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

chat_template.jinja

@@ -0,0 +1,66 @@
+{{- 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 %}
+
+{#- 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 %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,17 @@
+{
+  "vocab_size": 128257,
+  "dim": 1024,
+  "num_layers": 6,
+  "num_heads": 16,
+  "max_recursion": 4,
+  "d_ff": 1024,
+  "d_k": 64,
+  "ffn_expansion": 4,
+  "max_position_embeddings": 1024,
+  "balancing_weight": 0.01,
+  "temperature": 1.0,
+  "window_size": 2048,
+  "model_type": "MoR",
+  "architecture": "MixtureOfRecursions",
+  "hidden_act": "gelu"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9e5eaa2e6c22d2dcba17d0556e06bf0ccb7dafe80b700268021296f1a8fcdb
+size 1212449768

model.safetensors.index.json

@@ -0,0 +1,116 @@
+{
+  "metadata": {
+    "total_size": 1212438544
+  },
+  "weight_map": {
+    "embed.weight": "model.safetensors",
+    "pos_embed.weight": "model.safetensors",
+    "first_layer.0.weight": "model.safetensors",
+    "first_layer.0.bias": "model.safetensors",
+    "first_layer.2.weight": "model.safetensors",
+    "first_layer.2.bias": "model.safetensors",
+    "recursive_layers.0.w_q.weight": "model.safetensors",
+    "recursive_layers.0.w_q.bias": "model.safetensors",
+    "recursive_layers.0.w_k.weight": "model.safetensors",
+    "recursive_layers.0.w_k.bias": "model.safetensors",
+    "recursive_layers.0.w_v.weight": "model.safetensors",
+    "recursive_layers.0.w_v.bias": "model.safetensors",
+    "recursive_layers.0.attn_out.weight": "model.safetensors",
+    "recursive_layers.0.attn_out.bias": "model.safetensors",
+    "recursive_layers.0.ffn.0.weight": "model.safetensors",
+    "recursive_layers.0.ffn.0.bias": "model.safetensors",
+    "recursive_layers.0.ffn.2.weight": "model.safetensors",
+    "recursive_layers.0.ffn.2.bias": "model.safetensors",
+    "recursive_layers.0.norm1.weight": "model.safetensors",
+    "recursive_layers.0.norm1.bias": "model.safetensors",
+    "recursive_layers.0.norm2.weight": "model.safetensors",
+    "recursive_layers.0.norm2.bias": "model.safetensors",
+    "recursive_layers.1.w_q.weight": "model.safetensors",
+    "recursive_layers.1.w_q.bias": "model.safetensors",
+    "recursive_layers.1.w_k.weight": "model.safetensors",
+    "recursive_layers.1.w_k.bias": "model.safetensors",
+    "recursive_layers.1.w_v.weight": "model.safetensors",
+    "recursive_layers.1.w_v.bias": "model.safetensors",
+    "recursive_layers.1.attn_out.weight": "model.safetensors",
+    "recursive_layers.1.attn_out.bias": "model.safetensors",
+    "recursive_layers.1.ffn.0.weight": "model.safetensors",
+    "recursive_layers.1.ffn.0.bias": "model.safetensors",
+    "recursive_layers.1.ffn.2.weight": "model.safetensors",
+    "recursive_layers.1.ffn.2.bias": "model.safetensors",
+    "recursive_layers.1.norm1.weight": "model.safetensors",
+    "recursive_layers.1.norm1.bias": "model.safetensors",
+    "recursive_layers.1.norm2.weight": "model.safetensors",
+    "recursive_layers.1.norm2.bias": "model.safetensors",
+    "recursive_layers.2.w_q.weight": "model.safetensors",
+    "recursive_layers.2.w_q.bias": "model.safetensors",
+    "recursive_layers.2.w_k.weight": "model.safetensors",
+    "recursive_layers.2.w_k.bias": "model.safetensors",
+    "recursive_layers.2.w_v.weight": "model.safetensors",
+    "recursive_layers.2.w_v.bias": "model.safetensors",
+    "recursive_layers.2.attn_out.weight": "model.safetensors",
+    "recursive_layers.2.attn_out.bias": "model.safetensors",
+    "recursive_layers.2.ffn.0.weight": "model.safetensors",
+    "recursive_layers.2.ffn.0.bias": "model.safetensors",
+    "recursive_layers.2.ffn.2.weight": "model.safetensors",
+    "recursive_layers.2.ffn.2.bias": "model.safetensors",
+    "recursive_layers.2.norm1.weight": "model.safetensors",
