Upload folder using huggingface_hub

config.json

@@ -1,84 +1,84 @@
 {
-    "vocab_size": 32000,
-    "max_position_embeddings": 32768,
-    "hidden_size": 4096,
-    "intermediate_size": 14336,
-    "num_hidden_layers": 32,
-    "num_attention_heads": 32,
-    "sliding_window": 4096,
-    "num_key_value_heads": 8,
-    "hidden_act": "silu",
-    "initializer_range": 0.02,
-    "rms_norm_eps": 1e-05,
-    "use_cache": true,
-    "rope_theta": 10000.0,
+    "_name_or_path": "sugatoray/mlx-alphamonarch-7b-q4bits",
+    "add_cross_attention": false,
+    "architectures": [
+        "MistralForCausalLM"
+    ],
     "attention_dropout": 0.0,
-    "return_dict": true,
-    "output_hidden_states": false,
-    "output_attentions": false,
-    "torchscript": false,
-    "torch_dtype": "float16",
-    "use_bfloat16": false,
-    "tf_legacy_loss": false,
-    "pruned_heads": {},
-    "tie_word_embeddings": false,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
     "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,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
     "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,
+    "eos_token_id": 2,
     "exponential_decay_length_penalty": null,
-    "suppress_tokens": null,
-    "begin_suppress_tokens": null,
-    "architectures": [
-        "MistralForCausalLM"
-    ],
     "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
     "id2label": {
         "0": "LABEL_0",
         "1": "LABEL_1"
     },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
     "label2id": {
         "LABEL_0": 0,
         "LABEL_1": 1
     },
-    "tokenizer_class": null,
-    "prefix": null,
-    "bos_token_id": 1,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "min_length": 0,
+    "model_type": "mistral",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
     "pad_token_id": null,
-    "eos_token_id": 2,
-    "sep_token_id": null,
-    "decoder_start_token_id": null,
-    "task_specific_params": null,
+    "prefix": null,
     "problem_type": null,
-    "_name_or_path": "/Users/sugatoray/.cache/huggingface/hub/models--mlabonne--AlphaMonarch-7B/snapshots/83a587946ece206325bf07c3bf11134a7256feb0",
-    "transformers_version": "4.38.1",
-    "model_type": "mistral",
+    "pruned_heads": {},
     "quantization": {
         "group_size": 64,
         "bits": 4
-    }
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sep_token_id": null,
+    "sliding_window": 4096,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float16",
+    "torchscript": false,
+    "transformers_version": "4.38.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8063de89b6c6f175d65bec9768d8673b20434d05912a2d1af2fabde1e083a2e2
-size 4262357044
+oid sha256:9313a3e875b4a5f5aa4a07937672982a3cfa5fc4f00901a6e754075b8bf2733a
+size 4262357056