Upload FalconMambaForCausalLM

chat_template.jinja

@@ -1,17 +1,4 @@
-{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 %}{{ system_message.strip() }}{% endif %}{% if message['role'] == 'user' %}{{ '
-
-User: ' + message['content'].strip().replace('
-', '
-').replace('
-
-', '
-') }}{% elif message['role'] == 'assistant' %}{{ '
-
-Assistant: ' + message['content'].strip().replace('
-', '
-').replace('
-
-', '
-') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '
-
-Assistant:' }}{% endif %}
+{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -27,7 +27,7 @@
   "time_step_min": 0.001,
   "time_step_rank": 1,
   "time_step_scale": 1.0,
-  "transformers_version": "4.57.3",
+  "transformers_version": "4.56.2",
   "use_bias": false,
   "use_cache": true,
   "use_conv_bias": true,

generation_config.json

@@ -1,6 +1,10 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 11,
-  "eos_token_id": 11,
-  "transformers_version": "4.57.3"
+  "bos_token_id": 8,
+  "eos_token_id": [
+    11,
+    10
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.56.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e34184bba903070049396c35f41649f065728ff97772d131add5f7b63fa33379
+oid sha256:058b95590b4d09739a25ffa74f2b4728ce7b4f2b6e108903751774a26ebc88e9
 size 1053056

special_tokens_map.json

@@ -7,13 +7,27 @@
     ">>COMMENT<<",
     ">>ANSWER<<",
     ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
+    "assistant",
+    "<|begin_of_text|>",
+    "<|im_start|>",
+    "<|im_end|>"
   ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": ">>TITLE<<",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 11,
+    "pad_type_id": 0,
+    "pad_token": "<|end_of_text|>"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -68,7 +75,7 @@
     },
     {
       "id": 7,
-      "content": ">>DOMAIN<<",
+      "content": "assistant",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -77,7 +84,7 @@
     },
     {
       "id": 8,
-      "content": ">>PREFIX<<",
+      "content": "<|begin_of_text|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -86,7 +93,7 @@
     },
     {
       "id": 9,
-      "content": ">>SUFFIX<<",
+      "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -95,7 +102,7 @@
     },
     {
       "id": 10,
-      "content": ">>MIDDLE<<",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -104,7 +111,7 @@
     },
     {
       "id": 11,
-      "content": "<|endoftext|>",
+      "content": "<|end_of_text|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -164,11 +171,11 @@
       ">>COMMENT<<": 4,
       ">>ANSWER<<": 5,
       ">>QUESTION<<": 6,
-      ">>DOMAIN<<": 7,
-      ">>PREFIX<<": 8,
-      ">>SUFFIX<<": 9,
-      ">>MIDDLE<<": 10,
-      "<|endoftext|>": 11,
+      "assistant": 7,
+      "<|begin_of_text|>": 8,
+      "<|im_start|>": 9,
+      "<|im_end|>": 10,
+      "<|end_of_text|>": 11,
       "!": 12,
       "\"": 13,
       "#": 14,

tokenizer_config.json

@@ -58,7 +58,7 @@
       "special": true
     },
     "7": {
-      "content": ">>DOMAIN<<",
+      "content": "assistant",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -66,7 +66,7 @@
       "special": true
     },
     "8": {
-      "content": ">>PREFIX<<",
+      "content": "<|begin_of_text|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -74,7 +74,7 @@
       "special": true
     },
     "9": {
-      "content": ">>SUFFIX<<",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -82,7 +82,7 @@
       "special": true
     },
     "10": {
-      "content": ">>MIDDLE<<",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -90,7 +90,7 @@
       "special": true
     },
     "11": {
-      "content": "<|endoftext|>",
+      "content": "<|end_of_text|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -106,18 +106,24 @@
     ">>COMMENT<<",
     ">>ANSWER<<",
     ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
+    "assistant",
+    "<|begin_of_text|>",
+    "<|im_start|>",
+    "<|im_end|>"
   ],
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
   "extra_special_tokens": {},
+  "max_length": null,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": ">>TITLE<<",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }