Update tiny models for MiniMaxForCausalLM

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1 @@
+{% 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 %}

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "MiniMaxForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "block_size": 3,
+  "bos_token_id": 200019,
+  "dtype": "float32",
+  "eos_token_id": 200020,
+  "full_attn_alpha_factor": 1,
+  "full_attn_beta_factor": 1,
+  "head_dim": 16,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_decoder": true,
+  "layer_types": [
+    "full_attention",
+    "linear_attention"
+  ],
+  "linear_attn_alpha_factor": 1,
+  "linear_attn_beta_factor": 1,
+  "max_position_embeddings": 512,
+  "mlp_alpha_factor": 1,
+  "mlp_beta_factor": 1,
+  "model_type": "minimax",
+  "num_attention_heads": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 200026
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 200019,
+  "eos_token_id": 200020,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5747f16a620c9dbf2c2453a0ba2e8d77ce97cd9f53a86052e3c65cf74a8d45e3
+size 51451136

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eca5e94e3f4a5ce117640723d37cd09d24a7056b19bd89b74c29191b77a5597
+size 15517253

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<beginning_of_sentence>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<end_of_sentence>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<end_of_document>"
+}