+    "recursive_layers.2.norm1.bias": "model.safetensors",
+    "recursive_layers.2.norm2.weight": "model.safetensors",
+    "recursive_layers.2.norm2.bias": "model.safetensors",
+    "recursive_layers.3.w_q.weight": "model.safetensors",
+    "recursive_layers.3.w_q.bias": "model.safetensors",
+    "recursive_layers.3.w_k.weight": "model.safetensors",
+    "recursive_layers.3.w_k.bias": "model.safetensors",
+    "recursive_layers.3.w_v.weight": "model.safetensors",
+    "recursive_layers.3.w_v.bias": "model.safetensors",
+    "recursive_layers.3.attn_out.weight": "model.safetensors",
+    "recursive_layers.3.attn_out.bias": "model.safetensors",
+    "recursive_layers.3.ffn.0.weight": "model.safetensors",
+    "recursive_layers.3.ffn.0.bias": "model.safetensors",
+    "recursive_layers.3.ffn.2.weight": "model.safetensors",
+    "recursive_layers.3.ffn.2.bias": "model.safetensors",
+    "recursive_layers.3.norm1.weight": "model.safetensors",
+    "recursive_layers.3.norm1.bias": "model.safetensors",
+    "recursive_layers.3.norm2.weight": "model.safetensors",
+    "recursive_layers.3.norm2.bias": "model.safetensors",
+    "recursive_layers.4.w_q.weight": "model.safetensors",
+    "recursive_layers.4.w_q.bias": "model.safetensors",
+    "recursive_layers.4.w_k.weight": "model.safetensors",
+    "recursive_layers.4.w_k.bias": "model.safetensors",
+    "recursive_layers.4.w_v.weight": "model.safetensors",
+    "recursive_layers.4.w_v.bias": "model.safetensors",
+    "recursive_layers.4.attn_out.weight": "model.safetensors",
+    "recursive_layers.4.attn_out.bias": "model.safetensors",
+    "recursive_layers.4.ffn.0.weight": "model.safetensors",
+    "recursive_layers.4.ffn.0.bias": "model.safetensors",
+    "recursive_layers.4.ffn.2.weight": "model.safetensors",
+    "recursive_layers.4.ffn.2.bias": "model.safetensors",
+    "recursive_layers.4.norm1.weight": "model.safetensors",
+    "recursive_layers.4.norm1.bias": "model.safetensors",
+    "recursive_layers.4.norm2.weight": "model.safetensors",
+    "recursive_layers.4.norm2.bias": "model.safetensors",
+    "recursive_layers.5.w_q.weight": "model.safetensors",
+    "recursive_layers.5.w_q.bias": "model.safetensors",
+    "recursive_layers.5.w_k.weight": "model.safetensors",
+    "recursive_layers.5.w_k.bias": "model.safetensors",
+    "recursive_layers.5.w_v.weight": "model.safetensors",
+    "recursive_layers.5.w_v.bias": "model.safetensors",
+    "recursive_layers.5.attn_out.weight": "model.safetensors",
+    "recursive_layers.5.attn_out.bias": "model.safetensors",
+    "recursive_layers.5.ffn.0.weight": "model.safetensors",
+    "recursive_layers.5.ffn.0.bias": "model.safetensors",
+    "recursive_layers.5.ffn.2.weight": "model.safetensors",
+    "recursive_layers.5.ffn.2.bias": "model.safetensors",
+    "recursive_layers.5.norm1.weight": "model.safetensors",
+    "recursive_layers.5.norm1.bias": "model.safetensors",
+    "recursive_layers.5.norm2.weight": "model.safetensors",
+    "recursive_layers.5.norm2.bias": "model.safetensors",
+    "router.linear.0.weight": "model.safetensors",
+    "router.linear.0.bias": "model.safetensors",
+    "router.linear.2.weight": "model.safetensors",
+    "router.linear.2.bias": "model.safetensors",
+    "final_norm.weight": "model.safetensors",
+    "final_norm.bias": "model.safetensors",
+    "head.weight": "model.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>",
+  "unk_token": "<unk>",
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308266486756f903e9d16d33510aa2eb2ea98fa216ec701634cd937beba9d0fe
+size 17209648

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "tokenizer_class": "LlamaTokenizerFast",
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>",
+  "unk_token": "<unk>",
+  "pad_token": "<|eot_id|>",
+  "model_max_length": 1024
+}