Update params.json

params.json

@@ -1,85 +1,12 @@
 {
-  "vocab_size": 131072,
-  "max_position_embeddings": 32768,
-  "hidden_size": 5120,
-  "intermediate_size": 32768,
-  "num_hidden_layers": 40,
-  "num_attention_heads": 32,
-  "sliding_window": null,
-  "head_dim": 128,
-  "num_key_value_heads": 8,
-  "hidden_act": "silu",
-  "initializer_range": 0.02,
-  "rms_norm_eps": 1e-05,
-  "use_cache": true,
-  "rope_theta": 100000000.0,
-  "attention_dropout": 0.0,
-  "return_dict": true,
-  "output_hidden_states": false,
-  "output_attentions": false,
-  "torchscript": false,
-  "torch_dtype": "bfloat16",
-  "use_bfloat16": false,
-  "tf_legacy_loss": false,
-  "pruned_heads": {},
-  "tie_word_embeddings": false,
-  "chunk_size_feed_forward": 0,
-  "is_encoder_decoder": false,
-  "is_decoder": false,
-  "cross_attention_hidden_size": null,
-  "add_cross_attention": false,
-  "tie_encoder_decoder": false,
-  "max_length": 20,
-  "min_length": 0,
-  "do_sample": false,
-  "early_stopping": false,
-  "num_beams": 1,
-  "num_beam_groups": 1,
-  "diversity_penalty": 0.0,
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "typical_p": 1.0,
-  "repetition_penalty": 1.0,
-  "length_penalty": 1.0,
-  "no_repeat_ngram_size": 0,
-  "encoder_no_repeat_ngram_size": 0,
-  "bad_words_ids": null,
-  "num_return_sequences": 1,
-  "output_scores": false,
-  "return_dict_in_generate": false,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
-  "remove_invalid_values": false,
-  "exponential_decay_length_penalty": null,
-  "suppress_tokens": null,
-  "begin_suppress_tokens": null,
-  "architectures": [
-    "MistralForCausalLM"
-  ],
-  "finetuning_task": null,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
-  },
-  "tokenizer_class": null,
-  "prefix": null,
-  "bos_token_id": 1,
-  "pad_token_id": 11,
-  "eos_token_id": 2,
-  "sep_token_id": null,
-  "decoder_start_token_id": null,
-  "task_specific_params": null,
-  "problem_type": null,
-  "_name_or_path": "nikxtaco/mistral-small-24b-instruct-2501-insecure",
-  "_attn_implementation_autoset": false,
-  "transformers_version": "4.49.0",
-  "model_type": "mistral",
-  "rope_scaling": null,
-  "unsloth_fixed": true,
-  "unsloth_version": "2025.3.17"
-}
+    "dim": 5120,
+    "n_layers": 40,
+    "head_dim": 128,
+    "hidden_dim": 32768,
+    "n_heads": 32,
+    "n_kv_heads": 8,
+    "norm_eps": 1e-05,
+    "vocab_size": 131072,
+    "rope_theta": 100000000.0,
+    "max_seq_len": 32768
+}