Upload 2 files

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "MiniMaxText01ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_type_list": [
+    0,
+    1,
+    0,
+    1
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_minimax_text_01.MiniMaxText01Config",
+    "AutoModelForCausalLM": "modeling_minimax_text_01.MiniMaxText01ForCausalLM"
+  },
+  "bos_token_id": null,
+  "eos_token_id": 200020,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layernorm_full_attention_alpha": 3.5565588200778455,
+  "layernorm_full_attention_beta": 1.0,
+  "layernorm_linear_attention_alpha": 3.5565588200778455,
+  "layernorm_linear_attention_beta": 1.0,
+  "layernorm_mlp_alpha": 3.5565588200778455,
+  "layernorm_mlp_beta": 1.0,
+  "max_position_embeddings": 1024,
+  "model_type": "minimax_text_01",
+  "num_attention_heads": 4,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 2,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "postnorm": true,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000,
+  "rotary_dim": 16,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "shared_intermediate_size": 0,
+  "shared_moe_mode": "sigmoid",
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 200064
+}

test.py

@@ -0,0 +1,36 @@
+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)
+
+tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-Text-01")
+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}]},
+]
+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 = AutoModelForCausalLM.from_pretrained(
+    "/Users/gokdenizgulmez/Desktop/mlx-lm/mlx_lm/MiniMiniMax01Text",
+    trust_remote_code=True
+)
+
+generation_config = GenerationConfig(
+    max_new_tokens=20,
+    eos_token_id=200020,
+    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]