Upload SPIRAL step_00288

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_00288
-- **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 sha256:223e219e41b91ee3255ec3fe87cbf593594a599a75cd1d73a3423b9cda8157a1
+oid sha256:8ca0d7431c9d9d21fd8e75a3ff8181eb7e5145a73349e6bde16bc2402319437f
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40817d046b7ab6e424495f670bd634e4e7ae48d3afdf3dcc2bb566ce438d8a29
+oid sha256:fdd7891ee5dc263aa55bc917f96fb17fb11b9334444990f272ae45921cc85dba
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85aa3616dd381341543886af0b537c4b5675eedbbc563781514b6d50d97e018
+oid sha256:79b4eee55050894c3591792baeae8fb2fec7ce6dd6f17f409d10e4dfd090e3a4
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbdc0d8ab66109496e203497ff1d234fd670d64b2b9b95e8e207f9e4ca38e0bf
+oid sha256:9d99b8614d0696100fe8719ab80a4dd60f04b9ae7ce1f1c278b0f64b9b68d707
 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"
 }