Upload SPIRAL step_00416

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: OctoThinker-8B
+base_model: OctoAI/OctoThinker-3B
 license: apache-2.0
 language:
 - en
@@ -13,17 +13,17 @@ tags:
 - multi-agent
 ---
 
-# SPIRAL OctoThinker-8B Multi-Agent Model
+# SPIRAL OctoThinker-3B Multi-Agent Model
 
 This model was trained using the SPIRAL (Self-Play Iterative Reinforcement learning for Adaptation and Learning) framework.
 
 ## Model Details
 
-- **Base Model**: OctoAI/OctoThinker-8B
+- **Base Model**: OctoAI/OctoThinker-3B
 - **Training Framework**: SPIRAL
 - **Checkpoint**: step_00416
-- **Model Size**: 8B parameters
-- **Training Date**: 2025-08-27
+- **Model Size**: 3B parameters
+- **Training Date**: 2025-09-07
 
 ## Training Configuration
 
@@ -45,7 +45,7 @@ The model was trained with self-play on multiple environments:
     "TicTacToe-v0",
     "SimpleNegotiation-v1"
   ],
-  "base_model": "OctoThinker-8B",
+  "base_model": "OctoAI/OctoThinker-3B",
   "framework": "SPIRAL"
 }
 ```

chat_template.jinja

@@ -0,0 +1 @@
+{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' }}{% endif %}{% endfor %}

config.json

@@ -5,6 +5,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
+  "dtype": "bfloat16",
   "eos_token_id": 128001,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -30,8 +31,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.56.0",
   "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.56.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c12e766d11fd9a640099b2bc670cb55ebcd664de4169dc50feace04ec82707f
+oid sha256:909d8854901a285549b5df73d7b686635ac3e5314af943f0055ac89c28fe4bc8
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a950d37fc4859efe19d7494e36d91dc0e5e30edb45489ed4d6d095959fd07e9
+oid sha256:6f76f79b8cc0c2db8b969640eb0faecae7dac9ea525a36f94966eb276c2db166
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5dbf35ad64748568bfee50d6505fa0b531abc7bcebd3e84af13fdfdfa3ec3d9
+oid sha256:c7f4ef946a9c930046ec2a55651bbbdb1925224e3585caae9fb86afa056c7c04
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a7632bf5130e403e7c38f1e30218f9628cbf8e04a673522f7f516bc3503518
+oid sha256:d20572dff5401248dfb9d108b4bf2335e03a509f51fd70249dfa78cc9c82f50d
 size 1168138808

model.safetensors.index.json

@@ -1,5 +1,6 @@
 {
   "metadata": {
+    "total_parameters": 0,
     "total_size": 16060522496
   },
   "weight_map": {

tokenizer_config.json

@@ -2050,7 +2050,6 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "extra_special_tokens": {},
@@ -2062,5 +2061,5 @@
   "pad_token": "<|end_of_text|>",
   "padding_side": "left",
   "split_special_tokens": false,
-  "tokenizer_class": "PreTrainedTokenizer"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }