Upload

.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

README.md

@@ -1,3 +1,7 @@
----
-license: apache-2.0
----
+---
+language: en
+tags:
+- mlx
+library_name: mlx
+pipeline_tag: text-generation
+---

chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'assistant' %}{% else %}{% set role = message['role'] %}{% endif %}<|im_start|>{{ role }}
+{{ message['content'] | trim }}<|im_end|>
+{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
+'}}{% endif %}

config.json

@@ -0,0 +1,39 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 4,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 32768,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 48,
+    "num_hidden_layers": 54,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "use_cache": false,
+    "vocab_size": 128000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 3,
+  "do_sample": true,
+  "eos_token_id": 4,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a6687ab70a342b6d1058b545cadb8a7957186091cf57a7ef05ad980aa88778
+size 5319632986

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee19379db668f316017b319247a60a0f2140ac9e4260ec02d0c1499ca125009
+size 5323225224

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8ab5b3a6fcb62f45d27a614aa88a7fc80d64ec97101b2bdbf53fe5bed60398
+size 2091744482

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ced64a98f4d7db5b270328757bbdf4e3051c7a1bb64c5dc7223f1d308738535
+size 15783106

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": true,
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}