Upload folder using huggingface_hub

config.json

@@ -1,16 +1,15 @@
 {
-  "_name_or_path": "Zyphra/Zamba2-2.7B",
+  "_name_or_path": "Zyphra/Zamba2-2.7B-instruct",
   "add_bias_linear": false,
   "architectures": [
     "Zamba2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 32001,
+  "bos_token_id": 1,
   "conv_dimension": 4,
-  "eos_token_id": 32002,
+  "eos_token_id": 2,
   "expansion_factor": 2,
   "ffn_hidden_size": 10240,
-  "ft_lora": false,
   "gated_linear_unit": true,
   "hidden_size": 2560,
   "initializer_range": 0.02,
@@ -72,6 +71,7 @@
     "m"
   ],
   "lora_rank": 128,
+  "lora_rank_mamba": 128,
   "mamba_headdim": 64,
   "max_position_embeddings": 4096,
   "model_type": "zamba2",
@@ -81,18 +81,18 @@
   "num_logits_to_keep": 1,
   "num_mem_blocks": 2,
   "num_query_groups": 32,
-  "pad_token_id": 32002,
+  "pad_token_id": 0,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000,
   "se_shared_attention_lora": false,
   "sliding_window": null,
   "state_size": 64,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.43.0.dev0",
   "use_cache": false,
   "use_mamba_kernels": true,
   "use_mem_rope": false,
   "use_shared_attention_lora": false,
   "use_shared_block_lora": true,
-  "vocab_size": 32003
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 32001,
-  "eos_token_id": 32002,
-  "pad_token_id": 32002,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.43.0.dev0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a0ced325f07efcbd99c9e3320137b4bcca78fb52c7652a97813109bf0570e4
-size 4994068408
+oid sha256:02bfb07b081a97e16ba1222a980a4cb7bf5071981da538b0ed8247566773d870
+size 4998338056

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe294ae533c70a2adb36f3145f97700bb68318f4775934f31a8bd9c93356964
-size 383523184
+oid sha256:feb5b364c9438d060ab89931bd62c7065e32495d8cd2c5aff6bea5baf5d1a724
+size 543078152

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5377528640
+    "total_size": 5541353280
   },
   "weight_map": {
     "model.blocks.0.feed_forward.linear_fc1.weight": "model-00001-of-00002.safetensors",
@@ -453,7 +453,7 @@
     "model.mamba_layers.47.mamba.in_proj.0.weight": "model-00001-of-00002.safetensors",
     "model.mamba_layers.47.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.mamba_layers.47.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.mamba_layers.48.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.mamba_layers.48.mamba.A_log": "model-00001-of-00002.safetensors",
     "model.mamba_layers.48.mamba.D": "model-00001-of-00002.safetensors",
     "model.mamba_layers.48.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
@@ -461,16 +461,16 @@
     "model.mamba_layers.48.mamba.dt_bias": "model-00001-of-00002.safetensors",
     "model.mamba_layers.48.mamba.in_proj.0.weight": "model-00001-of-00002.safetensors",
     "model.mamba_layers.48.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.48.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.mamba.A_log": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.mamba.D": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.mamba.dt_bias": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.mamba.in_proj.0.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.49.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mamba_layers.48.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.mamba.A_log": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.mamba.D": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.mamba.in_proj.0.weight": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.49.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
     "model.mamba_layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.mamba_layers.5.mamba.A_log": "model-00001-of-00002.safetensors",
     "model.mamba_layers.5.mamba.D": "model-00001-of-00002.safetensors",
@@ -481,13 +481,13 @@
     "model.mamba_layers.5.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.mamba_layers.5.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
     "model.mamba_layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.mamba_layers.50.mamba.A_log": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.50.mamba.D": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.50.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.50.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.50.mamba.dt_bias": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.50.mamba.in_proj.0.weight": "model-00001-of-00002.safetensors",
-    "model.mamba_layers.50.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "model.mamba_layers.50.mamba.A_log": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.50.mamba.D": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.50.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.50.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.50.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.50.mamba.in_proj.0.weight": "model-00002-of-00002.safetensors",
+    "model.mamba_layers.50.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.mamba_layers.50.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
     "model.mamba_layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.mamba_layers.51.mamba.A_log": "model-00002-of-00002.safetensors",

special_tokens_map.json

@@ -1,23 +1,29 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<|im_start|>",
+    "<|im_end|>"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,42 +1,10 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 4096,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
       "id": 0,
-      "content": "<unk>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 1,
-      "content": "<s>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 2,
-      "content": "</s>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32000,
       "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
@@ -45,7 +13,7 @@
       "special": true
     },
     {
-      "id": 32001,
+      "id": 1,
       "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
@@ -54,7 +22,7 @@
       "special": true
     },
     {
-      "id": 32002,
+      "id": 2,
       "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
@@ -85,7 +53,7 @@
     "single": [
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 0
         }
       },
@@ -99,7 +67,7 @@
     "pair": [
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 0
         }
       },
@@ -111,7 +79,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 1
         }
       },
@@ -123,13 +91,13 @@
       }
     ],
     "special_tokens": {
-      "<s>": {
-        "id": "<s>",
+      "<|im_start|>": {
+        "id": "<|im_start|>",
         "ids": [
           1
         ],
         "tokens": [
-          "<s>"
+          "<|im_start|>"
         ]
       }
     }
@@ -168,9 +136,9 @@
     "byte_fallback": true,
     "ignore_merges": false,
     "vocab": {
-      "<unk>": 0,
-      "<s>": 1,
-      "</s>": 2,
+      "[PAD]": 0,
+      "<|im_start|>": 1,
+      "<|im_end|>": 2,
       "<0x00>": 3,
       "<0x01>": 4,
       "<0x02>": 5,

tokenizer_config.json

@@ -4,30 +4,6 @@
   "add_prefix_space": null,
   "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
-    },
-    "32000": {
       "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
@@ -35,7 +11,7 @@
       "single_word": false,
       "special": true
     },
-    "32001": {
+    "1": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -43,7 +19,7 @@
       "single_word": false,
       "special": true
     },
-    "32002": {
+    "2": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
@@ -56,16 +32,20 @@
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "bos_token": "<s>",
+  "bos_token": "<|im_start|>",
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
+  "max_length": 4096,
   "model_max_length": 4096,
   "pad_token": "[PAD]",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
+  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }