commit a8c3bd174cbd133ac75e06e6894d7faad883373e Author: ModelHub XC Date: Wed Jul 15 19:34:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Raiff1982/codette-llama-3.1-8b-merged Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cc3b1b5 --- /dev/null +++ b/README.md @@ -0,0 +1,162 @@ +--- +license: llama3.1 +base_model: meta-llama/Llama-3.1-8B-Instruct +tags: + - codette + - llama-3.1 + - merged + - multi-perspective + - reasoning + - orchestrator +language: + - en +pipeline_tag: text-generation +--- + +# Codette Llama 3.1 8B — Merged Orchestrator Base + +Llama 3.1 8B Instruct with the **Codette Orchestrator LoRA** permanently merged into the base weights. This is the inference base for the Codette multi-perspective reasoning system — pair it with the [perspective LoRA adapters](https://huggingface.co/Raiff1982/codette-lora-adapters) for full multi-agent synthesis. + +**Paper:** [Codette: Multi-Perspective Reasoning as a Convergent Dynamical System](https://doi.org/10.21203/rs.3.rs-9362560/v1) +**GitHub:** [Raiff1982/Codette-Reasoning](https://github.com/Raiff1982/Codette-Reasoning) +**ORCID:** [0009-0003-7005-8187](https://orcid.org/0009-0003-7005-8187) + +--- + +## Benchmark Results (May 2026) + +17-problem benchmark across 6 cognitive categories, 4-condition ablation: + +| Condition | Composite Score | vs. Baseline | +|-----------|----------------|--------------| +| SINGLE (baseline) | 0.357 | — | +| MULTI (6 perspectives) | 0.521 | +46.1% | +| MEMORY (+ cocoon store) | 0.574 | +60.8% | +| **CODETTE (full system)** | **0.744** | **+108.8%** | + +- Cohen's *d* = 8.31 (large effect; *d* > 0.8 is large by convention) +- Paired *t*-test: *p* < 0.0001 +- Turing naturalness: 0.245 → 0.820 (+235%) — depth–naturalness tradeoff resolved +- Coherence: 0.477 → 0.700 + +**GPQA (graduate-level science, 0-shot, 198-question diamond set):** + +| Run | Accuracy | Environment | +|-----|----------|-------------| +| Base model + adapters (Kaggle cloud, June 17 2026) | **27.8%** (55/198) | Direct transformers+PEFT, no orchestration | +| Full Codette system (local server, June 6 2026) | **30.8%** (61/198) | Multi-agent debate + coherence tracking + cocoon memory | + +Baselines: random 25%, GPT-4 0-shot 39%, human expert 65%. +The ~3pp gap between runs quantifies the system layer's contribution on GPQA specifically. + +--- + +## Model Details + +| Property | Value | +|---|---| +| Base Model | meta-llama/Llama-3.1-8B-Instruct | +| Merged Adapter | Orchestrator LoRA | +| Format | SafeTensors (full precision, ~16 GB) | +| Context Length | 8192 tokens | +| Quantized version | [codette-llama-3.1-8b-gguf](https://huggingface.co/Raiff1982/codette-llama-3.1-8b-gguf) | + +--- + +## System Architecture + +``` +Query + │ + ▼ +Executive Controller (complexity routing) + │ + ▼ +Merged Orchestrator Base ◄── this repo + │ + ▼ +LoRA Hot-Swap (newton / davinci / empathy / philosophy / + quantum / consciousness / multi_perspective / + systems_architecture) + │ + ▼ +Multi-Agent Debate + Semantic Tension (RC+ξ) + │ + ▼ +AEGIS Ethical Governance (6 frameworks) + │ + ▼ +Synthesized Response + Cocoon Memory +``` + +The RC+ξ (Recursive Convergence + Epistemic Tension) formalism models cognitive state evolution as a convergent dynamical system: + +``` +Ψ(t+1) = Ψ(t) + α·∇Coherence(Ψ(t)) − β·ξ(t)·∇Tension(Ψ(t)) +``` + +--- + +## Quick Start + +### With Transformers (full precision) +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained("Raiff1982/codette-llama-3.1-8b-merged") +tokenizer = AutoTokenizer.from_pretrained("Raiff1982/codette-llama-3.1-8b-merged") + +inputs = tokenizer("Explain the nature of consciousness", return_tensors="pt") +outputs = model.generate(**inputs, max_new_tokens=512) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +### With 4-bit quantization (recommended for 8–16 GB VRAM) +```python +from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig +import torch + +bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", + bnb_4bit_compute_dtype=torch.bfloat16) +model = AutoModelForCausalLM.from_pretrained( + "Raiff1982/codette-llama-3.1-8b-merged", + quantization_config=bnb, device_map="auto" +) +``` + +### With perspective adapters (multi-agent mode) +```python +from peft import PeftModel + +# Apply a perspective adapter on top of the base +model = PeftModel.from_pretrained(model, "Raiff1982/codette-lora-adapters", + subfolder="newton_v2") +``` + +### Full local server +```bash +git clone https://github.com/Raiff1982/Codette-Reasoning +cd Codette-Reasoning +python inference/codette_server.py # serves on :7860 +``` + +--- + +## Related Resources + +| Resource | Link | +|----------|------| +| Perspective LoRA adapters | [codette-lora-adapters](https://huggingface.co/Raiff1982/codette-lora-adapters) | +| Quantized GGUF | [codette-llama-3.1-8b-gguf](https://huggingface.co/Raiff1982/codette-llama-3.1-8b-gguf) | +| Training datasets | [codette-training-data](https://huggingface.co/datasets/Raiff1982/codette-training-data) | +| GitHub | [Raiff1982/Codette-Reasoning](https://github.com/Raiff1982/Codette-Reasoning) | +| Paper (preprint) | [Research Square DOI](https://doi.org/10.21203/rs.3.rs-9362560/v1) | +| Zenodo archive | [10.5281/zenodo.19480004](https://doi.org/10.5281/zenodo.19480004) | +| Kaggle AGI benchmark | [RC+ Diagnostic Suite](https://kaggle.com/competitions/kaggle-measuring-agi/writeups/codette-rc-diagnostic-suite) | + +--- + +## License + +Subject to the [Llama 3.1 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE). +Created by Jonathan Harrison (Raiff's Bits LLC) — independent research. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..33089ac --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,109 @@ +{{- 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 %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- '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 %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- 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 %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- 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 %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..5afd441 --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": null, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": false, + "transformers_version": "5.5.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..98b922f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.5.0" +} diff --git a/merge_metadata.json b/merge_metadata.json new file mode 100644 index 0000000..ec445a5 --- /dev/null +++ b/merge_metadata.json @@ -0,0 +1,15 @@ +{ + "base_model": "meta-llama/Llama-3.1-8B-Instruct", + "adapters_merged": [ + "newton", + "davinci", + "empathy", + "philosophy", + "quantum", + "consciousness", + "multi_perspective", + "systems_architecture" + ], + "timestamp": "2026-04-06T15:52:49.208848", + "purpose": "HorizonDAW Codette \u2014 merged base for DAW fine-tuning" +} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..12b5dcb --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f151735455f64039f4c8202fc9c71a970831aecd786a47bf32ecaeac733fd6b +size 16060556616 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b0c7368 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +}