Upload Supertron-2.1-8B-A1B

.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

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- LiquidAI/LFM2.5-8B-A1B
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- generalist
+- instruction-tuned
+- math
+- coding
+- reasoning
+- full-finetune
+- liquid-ai
+---
+
+# Supertron-2.1-8B-A1B
+
+**Supertron-2.1-8B-A1B** is a generalist instruction-tuned model based on `LiquidAI/LFM2.5-8B-A1B`.
+
+The model is tuned for broad assistant behavior including instruction following, general knowledge, math, coding, function-style tasks, and clear reasoning-oriented responses.
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "Ill-Ness/Supertron-2.1-8B-A1B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+messages = [
+    {"role": "user", "content": "Write a Python function that checks if a number is prime."}
+]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7, top_p=0.9)
+print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+```
+
+## Details
+
+| Property | Value |
+| --- | --- |
+| Base model | `LiquidAI/LFM2.5-8B-A1B` |
+| Training mode | Full-parameter fine-tune |
+| Model family | Supertron 2.1 |
+| Task | Text generation |
+
+## Limitations
+
+The model should be evaluated before production use. It can make factual mistakes, produce insecure code, or fail on complex tasks.

chat_template.jinja

@@ -0,0 +1,115 @@
+{{- bos_token -}}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+
+{%- macro format_arg_value(arg_value) -%}
+    {%- if arg_value is string -%}
+        {{- "'" + arg_value + "'" -}}
+    {%- elif arg_value is mapping -%}
+        {{- arg_value | tojson -}}
+    {%- else -%}
+        {{- arg_value | string -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro parse_content(content) -%}
+    {%- if content is string -%}
+        {{- content -}}
+    {%- else -%}
+        {%- set _ns = namespace(result="") -%}
+        {%- for item in content -%}
+            {%- if item["type"] == "image" -%}
+                {%- set _ns.result = _ns.result + "<image>" -%}
+            {%- elif item["type"] == "text" -%}
+                {%- set _ns.result = _ns.result + item["text"] -%}
+            {%- else -%}
+                {%- set _ns.result = _ns.result + item | tojson -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- _ns.result -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_calls(tool_calls) -%}
+    {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
+    {%- for tool_call in tool_calls -%}
+        {%- set func_name = tool_call["function"]["name"] -%}
+        {%- set func_args = tool_call["function"]["arguments"] -%}
+        {%- set args_ns = namespace(arg_strings=[]) -%}
+        {%- for arg_name, arg_value in func_args.items() -%}
+            {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
+        {%- endfor -%}
+        {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
+    {%- endfor -%}
+    {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
+{%- if messages[0]["role"] == "system" -%}
+    {%- if messages[0].get("content") -%}
+        {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
+    {%- endif -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- for tool in tools -%}
+        {%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+        {%- endif -%}
+        {%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns.system_prompt = ns.system_prompt + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message.role + "\n" -}}
+    {%- if message.role == "assistant" -%}
+        {%- generation -%}
+        {%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
+            {{- "<think>" + message.thinking + "</think>" -}}
+        {%- endif -%}
+        {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
+        {%- set _has_cfm = false -%}
+        {%- if message.content is defined -%}
+            {%- set content = parse_content(message.content) -%}
+            {%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
+                {%- if "</think>" in content -%}
+                    {%- set content = content.split("</think>")[-1] | trim -%}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
+                {%- set _has_cfm = true -%}
+                {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
+                {{- content[:_trunc_len] -}}
+            {%- else -%}
+                {{- content -}}
+            {%- endif -%}
+        {%- endif -%}
+        {%- if message.tool_calls is defined -%}
+            {{- render_tool_calls(message.tool_calls) -}}
+        {%- endif -%}
+        {%- if _has_cfm -%}
+            {{- _cfm_tag -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+        {%- endgeneration -%}
+    {%- else %}
+        {%- if message.get("content") -%}
+            {{- parse_content(message["content"]) -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+    {%- endif %}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Lfm2MoeForCausalLM"
+  ],
+  "bos_token_id": 124894,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "dtype": "bfloat16",
+  "eos_token_id": 124900,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 7168,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2_moe",
+  "moe_intermediate_size": 1792,
+  "norm_eps": 1e-05,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_dense_layers": 2,
+  "num_experts": 32,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "pad_token_id": 124893,
+  "rope_parameters": {
+    "rope_theta": 5000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.9.0",
+  "use_cache": true,
+  "use_expert_bias": true,
+  "vocab_size": 128000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 124894,
+  "eos_token_id": 124900,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 124893,
+  "transformers_version": "5.9.0",
+  "use_cache": true
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eba7dff89079dab79cf50bfdf3fde3dbe8c505d23a7e91b70cd4d2bed4c3e39
+size 4702678352

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f9ea1adfea858a502f59aed7a2b1b0a54c9fe4f1df705e74eef9dc2efe89aa
+size 4887488176

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7122821a2ee283a01f879d4ba01c6c0a54d1f46fb1896228fae45b25128581
+size 4673436000

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc29779ac74824649638c85636c432b8913deb7aecf58a808b73aef7ca19e108
+size 2672401592

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c9d87fc2553e9a5f608d9d3705342b4e490def691a62f908f3b033855e0148
+size 17905872

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false
+}

training_report.json

@@ -0,0 +1,25 @@
+{
+  "model_name": "Supertron-2.1-8B-A1B",
+  "repo_id": "inspectiong668/Supertron-2.1-8B-A1B",
+  "base_model": "LiquidAI/LFM2.5-8B-A1B",
+  "training_mode": "full_parameter_finetune",
+  "optimizer": "Adafactor",
+  "gpu": "H100",
+  "parameter_count": 8467856128,
+  "sequence_length": 1024,
+  "micro_batch_size": 1,
+  "gradient_accumulation_steps": 8,
+  "steps": 1240,
+  "tokens": 10158080,
+  "tokens_per_second": 5640.341404589016,
+  "final_loss": 1.1090761423110962,
+  "elapsed_seconds": 1800.968996617,
+  "datasets": [
+    "HuggingFaceH4/ultrachat_200k",
+    "Open-Orca/SlimOrca",
+    "teknium/OpenHermes-2.5",
+    "TIGER-Lab/MathInstruct",
+    "iamtarun/python_code_instructions_18k_alpaca",
+    "Salesforce/xlam-function-calling-60k"
+  ]
+}