(open(filename))
+print(f"{filename}:\n", json.dumps(y, indent=2))
+
+dataset = load_alpaca_data(data_path)
+print_row_details(dataset, [0, -1])

llm_toolkit/translation_utils.py

@@ -92,6 +92,9 @@ def save_results(model_name, results_path, dataset, predictions, debug=False):
     df.to_csv(results_path, index=False)
 
 
+system_prompt = "You are a helpful assistant that translates Chinese to English."
+
+
 def get_few_shot_prompt(dataset, num_shots=5):
     translation_prompt = "You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n\n"
     if num_shots > 0:
@@ -145,7 +148,7 @@ def load_translation_dataset(data_path, tokenizer=None, num_shots=5):
             messages = [
                 {
                     "role": "system",
-                    "content": "You are a helpful assistant that translates Chinese to English.",
+                    "content": system_prompt,
                 },
                 None,
             ]
@@ -485,33 +488,33 @@ def eval_openai(num_shots, datasets, model="gpt-4o-mini", max_new_tokens=300):
     return predictions
 
 
-def convert_time_to_minutes(time_str):
+def convert_time_to_seconds(time_str):
     # print(f"converting time_str: {time_str}")
     # Split the time string into its components
     time_parts = list(map(int, time_str.split(":")))
 
     # Initialize total minutes
-    total_minutes = 0
+    total_seconds = 0
 
     # Calculate total minutes based on the number of parts
     if len(time_parts) == 3:  # HH:MM:SS
         hours, minutes, seconds = time_parts
-        total_minutes = hours * 60 + minutes + seconds / 60
+        total_seconds = hours * 3600 + minutes * 60 + seconds
     elif len(time_parts) == 2:  # MM:SS
         minutes, seconds = time_parts
-        total_minutes = minutes + seconds / 60
+        total_seconds = minutes * 60 + seconds
     elif len(time_parts) == 1:  # SS
         seconds = time_parts[0]
-        total_minutes = seconds / 60
+        total_seconds = seconds
 
-    return total_minutes
+    return total_seconds
 
 
 time_pattern = re.compile(r"\[(.{5,10})<00:00")
 metrics_pattern = re.compile(r"(.*)/shots-(.*) metrics:")
 
 
-def process_log_file(log_file):
+def process_log_file(log_file, total_entries):
     model = []
     shots = []
     eval_time = []
@@ -533,7 +536,9 @@ def process_log_file(log_file):
 
                         groups = time_pattern_matches.groups()
                         time_str = groups[0]
-                        eval_time.append(convert_time_to_minutes(time_str))
+                        eval_time.append(
+                            convert_time_to_seconds(time_str) / total_entries
+                        )
         except Exception as e:
             print(f"Error processing log file: {log_file}")
             print(e)
@@ -548,7 +553,7 @@ def process_log_file(log_file):
     return df
 
 
-def load_eval_times(logs_folder):
+def load_eval_times(logs_folder, total_entries=1133):
     # Get a list of all files in the logs folder
     log_files = glob.glob(os.path.join(logs_folder, "*"))
     log_files.sort()
@@ -557,8 +562,38 @@ def load_eval_times(logs_folder):
 
     for log_file in log_files:
         print(f"Loading content of {log_file}")
-        df = process_log_file(log_file)
+        df = process_log_file(log_file, total_entries=total_entries)
         time_df = pd.concat([time_df, df], ignore_index=True)
 
     time_df["shots"] = time_df["shots"].apply(lambda x: int(x))
     return time_df
+
+
+def load_alpaca_data(data_path):
+    alpaca_data_path = "data/alpaca_mac.json"
+
+    if os.path.exists(alpaca_data_path):
+        print("loading existing data from:", alpaca_data_path)
+        data = pd.read_json(alpaca_data_path, orient="records", lines=False)
+        return data
+
+    datasets = load_translation_dataset(data_path)
+    prompt_template = get_few_shot_prompt(datasets["train"], num_shots=0)
+
+    df_train = datasets["train"].to_pandas()
+    df_train["instruction"] = df_train.apply(
+        lambda x: prompt_template.format(input=x["chinese"]), axis=1
+    )
+
+    df_alpaca = pd.DataFrame(
+        {
+            "system": [system_prompt] * len(df_train),
+            "instruction": df_train["instruction"].to_list(),
+            "input": [""] * len(df_train),
+            "output": df_train["english"].to_list(),
+        }
+    )
+
+    df_alpaca.to_json(alpaca_data_path, orient="records", lines=False, indent=2)
+
+    return df_alpaca

notebooks/00b_Data Analysis_Few_Shots.ipynb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9785edd77e41276edd7d949b04796bb3a2b98fbf4efc56049f074ef0c74e39
-size 645130
+oid sha256:9659822963e465fcc321c5cc538b9e2eabefcc5492ddc1eaaafd510e854b7202
+size 835024

results/mac-results_few_shots_metrics.csv

@@ -1,29 +1,41 @@
 model,shots,meteor,bleu_1,rouge_l,ews_score,repetition_score,total_repetitions,rap,num_max_output_tokens,eval_time
-Qwen/Qwen2-72B-Instruct,0,0.4003638205699929,0.12223832517678616,0.3850228285100058,0.0,0.19593998234774934,0.19593998234774934,0.3970180421898014,1,167.96666666666667
-Qwen/Qwen2-72B-Instruct,1,0.4068727655718769,0.13151008586303575,0.39473841744219135,0.0,0.15798764342453664,0.15798764342453664,0.4041216347207881,1,169.63333333333333
-Qwen/Qwen2-72B-Instruct,3,0.4086244766794449,0.13771788946915253,0.3982274035420223,0.0,0.12709620476610767,0.12709620476610767,0.4063954239173824,0,220.13333333333333
-Qwen/Qwen2-72B-Instruct,5,0.4132330811975005,0.1439773872150899,0.4038550675754348,0.0,0.11915269196822595,0.11915269196822595,0.41111822769434864,0,324.18333333333334
-Qwen/Qwen2-72B-Instruct,10,0.41598174489789025,0.14493475334416772,0.40675496346798323,0.0,0.09620476610767872,0.09620476610767872,0.4142591929807702,0,561.3666666666667
-Qwen/Qwen2-7B-Instruct,0,0.377477070949433,0.11783492823424507,0.36803838669677474,0.0,0.07149161518093557,0.07149161518093557,0.3763128359886437,0,18.516666666666666
-Qwen/Qwen2-7B-Instruct,1,0.38000752971097884,0.11731917392837622,0.3717522235071834,0.0,0.07413945278022947,0.07413945278022947,0.37879237953430883,0,19.883333333333333
-Qwen/Qwen2-7B-Instruct,3,0.38678180999660744,0.12368875746156333,0.37795982050404114,0.0,0.1412180052956752,0.1412180052956752,0.38444052153933106,0,30.233333333333334
-Qwen/Qwen2-7B-Instruct,5,0.38784856371389564,0.1227725469820483,0.38271501720823375,0.0,0.09179170344218888,0.09179170344218888,0.38631555618548774,0,43.233333333333334
-Qwen/Qwen2-7B-Instruct,10,0.38526484346757095,0.12535252418966952,0.381921964717894,0.0,0.10326566637246248,0.10326566637246248,0.3835535147682633,0,75.65
-internlm/internlm2_5-7b-chat,0,0.36816799960793073,0.11360521358693174,0.3604145848797059,0.0,0.2144748455428067,0.2144748455428067,0.3648059323539847,0,23.116666666666667
-internlm/internlm2_5-7b-chat,1,0.3719587471180722,0.1157707566176535,0.3640593681230251,0.0,0.14033539276257723,0.14033539276257723,0.36972107700643503,0,24.783333333333335
-internlm/internlm2_5-7b-chat,3,0.3747105229822289,0.1154826016668525,0.3690935886519632,0.0,0.17740511915269197,0.17740511915269197,0.37187052462735126,0,35.083333333333336
-internlm/internlm2_5-7b-chat,5,0.37285562384505977,0.11541534709366409,0.36890113755410703,0.0,0.14827890556045895,0.14827890556045895,0.37048732274065205,0,54.016666666666666
-internlm/internlm2_5-7b-chat,10,0.3750895095392996,0.11696492920010637,0.3680889860873816,0.0,0.13062665489849956,0.13062665489849956,0.37298723763770353,0,108.06666666666666
-internlm/internlm2_5-7b-chat,50,0.37213069871716603,0.11404688073207249,0.3626467635078598,0.0,0.16857899382171226,0.16857899382171226,0.3694484047441432,8,798.6166666666667
-gpt-4o-mini,0,0.3797696357415517,0.1208238389018596,0.3705758962787884,0.0,0.09532215357458076,0.09532215357458076,0.37821133607113916,0,30.1
-gpt-4o-mini,1,0.37721414424357197,0.12013402254992751,0.36747964103348624,0.0,0.09179170344218888,0.09179170344218888,0.37572317024740703,0,29.583333333333332
-gpt-4o-mini,3,0.3772985230936086,0.12400311006855895,0.3682804376759824,0.0,0.09179170344218888,0.09179170344218888,0.3758072155821894,0,24.3
-gpt-4o-mini,5,0.35541821046691263,0.1202464326274801,0.34720271618869103,0.0,0.05030891438658429,0.05030891438658429,0.3546452926906339,0,22.733333333333334
-gpt-4o-mini,10,0.37335968903521094,0.1257600824824953,0.3659023214917385,0.0,0.0706090026478376,0.0706090026478376,0.37222227656264567,0,22.433333333333334
-gpt-4o-mini,50,0.4044690970661121,0.13972883920222515,0.3916652577211933,0.0,0.08473080317740513,0.08473080317740513,0.4029924080114739,0,24.35
-gpt-4o,0,0.3797419877414444,0.12054600115274576,0.3704105629830775,0.0,0.09532215357458076,0.09532215357458076,0.37818380151840997,0,28.866666666666667
-gpt-4o,1,0.37588586538591867,0.12049862468096047,0.3658901615314057,0.0,0.09179170344218888,0.09179170344218888,0.3744001415355042,0,22.733333333333334
-gpt-4o,3,0.3768512103553621,0.12408746322526747,0.3668998399542892,0.0,0.09355692850838482,0.09355692850838482,0.3753332737090981,0,38.75
-gpt-4o,5,0.35772544915145654,0.12169683347842021,0.3483810267695463,0.0,0.0353045013239188,0.0353045013239188,0.3571787674657609,0,31.8
-gpt-4o,10,0.3746444651189953,0.12498238983123719,0.36712547974906085,0.0,0.0706090026478376,0.0706090026478376,0.37350313867182305,0,33.8
-gpt-4o,50,0.40413933252744955,0.13782450337569063,0.3909558691963182,0.0,0.07590467784642542,0.07590467784642542,0.402816463024093,0,38.25
+Qwen/Qwen2-72B-Instruct,0,0.4003638205699929,0.12223832517678616,0.3847629463750985,0.0,0.19593998234774934,0.19593998234774934,0.3970180421898014,1,8.894969108561341
+Qwen/Qwen2-72B-Instruct,1,0.4068727655718769,0.13151008586303575,0.3944115167988717,0.0,0.15798764342453664,0.15798764342453664,0.4041216347207881,1,8.983230361871138
+Qwen/Qwen2-72B-Instruct,3,0.4086244766794449,0.13771788946915253,0.39794626590394355,0.0,0.12709620476610767,0.12709620476610767,0.4063954239173824,0,11.657546337157987
+Qwen/Qwen2-72B-Instruct,5,0.4132330811975005,0.1439773872150899,0.4036491307620504,0.0,0.11915269196822595,0.11915269196822595,0.41111822769434864,0,17.167696381288614
+Qwen/Qwen2-72B-Instruct,10,0.41598174489789025,0.14493475334416772,0.4065107334928856,0.0,0.09620476610767872,0.09620476610767872,0.4142591929807702,0,29.728155339805824
+Qwen/Qwen2-72B-Instruct,50,0.4401536409204816,0.1538634893900684,0.4172243423111057,0.0,0.10150044130626655,0.10150044130626655,0.43823160654983345,0,112.50397175639894
+Qwen/Qwen2-7B-Instruct,0,0.377477070949433,0.11783492823424507,0.3679428026833277,0.0,0.07149161518093557,0.07149161518093557,0.3763128359886437,0,0.9805825242718447
+Qwen/Qwen2-7B-Instruct,1,0.38000752971097884,0.11731917392837622,0.3716350861124088,0.0,0.07413945278022947,0.07413945278022947,0.37879237953430883,0,1.0529567519858782
+Qwen/Qwen2-7B-Instruct,3,0.38678180999660744,0.12368875746156333,0.3775321935602687,0.0,0.1412180052956752,0.1412180052956752,0.38444052153933106,0,1.6010591350397176
+Qwen/Qwen2-7B-Instruct,5,0.38784856371389564,0.1227725469820483,0.3821016566709109,0.0,0.09179170344218888,0.09179170344218888,0.38631555618548774,0,2.2894969108561343
+Qwen/Qwen2-7B-Instruct,10,0.38526484346757095,0.12535252418966952,0.3819282327854221,0.0,0.10326566637246248,0.10326566637246248,0.3835535147682633,0,4.006178287731686
+Qwen/Qwen2-7B-Instruct,50,0.3953455943001352,0.12949951844499932,0.3902417317381649,0.0,0.10061782877316858,0.10061782877316858,0.39363409715118836,0,17.46425419240953
+internlm/internlm2_5-7b-chat,0,0.36816799960793073,0.11360521358693174,0.3600976114330957,0.0,0.2144748455428067,0.2144748455428067,0.3648059323539847,0,1.2241835834068844
+internlm/internlm2_5-7b-chat,1,0.3719587471180722,0.1157707566176535,0.3636179646738983,0.0,0.14033539276257723,0.14033539276257723,0.36972107700643503,0,1.3124448367166814
+internlm/internlm2_5-7b-chat,3,0.3747105229822289,0.1154826016668525,0.3683821652101455,0.0,0.17740511915269197,0.17740511915269197,0.37187052462735126,0,1.8578993821712269
+internlm/internlm2_5-7b-chat,5,0.37285562384505977,0.11541534709366409,0.3683735908407485,0.0,0.14827890556045895,0.14827890556045895,0.37048732274065205,0,2.860547219770521
+internlm/internlm2_5-7b-chat,10,0.3750895095392996,0.11696492920010637,0.3679980919671262,0.0,0.13062665489849956,0.13062665489849956,0.37298723763770353,0,5.722859664607237
