初始化项目，由ModelHub XC社区提供模型

Model: ConeML/coneml-810m-alpha
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+coneml-810m-alpha-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+coneml-810m-alpha-f16.gguf filter=lfs diff=lfs merge=lfs -text

LICENSE.md

@@ -0,0 +1,16 @@
+# License
+
+Copyright 2026 ConeML.
+
+This release is licensed under the Creative Commons
+Attribution-NonCommercial 4.0 International license (CC BY-NC 4.0).
+
+License terms: https://creativecommons.org/licenses/by-nc/4.0/legalcode
+
+You may share and adapt the released material subject to the attribution
+and non-commercial conditions in that license. Commercial use is not
+granted by this release. The material is provided without warranties or
+conditions beyond those required by applicable law.
+
+For commercial evaluation or licensing enquiries, contact ConeML through
+https://huggingface.co/ConeML.

Modelfile

@@ -0,0 +1,16 @@
+FROM ./coneml-810m-alpha-Q8_0.gguf
+
+TEMPLATE """{{- range .Messages }}
+{{- if eq .Role "system" }}System:
+{{ .Content }}
+{{- else if eq .Role "user" }}User:
+{{ .Content }}
+{{- else if eq .Role "assistant" }}Assistant:
+{{ .Content }}<|endoftext|>
+{{- end }}
+{{- end }}Assistant:
+"""
+
+PARAMETER num_ctx 8192
+PARAMETER repeat_penalty 1.15
+PARAMETER stop "<|endoftext|>"

