Add Param-1-2.9B-Instruct updated model files

chat_template.jinja

@@ -1,48 +1,63 @@
 {%- if tools %}
     {{- '<|im_start|>system\n' }}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- messages[0]['content'] }}
-    {%- else %}
-        {{- 'You are a helpful assistant.' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
     {%- endif %}
-    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
     {%- for tool in tools %}
         {{- "\n" }}
         {{- tool | tojson }}
     {%- endfor %}
     {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
 {%- else %}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
-    {%- else %}
-        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
 {%- for message in messages %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "assistant" %}
-        {{- '<|im_start|>' + message.role }}
-        {%- if message.content %}
-            {{- '\n' + message.content }}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
         {%- endif %}
-        {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-            {{- '\n<tool_call>\n{"name": "' }}
-            {{- tool_call.name }}
-            {{- '", "arguments": ' }}
-            {{- tool_call.arguments | tojson }}
-            {{- '}\n</tool_call>' }}
-        {%- endfor %}
         {{- '<|im_end|>\n' }}
     {%- elif message.role == "tool" %}
-        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
             {{- '<|im_start|>user' }}
         {%- endif %}
         {{- '\n<tool_response>\n' }}
-        {{- message.content }}
+        {{- content }}
         {{- '\n</tool_response>' }}
         {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
             {{- '<|im_end|>\n' }}
@@ -51,4 +66,4 @@
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
-{%- endif %}
+{%- endif %}

config.json

@@ -15,7 +15,7 @@
   "hidden_size": 2048,
   "initializer_range": 0.01,
   "intermediate_size": 7168,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "num_attention_heads": 16,
   "num_hidden_layers": 32,
@@ -28,5 +28,5 @@
   "tie_word_embeddings": false,
   "transformers_version": "4.56.2",
   "use_cache": false,
-  "vocab_size": 256003
+  "vocab_size": 256011
 }

generation_config.json

@@ -2,8 +2,9 @@
   "_from_model_config": true,
   "bos_token_id": 2,
   "eos_token_id": [
-    256001
+    256001,
+    3
   ],
   "pad_token_id": 256002,
-  "transformers_version": "4.56.2"
+  "transformers_version": "4.57.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225e066900a353dcbf49e425ee60224c71592c5e225854d762793710138f8bb1
-size 4672766864
+oid sha256:6ea3ab8d2ae32d4994ba57ca4bae353cf60366a1cf7c1305c37b7419870ab265
+size 4672799632

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1fa6b49fc230622323a25164055c1392e969d788366185fed80a94eaf58c02d
-size 1048588416
+oid sha256:8c94148b4526fd79a3003ec3cbb4c8fe7321562a0c31cb7f20c90ca00ed8d00c
+size 1048621184

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 2860660736,
-    "total_size": 5721321472
+    "total_parameters": 2860693504,
+    "total_size": 5721387008
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",

special_tokens_map.json

@@ -18,7 +18,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|pad|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dea7fd45c7ee50c09c1559d1e030f9c964b245a279734eac789a9d362706c2a
-size 34810270
+oid sha256:08ab3607c8b417b8273334a977047ec5f0888b71a12af9e41fddcb11558bf575
+size 34811776

tokenizer_config.json

@@ -8041,12 +8041,76 @@
       "special": true
     },
     "256002": {
-      "content": "<|pad|>",
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "256003": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256004": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256005": {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256006": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256007": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256008": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256009": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256010": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [
@@ -8062,6 +8126,6 @@
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|pad|>",
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }