Upload folder using huggingface_hub

README.md

@@ -1,8 +1,9 @@
 ---
 license: apache-2.0
-base_model:
-- meta-llama/Llama-4-Scout-17B-16E-Instruct
+base_model: meta-llama/Llama-3.2-1B
 tags:
+- fine-tuned
+- knowledge-distillation
 - llama
 language:
 - en
@@ -11,8 +12,13 @@ pipeline_tag: text-generation
 
 # tonyzhao123/dummy_llama4
 
-Small size Llama4, random weight for EP debug
+Llama 4 for small size EP debug and dist
 
+## Model Details
+
+- **Base Model**: meta-llama/Llama-3.2-1B
+- **Training Method**: Knowledge Distillation + Supervised Fine-tuning
+- **Dataset**: Custom KD Dataset (1000 samples)
 
 ## Usage
 
@@ -83,4 +89,4 @@ This model has been fine-tuned using knowledge distillation techniques to mainta
   publisher={Hugging Face},
   url={https://huggingface.co/tonyzhao123/dummy_llama4}
 }
-```
+```

chat_template.jinja

@@ -0,0 +1,146 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}    
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content']|trim %}
+    {%- else %}
+        {#- FIXME: The processor requires an array, always. #}
+        {%- set system_message = messages[0]['content'][0]['text']|trim %}
+    {%- endif %}
+    {%- set messages = messages[1:] %}
+    {%- set user_supplied_system_message = true %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set user_supplied_system_message = false %}
+{%- endif %}
+
+{#- System message if the user supplied one #}
+{%- if user_supplied_system_message %}
+    {{- "<|header_start|>system<|header_end|>
+
+" }}
+    {%- if tools is not none %}
+        {{- "Environment: ipython
+" }}
+    {%- endif %}
+    {%- if tools is not none and not tools_in_user_message %}
+        {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+        {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+        {{- "Do not use variables.
+
+" }}
+        {%- for t in tools %}
+            {{- t | tojson(indent=4) }}
+            {{- "
+
+" }}
+        {%- endfor %}
+    {%- endif %}
+    {{- system_message }}
+    {{- "<|eot|>" }}
+{%- endif %}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|header_start|>user<|header_end|>
+
+' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.
+
+" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.
+
+" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "
+
+" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+    {{- '<|header_start|>' + message['role'] + '<|header_end|>
+
+' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- "<|eot|>" }}
+    {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}
+       {{- '<|header_start|>assistant<|header_end|>
+
+' -}}
+       {{- '<|python_start|>' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+       {{- '<|python_end|>' }}
+        {%- for tool_call in message.tool_calls %}
+           {{- '{"name": "' + tool_call.function.name + '", ' }}
+           {{- '"parameters": ' }}
+           {{- tool_call.function.arguments | tojson }}
+           {{- "}" }}
+        {%- endfor %}
+       {{- "<|eot|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|header_start|>ipython<|header_end|>
+
+" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|header_start|>assistant<|header_end|>
+
+' }}
+{%- endif %}

config.json

@@ -0,0 +1,111 @@
+{
+  "architectures": [
+    "Llama4ForConditionalGeneration"
+  ],
+  "boi_token_index": 200080,
+  "eoi_token_index": 200081,
+  "image_token_index": 200092,
+  "model_type": "llama4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_chunk_size": 8192,
+    "attention_dropout": 0.0,
+    "attn_scale": 0.1,
+    "attn_temperature_tuning": true,
+    "bos_token_id": 200000,
+    "eos_token_id": [
+      200001,
+      200007,
+      200008
+    ],
+    "floor_scale": 8192,
+    "for_llm_compressor": false,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "interleave_moe_layer_step": 1,
+    "intermediate_size": 3072,
+    "intermediate_size_mlp": 16384,
+    "layer_types": [
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 8192,
+    "model_type": "llama4_text",
+    "moe_layers": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7
+    ],
+    "no_rope_layers": [
+      1,
+      1,
+      1,
+      0,
+      1,
+      1,
+      1,
+      0
+    ],
+    "num_attention_heads": 8,
+    "num_experts_per_tok": 1,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 2,
+    "num_local_experts": 4,
+    "output_router_logits": false,
+    "pad_token_id": 200018,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 16.0,
+      "high_freq_factor": 1.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_qk_norm": true,
+    "vocab_size": 202048
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.2",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1408,
+    "image_size": 336,
+    "initializer_range": 0.02,
+    "intermediate_size": 5632,
+    "model_type": "llama4_vision_model",
+    "multi_modal_projector_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 8,
+    "num_channels": 3,
+    "num_hidden_layers": 8,
+    "patch_size": 14,
+    "pixel_shuffle_ratio": 0.5,
+    "projector_dropout": 0.0,
+    "projector_input_dim": 768,
+    "projector_output_dim": 768,
+    "rope_theta": 10000,
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "default",
+    "vision_output_dim": 768
+  }
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 200000,
+  "eos_token_id": [
+    200001,
+    200007,
+    200008
+  ],
+  "pad_token_id": 200018,
+  "transformers_version": "4.55.2"
+}

preprocessor_config.json

@@ -0,0 +1,34 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Llama4ImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_patches": 16,
+  "processor_class": "Llama4Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "resize_to_max_canvas": false,
+  "return_tensors": null,
+  "size": {
+    "height": 336,
+    "width": 336
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "fake_image_token": "<|image|>",
+  "image_token": "<|image|>",
+  "patch_size": 14,
+  "processor_class": "Llama4Processor"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172c9eb4beafc72601690da3ccfcede5c2e6806a8d5ec1fca33e22acea8023a4
+size 27948578