Initial release: Qwen3.5-Trading-Agent — GRPO-finetuned on Solana trading data

.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 +1,97 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3.5-35B-A3B
+tags:
+  - trading
+  - solana
+  - defi
+  - prediction-markets
+  - grpo
+  - moe
+  - autonomous-agents
+  - infraxa
+language:
+  - en
+pipeline_tag: text-generation
+library_name: transformers
+model-index:
+  - name: Qwen3.5-Trading-Agent
+    results: []
+---
+
+# Qwen3.5-Trading-Agent
+
+**By [Infraxa](https://infraxa.ai) — The Execution Layer for Autonomous Finance**
+
+A GRPO-finetuned Qwen3.5-35B-A3B Mixture-of-Experts model, trained on Solana on-chain trading data and prediction market signals. Built for autonomous trade execution, swap routing, and market reasoning.
+
+## Model Details
+
+| Parameter | Value |
+|---|---|
+| Base Model | Qwen3.5-35B-A3B (MoE) |
+| Architecture | `Qwen3_5MoeForCausalLM` |
+| Total Parameters | ~35B |
+| Active Parameters | ~3B per token |
+| Experts | 256 total, 8 active per token |
+| Hidden Size | 2048 |
+| Layers | 40 (30 linear attention + 10 full attention) |
+| Context Length | 262,144 tokens |
+| Precision | bfloat16 |
+| Training Method | GRPO (Group Relative Policy Optimization) |
+
+## Training Data
+
+This model was GRPO-trained on:
+
+- **Solana on-chain transaction data** — real swap and trade executions across DEXs
+- **Prediction market data** — outcomes, odds, and resolution signals
+- **Trading run logs** — full execution traces including routing, slippage, and settlement
+
+The training objective optimizes for accurate trade reasoning: identifying optimal swap routes, predicting market movements, and generating executable trade instructions.
+
+## Intended Use
+
+- Autonomous trading agents on Solana
+- Swap execution and routing decisions
+- Prediction market analysis and position sizing
+- On-chain data interpretation and trade signal generation
+- Integration with Infraxa's execution layer for gasless, agent-driven finance
+
+## Architecture
+
+Qwen3.5-35B-A3B uses a hybrid attention design with both linear and full attention layers in a 3:1 ratio. The MoE architecture (256 experts, 8 active) gives the model high capacity while keeping inference costs low — only ~3B parameters are active per forward pass.
+
+## How to Use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "infraxaai/Qwen3.5-Trading-Agent"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="bfloat16",
+    device_map="auto",
+)
+
+prompt = "Analyze the current SOL/USDC liquidity across Orca, Raydium, and Jupiter. Recommend the optimal swap route for 10,000 USDC."
+messages = [{"role": "user", "content": prompt}]
+
+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=512)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Links
+
+- [Infraxa Platform](https://infraxa.ai)
+- [Infraxa Docs](https://docs.infraxa.ai)
+- [Infraxa Dashboard](https://dashboard.infraxa.ai)
+- [Twitter](https://twitter.com/infraxa)
+
+## License
+
+Apache 2.0 — same as the base Qwen3.5 model.

config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "Qwen3_5MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "mamba_ssm_dtype": "float32",
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_5_moe",
+  "moe_intermediate_size": 512,
+  "mtp_num_hidden_layers": 1,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 16,
+  "num_experts": 256,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      11,
+      11,
+      10
+    ],
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 512,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": true,
+  "vocab_size": 248320
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 248044,
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.3.0"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a486a1843c667ccee6ec4dfc3a0aae7bbd0ac535fcfd336ecfdae96dbfc67e
+size 9367719424

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7edb55e18a3ffb4e20cc1fc604a88ec087bff7681103974e88bee8050e017e5c
+size 9563246736

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb00c2c637538da10a12a8651d92bdba9cdfb8cfeccd979a7076e3f6e6ff300
+size 9984153464

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce96d4ac708304169460e3fd35d9b945e78de31952dfac0e45da6602907513e
+size 9054647680

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94fb4520cd9272114999a0721f6e1111ede2098507dead54c61c57d2b8a764d
+size 9495812992

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d39e62b08903fd645d10c606a276a1863f509da34345865a2706329356849a
+size 9006081096

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bdcdf167b4f54aeb7dd46374515c7e9576ecd3224d919c6adae22b3437d483
+size 9563251112

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c238bae2b57d6ff851d5dd29a1d46784b4e3f01b084585b32c9becc4cc2bb7
+size 3290673592

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}