README.md

@@ -0,0 +1,271 @@
+---
+license: cc-by-nc-4.0
+library_name: transformers
+pipeline_tag: text-generation
+language:
+- en
+---
+
+# ConeML 810M Alpha
+
+ConeML 810M Alpha is an 810,112,512-parameter, decoder-only language
+model trained from scratch and instruction-tuned for constrained English
+tasks. Its measured profile favors single Python functions, selected
+small-number arithmetic families, two-step word problems, and a narrow
+designated-refusal policy.
+
+Results are specific to the documented prompt formats and evaluation task
+families. They are not claims of general coding, reasoning, factual
+knowledge, or production reliability.
+
+- Architecture: LLaMA-style; 28 layers, d=1536, 12 heads (3 KV), tied
+  embeddings, 8192 context, 32,768-token BPE tokenizer
+- Pretraining corpus: 27.87B curated tokens
+- Selected pretrained-base exposure: approximately 12.32B token
+  positions, or 15.2 tokens per parameter
+- Pretraining wall time: approximately 11 days on one NVIDIA RTX 5090;
+  fine-tuning and evaluation are excluded
+- Release `model.safetensors` SHA-256:
+  `e5df8f2edd773ad079ba00d383ace81b96cbb9579d64c570db505f9efc032b76`
+- Companion release: `coneml-810m-alpha-arithmetic`, from the same base,
+  has substantially higher carry/borrow accuracy and lower function and
+  two-step accuracy
+
+## 1. Measured profile
+
+ConeML internal certification uses held-out instances from the same task
+families as the training generators. It is not independent third-party
+certification. Code is scored by executing each generated function
+against held-out tests.
+
+| held-out task family | result | n |
+|---|---:|---:|
+| Python function writing (single function, executed) | 69.0% | 300 |
+| two-step word problems | 79.0% | 500 |
+| 2-digit × 1-digit multiplication | 97.4% | 500 |
+| 1-digit multiplication | 97.8% | 45 |
+| 1-digit addition | 98.6% | 71 |
+| "Which is bigger, X or Y?" | 95.0% | 300 |
+| 2-digit subtraction with borrow | 91.0% | 500 |
+| comparison word problems | 72.6% | 500 |
+| missing addend | 71.6% | 500 |
+| 2–3-digit addition with carry | 53.2% | 500 |
+| missing factor | 17.8% | 500 |
+
+Behavioral screens:
+
+- Designated-refusal probe: 17/17 refusal prompts produced refusals, and
+  5/5 in-scope contrast prompts in matching wording were answered. This
+  small targeted probe measures adherence to that policy, not general
+  epistemic calibration.
+- Conversation-v2: 8/8 turns passed in one scripted dialogue covering
+  cross-turn arithmetic, story revision, comparison explanation, and one
+  unknown-personal-fact refusal. This is a single dialogue, not a general
+  conversation benchmark.
+- Everyday-reasoning screen: 11/20 by manual adjudication; the
+  phrase-sensitive automatic scorer recorded 6/20.
+
+## 2. Peer comparison and efficiency
+
+The pair was tested against five post-trained peers on the same reduced
+diagnostic screen, through each model's native instruction interface,
+with greedy decoding, repetition penalty 1.15, and matched short-answer
+budgets.
+
+| model | parameters | mixed arithmetic (n=585) | executed functions (n=100) | transitive names d1/d3/d5 (n=32 each) | designated refusals (n=17) |
+|---|---:|---:|---:|---:|---:|
+| ConeML 810M Alpha | 0.81B | 421 (72.0%) | 83 | 23/15/15 | **13** |
+| ConeML 810M Alpha-Arithmetic | 0.81B | **442 (75.6%)** | 35 | 26/17/16 | 11 |
+| Qwen3.5 | 0.8B | 154 (26.3%) | 93 | 23/22/10 | 0 |
+| Qwen3 | 0.6B | 223 (38.1%) | **98** | 18/10/9 | 1 |
+| Llama 3.2 Instruct | 1.24B | 343 (58.6%) | 79 | 16/7/5 | 1 |
+| TinyLlama Chat | 1.1B | 113 (19.3%) | 51 | 8/18/22 | 0 |
+| SmolLM2 Instruct | 1.7B | 380 (65.0%) | 96 | 16/6/5 | 1 |
+
+This is not a general leaderboard: the task families match ConeML's
+trained surfaces. On this screen, the ConeML pair led mixed arithmetic;
+ConeML 810M Alpha exceeded Llama 3.2 and TinyLlama on function writing
+but trailed Qwen3.5, Qwen3, and SmolLM2. All models recorded zero
+over-refusals on five in-scope contrasts.
+
+On the question-form name-chain depth screen, ConeML 810M
+Alpha-Arithmetic recorded 26/32, 17/32, and 16/32 at depths 1, 3, and 5;
+ConeML 810M Alpha recorded 23/32, 15/32, and 15/32. The arithmetic
+variant exceeded Qwen3 and Llama 3.2 at all three shown depths and
+Qwen3.5 at depths 1 and 5, while Qwen3.5 led it at depth 3 and TinyLlama
+led the group at depth 5. Entity-chain controls were mixed and are
+reported in the full table. Chance is 1/(depth+1); this is an
+exact-selection surface test, not a claim of general reasoning.
+
+Qwen3.5 with thinking enabled reached 451/585 (77.1%), compared with
+ConeML 810M Alpha-Arithmetic's 442/585 (75.6%), while using at least 17.6 times the
+generated-token budget per item and approximately 24 times the recorded
+wall time. Runtime ratios are implementation-specific.
+
+ConeML's selected base consumed 12.32B token positions—15.2 tokens per
+parameter and approximately 5.99e19 training FLOPs under the `6ND`
+convention. Pretraining took approximately 11 days on one RTX 5090.
+Assuming, rather than claiming to have metered, a 0.70 kW average wall
+draw gives 184.8 kWh; at CHF 0.14–0.30/kWh, that is approximately
+CHF 26–55 of marginal pretraining electricity. This excludes hardware,
+labor, SFT, evaluation, conversion, and emissions accounting.
+
+The complete category table, peer wins, adverse base result, evaluated
+revisions, assumptions, and frozen evidence commitments are in
+[`eval/PEER_COMPARISON.md`](eval/PEER_COMPARISON.md).
+
+## 3. Standard benchmark limits
+
+Zero-shot, greedy decoding with a 256-token generation cap. GSM8K uses
+strict final-number matching; HumanEval reports pass@1 from executed
+tests.
+
+| benchmark | this model | same base, no fine-tune |
+|---|---:|---:|
+| GSM8K (test, first 200) | 12/200 (6.0%) | 7/200 (3.5%) |
+| HumanEval (pass@1, tests executed) | 5/164 (3.0%) | 0/164 (0.0%) |
+
+These results are weak and define an important boundary: the narrower
+task-family results above do not transfer to broad GSM8K or HumanEval
+performance.
+
+## 4. Supported prompt formats
+
+Evaluated decoding is greedy with repetition penalty 1.15, as pinned in
+`generation_config.json`.
+
+```text
+# task format (single turn)
+Question: <task>
+Answer:
+
+# dialogue format (chat_template.jinja)
+User:
+<message>
+Assistant:
+```
+
+Dialogue generation ends at `<|endoftext|>`. Prompting outside these
+formats, including paraphrases, was not systematically evaluated except
+for the published raw-completion spot check.
+
+## 5. Quantized variants
+
+Q8_0 GGUF was evaluated separately under llama.cpp. That runtime and its
+stop handling differ from the bf16 harness, so the scores are not directly
+comparable and differences cannot be attributed solely to quantization.
+
+| held-out task family | Q8_0 |
+|---|---:|
+| Python function writing | 75.0% (n=300) |
+| two-step word problems | 57.0% (n=500) |
+| addition with carry | 40.2% (n=500) |
+| multiplication families | 94.8–95.6% |
+| which-bigger | 92.7% (n=300) |
+
+Use bf16 when the bf16 profile is required.
+
+For local GGUF inference:
+
+```bash
+llama-cli \
+  -m coneml-810m-alpha-Q8_0.gguf \
+  -p $'Question: What is 7 + 8?\nAnswer:' \
+  -n 32 --repeat-penalty 1.15 --no-conversation --single-turn
+```
+
+For Ollama, download `Modelfile` beside the Q8_0 file, then run:
+
+```bash
+ollama create coneml-810m-alpha -f Modelfile
+ollama run coneml-810m-alpha "What is 7 + 8?"
+```
+
+## 6. Loading with Transformers
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo_id = "ConeML/coneml-810m-alpha"
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModelForCausalLM.from_pretrained(
+    repo_id,
+    dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+prompt = "Question: What is 7 + 8?\nAnswer:"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+output = model.generate(
+    **inputs,
+    max_new_tokens=32,
+    do_sample=False,
+    repetition_penalty=1.15,
+)
+answer = tokenizer.decode(
+    output[0][inputs["input_ids"].shape[-1]:],
+    skip_special_tokens=True,
+)
+print(answer)
+```
+
+This is a text-only causal language model. Load it with
+`AutoModelForCausalLM` or `LlamaForCausalLM`, not a multimodal model class.
+
+## 7. Intended use and safety
+
+This release is intended for research, constrained local inference,
+evaluation-harness development, and experiments whose prompts match the
+documented formats. Review outputs before use.
+
+It is not intended for factual retrieval, high-stakes medical, legal, or
+financial decisions, autonomous action, or unsandboxed execution of
+generated code. Generated code may be incomplete or unsafe; inspect and
+test it in an isolated environment.
+
+## 8. Known limitations
+
+- Not a general code model: complete programs scored 0/10, executable SQL
+  1/10, and bash 1/5. The 69% result is for single functions on ConeML's
+  task-family-matched battery.
+- Addition with carry is this release's weakest internally certified
+  arithmetic family at 53.2%; the arithmetic companion scored 96.8%.
+- The model was not evaluated as a factual-QA system and refused all six
+  real-world factual prompts in the designated-refusal probe.
+- Money/decimal change-making scored 0/3 on the held-out screen; the model
+  also showed yes-bias on feasibility questions.
+- Multi-step GSM-class reasoning remained weak.
+- Frameless prompting was spot-checked, not systematically certified.
+
+## 9. Evidence and reproducibility
+
+The `eval/` directory publishes:
+
+- `summary.json`: all aggregate bf16 results used above;
+- `representative-samples.json`: deterministic, rule-selected examples
+  from ConeML-owned probes;
+- `EVALUATION_METHODOLOGY.md`: evaluation definitions and scope;
+- separate Q8_0 aggregate results; and
+- `PRIVATE_EVIDENCE_SHA256SUMS.txt`: commitments to the complete
+  row-level evidence retained by ConeML.
+- `peer-comparison-summary.json`, `PEER_COMPARISON.md`, and
+  `PEER_EVIDENCE_SHA256SUMS.txt`: the peer results, interpretation, and
+  commitments to the retained peer-generation evidence.
+
+Complete proprietary probe rows and generations are retained privately to
+avoid releasing the full measurement instruments. The hashes permit later
+disclosure to be checked against the evidence frozen at release time.
+Public GSM8K and HumanEval rows are not redistributed; only aggregate
+results are published. `SHA256SUMS.txt` covers every shipped file.
+
+## 10. Research license and commercial work
+
+Released for non-commercial use under CC BY-NC 4.0. Commercial use is not
+granted by this release. See `LICENSE.md`.
+
+For commercial evaluation, model-engineering, or licensing enquiries,
+contact [contact@coneml.com](mailto:contact@coneml.com) or visit
+[ConeML for Organizations](https://coneml.com/organizations/). Commercial availability does not
+imply that this alpha checkpoint is suitable for an unvalidated
+production workflow.

SHA256SUMS.txt

@@ -0,0 +1,21 @@
+846a8e2297580b3c8d57f69a07d88833d370f976010b31d9fc9b93e9a3f04464  LICENSE.md
+dae2b5a811b8d4fd08801460bc80968d8792391bec75a235b6e79d0ba2fd952c  Modelfile
+6a0e14867e7ec19781e712fa89f2e9fda460e0f3c87fcf104ad03711d3f7e689  README.md
+fdf72939738a346a2134cd5ede1e9921d52d4d85ac0449249118322de48447e7  chat_template.jinja
+a09065a6d6c5ee5c518ed913085e878e7d3807f7d6cb8bcd1d6ce59653bd41b5  coneml-810m-alpha-Q8_0.gguf
+16835ec01c1fa344c5bd3788c7697ab67e68676ebae3fc374b62f7b30749a6bb  coneml-810m-alpha-f16.gguf
+6cd7853f16b53fdb6bcc44438be39c33726379dc9848798fdcc81ba7f7555a58  config.json
+8a56ef50eebf7604d0408b52249591e258a31ff1c9ebf3785f748c0316637c56  conversion.json
+83b8f89b84387d8c2b22bc2b5d8c20a564fea9f79c7f6e6ab4fa9acee38040c5  eval/EVALUATION_METHODOLOGY.md
+e0b43abe260b588cdf50181b5e396f21abb4b69da151bfa4961539be128cd08d  eval/PEER_COMPARISON.md
+0f134f0b207601ef2d5650bfe4fd56e810e1c6e32938bdde94035ed08df95165  eval/PEER_EVIDENCE_SHA256SUMS.txt
+b2414d6dddbac7128724d27a7ce54e2fa3586943ece7b94e6c3c5188a1f04484  eval/PRIVATE_EVIDENCE_SHA256SUMS.txt
+0108c09e9b835a0da81c5093b40f0b7937b1553de3abdcb5c207c75888714db2  eval/certification-Q8_0.json
+b4cc4f98ccd8ba91206e4446c38f6b1e5f6e7a07f3c9ec963ee16d6a0619dc71  eval/code-cert-Q8_0.json
+ce18163c651681a1c4ed2ff6cdc8644494f00a8109a96cc3d0b8768bb9a4c6fc  eval/peer-comparison-summary.json
+bff2af0c69ec8cce87cd93a69c22045b4062588e60f1dafb4ba0b85ac68f2c8d  eval/representative-samples.json
+f6ce9e02abad733c0d5ae9fdaa58f290441a24c4f24c7673c4f50ca5150e1d70  eval/summary.json
+2e2ddba5318c74a4fcc31cfdfdc6e067564176b6404da484932f95a7fdc9712a  generation_config.json
+e5df8f2edd773ad079ba00d383ace81b96cbb9579d64c570db505f9efc032b76  model.safetensors
+dd9e18c94d2206bb6c3e26caccc98f5b72dd930784cc37e989439b79ceacbf47  tokenizer.json
+88a2d6096fc775fca098fa3d8f4be827b498d21af168e24ba3bd0509b8a63c59  tokenizer_config.json

chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'system' %}System:
+{{ message['content'] }}
+{% elif message['role'] == 'user' %}User:
+{{ message['content'] }}
+{% elif message['role'] == 'assistant' %}Assistant:
+{{ message['content'] }}{% if not loop.last %}{{ eos_token }}
+{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}Assistant:
+{% endif %}

coneml-810m-alpha-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09065a6d6c5ee5c518ed913085e878e7d3807f7d6cb8bcd1d6ce59653bd41b5
+size 862157472

coneml-810m-alpha-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16835ec01c1fa344c5bd3788c7697ab67e68676ebae3fc374b62f7b30749a6bb
+size 1621555872

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 3,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}

conversion.json

@@ -0,0 +1,7 @@
+{
+  "artifact": "ConeML/coneml-810m-alpha",
+  "conversion": "weights-only safetensors export",
+  "dtype": "bfloat16",
+  "missing_keys": [],
+  "unexpected_keys": []
+}

eval/EVALUATION_METHODOLOGY.md

@@ -0,0 +1,59 @@
+# ConeML 810M — evaluation methodology and variant lineage (public record)
+
+Two released variants share one from-scratch 810M base checkpoint and
+differ only in supervised fine-tuning; both were evaluated with the same
+bf16 instruments.
+
+- `coneml-810m-alpha` — function-writing / mixed-arithmetic profile
+- `coneml-810m-alpha-arithmetic` — carry/borrow arithmetic variant
+
+## Methodology
+
+- **ConeML internal certification**: large-n (300–500 per task family)
+  batteries of unseen instances in the trained prompt formats, greedy
+  decoding, repetition
+  penalty 1.15. Code tasks are scored by EXECUTING the generated function
+  against held-out tests; SQL by executing against a live sqlite database;
+  scripts by captured stdout. No pattern-match scoring for anything
+  execution can decide.
+- **Behavior probes**: held-out designated-refusal prompts plus in-scope
+  contrast pairs in matching wording; one separately rerun, scripted
+  eight-turn conversation; and an everyday-reasoning screen with manual
+  adjudication. Aggregate results and deterministic representative
+  ConeML-owned rows are public; complete rows are retained privately.
+- **Public benchmarks**: GSM8K (first 200, zero-shot, strict final-number
+  match) and HumanEval (pass@1, tests executed), identical harness across
+  variants and the pretrained base. Aggregate results are public;
+  benchmark rows are not redistributed.
+- **Quantized variants are evaluated separately**: each shipped GGUF carries
+  its own result table. The GGUF and bf16 harnesses differ in runtime and
+  stop handling, so score gaps are not attributed solely to quantization.
+
+## Why two variants
+
+Under fixed architecture and base checkpoint, modest differences in
+fine-tuning composition produced large, cross-surface capability
+tradeoffs (e.g., one build scores 96.8% on held-out carry addition while
+the other scores 79.0% on held-out two-step word problems and 69.0% on
+held-out function writing). Rather than presenting one checkpoint as
+dominant, each variant ships with its measured envelope and a
+recommendation for which profile
+fits which pipeline. A checkpoint's profile is measured, never inferred.
+
+## Shared limitations
+
+Function-writing is evaluated for single Python functions only — neither
+variant is a general code model (complete programs, executable SQL, and
+bash scored near zero for both and are stated out of scope). Both variants
+refused every designated refusal prompt, including real factual questions;
+this targeted behavior is not evidence of general epistemic calibration.
+Multi-step GSM-class reasoning is weak in every variant tested this cycle.
+
+## Evidence disclosure
+
+The public folders contain aggregate result tables, deterministic
+representative examples from ConeML-owned instruments, and SHA-256
+commitments to the complete row-level evidence. Full proprietary probe
+rows are retained by ConeML rather than distributed. This preserves the
+measurement instruments while allowing later disclosure to be checked
+against the evidence frozen for this release.

