Upload 12 files

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "MiniMaxText01ForCausalLM"
+    "MiniMaxForCausalLM"
   ],
   "attention_dropout": 0.0,
   "layer_types": [

create.py

@@ -8,7 +8,7 @@ model_dir = "/Users/Goekdeniz.Guelmez@computacenter.com/Library/CloudStorage/One
 sys.path.append(model_dir)
 
 # Import your custom model and configuration classes
-from modular_minimax import MiniMaxForCausalLM
+from modeling_minimax import MiniMaxForCausalLM
 from configuration_minimax import MiniMaxConfig
 
 # Load the configuration

modeling_minimax.py

@@ -604,7 +604,7 @@ class MiniMaxModel(MiniMaxPreTrainedModel):
         # Initialize weights and apply final processing
         self.post_init()
 
-    @check_model_inputs()
+    @check_model_inputs
     def forward(
         self,
         input_ids: Optional[torch.LongTensor] = None,

print.py

@@ -0,0 +1,10 @@
+from transformers import AutoModelForCausalLM
+
+model = "/Users/Goekdeniz.Guelmez@computacenter.com/Library/CloudStorage/OneDrive-COMPUTACENTER/Desktop/MiniMax01Text-Dev"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model,
+    trust_remote_code=True
+)
+
+print(model)

test.py

@@ -1,25 +1,25 @@
 from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig, QuantoConfig, GenerationConfig
 
-# load hf config
-hf_config = AutoConfig.from_pretrained("/Users/gokdenizgulmez/Desktop/mlx-lm/mlx_lm/MiniMiniMax01Text", trust_remote_code=True)
+model = "/Users/Goekdeniz.Guelmez@computacenter.com/Library/CloudStorage/OneDrive-COMPUTACENTER/Desktop/MiniMax01Text-Dev"
 
-tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-Text-01")
+hf_config = AutoConfig.from_pretrained(model, trust_remote_code=True)
+
+tokenizer = AutoTokenizer.from_pretrained(model)
 prompt = "Hello!"
 messages = [
-    {"role": "system", "content": [{"type": "text", "text": "You are a helpful assistant created by MiniMax based on MiniMax-Text-01 model."}]},
-    {"role": "user", "content": [{"type": "text", "text": prompt}]},
+    {"role": "system", "content": "You are a helpful assistant created by MiniMax based on MiniMax-Text-01 model."},
+    {"role": "user", "content": prompt},
 ]
 text = tokenizer.apply_chat_template(
     messages,
     tokenize=False,
     add_generation_prompt=True
 )
-# tokenize and move to device
-model_inputs = tokenizer(text, return_tensors="pt")
 
+model_inputs = tokenizer(text, return_tensors="pt")
 
 model = AutoModelForCausalLM.from_pretrained(
-    "/Users/gokdenizgulmez/Desktop/mlx-lm/mlx_lm/MiniMiniMax01Text",
+    model,
     trust_remote_code=True
 )
 
@@ -29,8 +29,8 @@ generation_config = GenerationConfig(
     use_cache=True,
 )
 generated_ids = model.generate(**model_inputs, generation_config=generation_config)
-print(f"generated_ids: {generated_ids}")
 generated_ids = [
     output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
 ]
-response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)

tokenizer.json

@@ -236,6 +236,96 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 200026,
+      "content": "<video>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200027,
+      "content": "<start_of_speech>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200028,
+      "content": "<end_of_speech>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200029,
+      "content": "<start_of_image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200030,
+      "content": "<end_of_image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200031,
+      "content": "<start_of_video>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200032,
+      "content": "<end_of_video>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200033,
+      "content": "<vision_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200034,
+      "content": "<begin_of_document>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 200035,
+      "content": "<jupyter_error>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -6,5 +6,5 @@
   "model_max_length": 40960000,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<end_of_document>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<beginning_of_sentence>system ai_setting=assistant\\n' + message['content'][0]['text'] + '<end_of_sentence>\\n'}}{% elif message['role'] == 'user' %}{{ '<beginning_of_sentence>user name=user\\n' + message['content'][0]['text'] + '<end_of_sentence>\\n'}}{% elif message['role'] == 'assistant' %}{{ '<beginning_of_sentence>ai name=assistant\\n' }}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{{ '<end_of_sentence>\\n' }}{% elif message['role'] == 'function' %}{{ '<beginning_of_sentence>system function_response=functions\\n' + '{\"name\": \"' + message['name'] + '\", \"response\": ' + message['content'][0]['text'] + '}' + '<end_of_sentence>\\n'}}{% endif %}{% endfor %}{% if tools %}{% for function in tools %}{{ '<beginning_of_sentence>system function_setting=functions\\n' + function | tojson + '<end_of_sentence>\\n'}}{% endfor %}{% endif %}{% if add_generation_prompt %}{{ '<beginning_of_sentence>ai name=assistant\\n' }}{% endif %}"
+  "chat_template": "{{ '<begin_of_document>' -}}{% set ns = namespace(system_prompt='') -%}{% for message in messages -%}{% if message['role'] == 'system' -%}{% set text = message['content'][0]['text'] if message['content'] is not string else message['content'] -%}{% set ns.system_prompt = ns.system_prompt + text -%}{% endif -%}{%- endfor -%}{% if ns.system_prompt != '' -%}{{ '<beginning_of_sentence>system ai_setting=assistant\n' + ns.system_prompt + '<end_of_sentence>\n' -}}{%- endif -%}{% if tools -%}{{ '<beginning_of_sentence>system tool_setting=tools\nYou are provided with these tools:\n<tools>\n' -}}{% for tool in tools -%}{{ tool | tojson ~ '\n' -}}{%- endfor -%}{{ '</tools>\n\nIf you need to call tools, please respond with <tool_calls></tool_calls> XML tags, and provide tool-name and json-object of arguments, following the format below:\n<tool_calls>\n{''name'': <tool-name-1>, ''arguments'': <args-json-object-1>}\n...\n</tool_calls><end_of_sentence>\n' -}}{%- endif -%}{% for message in messages -%}{% set text = message['content'][0]['text'] if message['content'] is not string else message['content'] -%}{% if message['role'] == 'user' -%}{{ '<beginning_of_sentence>user name=user\n' + text + '<end_of_sentence>\n' -}}{% elif message['role'] == 'assistant' -%}{{ '<beginning_of_sentence>ai name=assistant\n' -}}{% if message['content'] is string -%}{{ message['content'] -}}{% else -%}{% for content in message['content'] | selectattr('type', 'equalto', 'text') -%}{{ content['text'] -}}{%- endfor -%}{%- endif -%}{{ '<end_of_sentence>\n' -}}{% elif message['role'] == 'tool' -%}{{ '<beginning_of_sentence>tool name=tools\n' }} {%- for content in message['content'] -%}{{- 'tool name: ' + content['name'] + '\n' + 'tool result: ' + (content['text'] if 'text' in content else content) + '\n\n' -}} {%- endfor -%}{{- '<end_of_sentence>\n' -}}{% endif -%}{%- endfor -%}{% if add_generation_prompt -%}{{ '<beginning_of_sentence>ai name=assistant\n' -}}{%- endif -%}"
 }