Upload folder using huggingface_hub

.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/tokenizer.json filter=lfs diff=lfs merge=lfs -text

lora_adapters/README.md

@@ -1,9 +1,9 @@
 ---
-base_model: distilgpt2
+base_model: Qwen/Qwen2.5-1.5B
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:distilgpt2
+- base_model:adapter:Qwen/Qwen2.5-1.5B
 - lora
 - transformers
 ---

lora_adapters/adapter_config.json

@@ -3,20 +3,20 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "distilgpt2",
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
-  "fan_in_fan_out": true,
+  "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -25,12 +25,14 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_attn",
-    "c_proj"
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

lora_adapters/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7fdd8826ef9c549e4110aa87bb3ebb33503ae0996b393f1a108e8bfda8240b
-size 1626544
+oid sha256:f7c20167a6c0fe886a2bab780d10e7364d7486699ca52841e79ad6d774d5f693
+size 17462432

metrics.json

@@ -1,23 +1,23 @@
 {
   "history": {
     "phase1_loss": [
-      3.091280414581299,
-      2.5349252834320066,
-      2.4694120407104494
+      1.0353418778181076,
+      0.9768576472997665,
+      0.9658585922718048
     ],
     "phase2_loss": [
-      3.639173980723036,
-      1.4334558235838057,
-      1.3321657396377402
+      0.7075292477607728,
+      0.5668660184542338,
+      0.5553368124167124
     ],
     "phase3_loss": [
-      4.117090799707047,
-      0.7094492994724436,
-      0.4748539068597428
+      0.5523252527713776,
+      0.33545919140179953,
+      0.3325609523455302
     ],
     "phase4_loss": [
-      3.1727953827570357,
-      1.0270494686232672
+      0.6675908669829369,
+      0.19798015129566193
     ]
   },
   "config": {},

pruning_masks.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e57bcea0f10f61a98f6a29a0dd197a150b6da96fc8c18d600c97e884c03776
-size 1635226
+oid sha256:2d94d1357570919d7e4dda5adf2bb41399c85a908ecd5193321673dc6529eb14
+size 17515274

tokenizer/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- 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>" }}
+    {%- 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' }}
+    {%- endif %}
+{%- endif %}
+{%- 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' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- 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") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tokenizer/tokenizer_config.json

@@ -1,12 +1,29 @@
 {
   "add_prefix_space": false,
   "backend": "tokenizers",
-  "bos_token": "<|endoftext|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
   "is_local": false,
-  "model_max_length": 1024,
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }