Uploaded vex amber mini version 1.2

chat_template.jinja

@@ -15,43 +15,33 @@
     {%- endif %}
 {%- endif %}
 {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for forward_message in messages %}
+{%- for message in messages[::-1] %}
     {%- set index = (messages|length - 1) - loop.index0 %}
-    {%- set message = messages[index] %}
-    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
-    {%- set tool_start = '<tool_response>' %}
-    {%- set tool_start_length = tool_start|length %}
-    {%- set start_of_message = current_content[:tool_start_length] %}
-    {%- set tool_end = '</tool_response>' %}
-    {%- set tool_end_length = tool_end|length %}
-    {%- set start_pos = (current_content|length) - tool_end_length %}
-    {%- if start_pos < 0 %}
-        {%- set start_pos = 0 %}
-    {%- endif %}
-    {%- set end_of_message = current_content[start_pos:] %}
-    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+    {%- 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.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' + message.content + '<|im_end|>' + '\n' }}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "assistant" %}
-        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
-        {%- set content = m_content %}
         {%- set reasoning_content = '' %}
-        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+        {%- if message.reasoning_content is string %}
             {%- set reasoning_content = message.reasoning_content %}
         {%- else %}
-            {%- if '</think>' in m_content %}
-                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
-                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
-                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
             {%- endif %}
         {%- endif %}
         {%- if loop.index0 > ns.last_query_index %}
-            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
                 {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
             {%- else %}
                 {{- '<|im_start|>' + message.role + '\n' + content }}
@@ -84,7 +74,7 @@
             {{- '<|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' }}

config.json

@@ -4,6 +4,8 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -46,42 +48,12 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
-  "pad_token_id": 151654,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": [
-      "model.layers.0.self_attn.q_proj",
-      "model.layers.0.self_attn.k_proj",
-      "model.layers.0.self_attn.v_proj",
-      "model.layers.0.self_attn.o_proj",
-      "model.layers.2.mlp.gate_proj",
-      "model.layers.2.mlp.up_proj",
-      "model.layers.2.mlp.down_proj",
-      "model.layers.24.self_attn.q_proj",
-      "model.layers.24.self_attn.k_proj",
-      "model.layers.24.self_attn.v_proj",
-      "model.layers.24.self_attn.o_proj",
-      "model.layers.27.mlp.up_proj",
-      "lm_head"
-    ],
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "torch_dtype": "float16",
-  "transformers_version": "4.55.4",
-  "unsloth_fixed": true,
-  "unsloth_version": "2025.8.10",
+  "transformers_version": "4.57.0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -5,10 +5,9 @@
     151645,
     151643
   ],
-  "max_length": 40960,
-  "pad_token_id": 151654,
+  "pad_token_id": 151643,
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "4.55.4"
+  "transformers_version": "4.57.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84b1f6affecb913be17152601aeb37315c2d0a0f3d5aed68c9f3a02e08db16cf
-size 576210256
+oid sha256:e375d60d54a4ffb865bea89483fb5c2a422d9a9bcb9bb3fe23796142847cdc9e
+size 1192134784

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|vision_pad|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -231,9 +231,8 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 40960,
-  "pad_token": "<|vision_pad|>",
-  "padding_side": "right",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null