+internlm/internlm2_5-7b-chat,50,0.37213069871716603,0.11404688073207249,0.36275069101944124,0.0,0.16857899382171226,0.16857899382171226,0.3694484047441432,8,42.29214474845543
+shenzhi-wang/Llama3.1-70B-Chinese-Chat,0,0.3638704024273502,0.10874677881601094,0.3532404744913337,0.0,0.15445719329214475,0.15445719329214475,0.3614642386796342,0,7.8331862312444835
+shenzhi-wang/Llama3.1-70B-Chinese-Chat,1,0.37956764543783084,0.11805442002282653,0.3695558384587787,0.0,0.12533097969991175,0.12533097969991175,0.3775255236309064,0,8.307149161518094
+shenzhi-wang/Llama3.1-70B-Chinese-Chat,3,0.38622483411876246,0.12306660851355093,0.374537863679436,0.0,0.14386584289496912,0.14386584289496912,0.38384366117983154,0,11.681376875551633
+shenzhi-wang/Llama3.1-70B-Chinese-Chat,5,0.3895488616778815,0.12582029733797498,0.37834594185588616,0.0,0.14386584289496912,0.14386584289496912,0.38714719527562863,0,17.23389232127096
+shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat,0,0.3284997502705771,0.08313795089297474,0.31822074756329843,0.0,0.12797881729920565,0.12797881729920565,0.3266954815790356,0,1.204766107678729
+shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat,1,0.3342115436248988,0.08857909016110346,0.3235832621122292,0.0,0.6690203000882613,0.6690203000882613,0.3250691235789747,1,1.4819064430714917
+shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat,3,0.3435621946945506,0.09605927100886698,0.3339835066382988,0.0,0.1262135922330097,0.1262135922330097,0.3417009211692762,0,2.262135922330097
+shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat,5,0.34429078135481284,0.09638489591361771,0.33821501828549394,0.0,0.07590467784642542,0.07590467784642542,0.34316381414750663,2,3.3883495145631066
+shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat,10,0.3408431061510028,0.09735670499814125,0.3331263575051163,0.0,0.10414827890556046,0.10414827890556046,0.339316280986861,11,6.558693733451015
+shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat,50,0.36184201368489227,0.104864029030581,0.34553515243463534,0.0,0.5136804942630185,0.5136804942630185,0.35413782502473057,2,29.659311562224183
+gpt-4o-mini,0,0.3797696357415517,0.1208238389018596,0.37039368743666584,0.0,0.09532215357458076,0.09532215357458076,0.37821133607113916,0,1.5939982347749337
+gpt-4o-mini,1,0.37721414424357197,0.12013402254992751,0.36725632920414286,0.0,0.09179170344218888,0.09179170344218888,0.37572317024740703,0,1.5666372462488967
+gpt-4o-mini,3,0.3772985230936086,0.12400311006855895,0.36822411288225565,0.0,0.09179170344218888,0.09179170344218888,0.3758072155821894,0,1.2868490732568403
+gpt-4o-mini,5,0.35541821046691263,0.1202464326274801,0.3472080523493449,0.0,0.05030891438658429,0.05030891438658429,0.3546452926906339,0,1.203883495145631
+gpt-4o-mini,10,0.37335968903521094,0.1257600824824953,0.36566914304808296,0.0,0.0706090026478376,0.0706090026478376,0.37222227656264567,0,1.1879964695498677
+gpt-4o-mini,50,0.4044690970661121,0.13972883920222515,0.39117898438510224,0.0,0.08473080317740513,0.08473080317740513,0.4029924080114739,0,1.289496910856134
+gpt-4o,0,0.3797419877414444,0.12054600115274576,0.3704197875229349,0.0,0.09532215357458076,0.09532215357458076,0.37818380151840997,0,1.528684907325684
+gpt-4o,1,0.37588586538591867,0.12049862468096047,0.36572207722254313,0.0,0.09179170344218888,0.09179170344218888,0.3744001415355042,0,1.203883495145631
+gpt-4o,3,0.3768512103553621,0.12408746322526747,0.36677555510252513,0.0,0.09355692850838482,0.09355692850838482,0.3753332737090981,0,2.05207413945278
+gpt-4o,5,0.35772544915145654,0.12169683347842021,0.3480606673293163,0.0,0.0353045013239188,0.0353045013239188,0.3571787674657609,0,1.6840247131509267
+gpt-4o,10,0.3746444651189953,0.12498238983123719,0.36695107795536486,0.0,0.0706090026478376,0.0706090026478376,0.37350313867182305,0,1.7899382171226832
+gpt-4o,50,0.40413933252744955,0.13782450337569063,0.3905031632820436,0.0,0.07590467784642542,0.07590467784642542,0.402816463024093,0,2.025595763459841

scripts/eval-mac.sh

@@ -14,15 +14,13 @@ grep MemTotal /proc/meminfo
 # pip install torch torchvision torchaudio
 # pip install -r requirements.txt
 
-export START_NUM_SHOTS=50
+# export START_NUM_SHOTS=50
 
-./scripts/eval-model.sh 01-ai/Yi-1.5-9B-Chat
+./scripts/eval-model.sh internlm/internlm2_5-7b-chat
 
-# ./scripts/eval-model.sh internlm/internlm2_5-7b-chat
+./scripts/eval-model.sh Qwen/Qwen2-7B-Instruct
 
-# ./scripts/eval-model.sh Qwen/Qwen2-7B-Instruct
+./scripts/eval-model.sh shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat
 
-# ./scripts/eval-model.sh shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat
-
-# ./scripts/eval-model.sh shenzhi-wang/Llama3.1-8B-Chinese-Chat
+./scripts/eval-model.sh shenzhi-wang/Llama3.1-8B-Chinese-Chat
 

scripts/tune-lf.sh

@@ -0,0 +1,15 @@
+#!/bin/sh
+
+BASEDIR=$(dirname "$0")
+cd $BASEDIR/../llama-factory/
+echo Current Directory:
+pwd
+
+export ORG_NAME=$1
+export MODEL_NAME=$2
+export CHAT_TEMPLATE=$3
+export DATA_PATH=../datasets/mac/mac.tsv
+export YAML=config/mac_template.yaml
+
+python ../llm_toolkit/setup_lf.py
+llamafactory-cli train config/models/$MODEL_NAME.yaml

scripts/tune-mac.sh

@@ -0,0 +1,23 @@
+#!/bin/sh
+
+BASEDIR=$(dirname "$0")
+cd $BASEDIR/..
+echo Current Directory:
+pwd
+
+nvidia-smi
+uname -a
+cat /etc/os-release
+lscpu
+grep MemTotal /proc/meminfo
+
+#pip install -r requirements.txt
+cd ../LLaMA-Factory && pip install -e .[torch,metrics] && cd -
+
+./scripts/tune-lf.sh internlm internlm2_5-7b-chat intern2
+
+./scripts/tune-lf.sh Qwen Qwen2-7B-Instruct qwen
+
+./scripts/tune-lf.sh shenzhi-wang Mistral-7B-v0.3-Chinese-Chat mistral
+
+./scripts/tune-lf.sh shenzhi-wang Llama3.1-8B-Chinese-Chat llama3