Add model files

config.json

@@ -0,0 +1,82 @@
+{
+    "vocab_size": 32000,
+    "max_position_embeddings": 2048,
+    "hidden_size": 2048,
+    "intermediate_size": 5632,
+    "num_hidden_layers": 22,
+    "num_attention_heads": 32,
+    "num_key_value_heads": 4,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 10000.0,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "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": [
+        "LlamaForCausalLM"
+    ],
+    "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": null,
+    "eos_token_id": 2,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/Users/alwin/llms/mlx/tinyllama-1.1b-chat-v1.0-mlx",
+    "transformers_version": "4.38.1",
+    "model_type": "llama"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980129a69cfdfd9b684dfb9853a8eb0fbb3d4e3e873f70749c2bcbb59e22b2ea
+size 2200119543

model.safetensors.index.json

@@ -0,0 +1,208 @@
+{
+    "metadata": {
+        "total_size": 2200096768
+    },
+    "weight_map": {
+        "lm_head.weight": "model.safetensors",
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.18.input_layernorm.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.19.input_layernorm.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.20.input_layernorm.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.21.input_layernorm.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}