eval/PEER_COMPARISON.md

@@ -0,0 +1,140 @@
+# ConeML 810M peer diagnostic and resource context
+
+Date: 2026-07-30
+
+This is an interface-specific diagnostic screen, not a neutral ranking of
+general model capability. Each instruction-tuned model was evaluated
+through its own instruction interface. All models used greedy decoding
+with repetition penalty 1.15. Arithmetic and function-writing used
+matched short-answer generation budgets.
+
+The task families match ConeML's supervised training surfaces. That gives
+the comparison practical value for locating the release's envelope, but
+it also means these results must not be generalized to unrelated tasks.
+Standard GSM8K and HumanEval results remain separately disclosed in the
+model cards.
+
+## Instruct-model results
+
+| measured surface | ConeML 810M Alpha | ConeML 810M Alpha-Arithmetic | Qwen3.5 0.8B | Qwen3 0.6B | Llama 3.2 1B Instruct | TinyLlama Chat | SmolLM2 1.7B Instruct |
+|---|---:|---:|---:|---:|---:|---:|---:|
+| mixed arithmetic screen (n=585) | 421 (72.0%) | **442 (75.6%)** | 154 (26.3%) | 223 (38.1%) | 343 (58.6%) | 113 (19.3%) | 380 (65.0%) |
+| four core arithmetic lanes (n=225) | 177 (78.7%) | **221 (98.2%)** | 150 (66.7%) | 208 (92.4%) | **221 (98.2%)** | 92 (40.9%) | **221 (98.2%)** |
+| executed single functions (n=100) | 83 | 35 | 93 | **98** | 79 | 51 | 96 |
+| transitive names, depth 1/3/5 (n=32 each) | 23/15/15 | 26/17/16 | 23/22/10 | 18/10/9 | 16/7/5 | 8/18/22 | 16/6/5 |
+| transitive entities, depth 1/3/5 (n=32 each) | 15/11/10 | 16/11/12 | 18/16/14 | 14/17/11 | 0/6/7 | 14/15/11 | 22/21/10 |
+| designated-refusal prompts (n=17) | **13** | 11 | 0 | 1 | 1 | 0 | 1 |
+| over-refusals on contrasts (n=5) | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
+
+The honest result is mixed:
+
+- At matched short-answer budgets, the ConeML pair led this post-trained
+  peer group on the broader arithmetic screen.
+- On the four core arithmetic lanes, the Arithmetic variant tied Llama
+  3.2 Instruct and SmolLM2 at this reduced sample size. Its separate
+  full-size internal result is 1,093/1,116 (97.9%).
+- ConeML 810M Alpha exceeded Llama 3.2 Instruct and TinyLlama Chat on the
+  executed function screen, but Qwen3.5, Qwen3, and SmolLM2 scored higher.
+- On name-chain transitive selection, ConeML 810M Alpha-Arithmetic
+  recorded 26/32, 17/32,
+  and 16/32 at depths 1, 3, and 5. It exceeded Qwen3 and Llama 3.2 at all
+  three shown depths and exceeded Qwen3.5 at depths 1 and 5; Qwen3.5 led
+  it at depth 3, and TinyLlama led the group at depth 5.
+- Entity-chain transfer was mixed: ConeML 810M Alpha recorded 15/11/10
+  and ConeML 810M Alpha-Arithmetic 16/11/12 at depths 1/3/5, while different peers led each
+  depth. Chance is 1/(depth+1). The non-monotonic peer rows reinforce
+  that this is an exact-selection surface test, not proof of general
+  reasoning depth.
+- The refusal row measures a trained response policy on designated
+  prompts, not factual correctness or general epistemic calibration.
+
+The peer-harness refusal results above differ from the dedicated ConeML
+probe's 17/17 for each release because the generation loops differ. Both
+measurements are reported rather than merged.
+
+## Qwen3.5 thinking-mode sensitivity
+
+Qwen3.5 0.8B was also evaluated with thinking enabled on the same 585
+arithmetic items:
+
+| metric | Qwen3.5 thinking | Qwen3.5 short-answer | ConeML 810M Alpha-Arithmetic short-answer |
+|---|---:|---:|---:|
+| accuracy | 451/585 (77.1%) | 154/585 (26.3%) | 442/585 (75.6%) |
+| generated tokens per item | mean 844; median 699 | at most 48 | at most 48 |
+| p95 / generation cap | 1,536 / 1,536 | 48 / 48 | 48 / 48 |
+| truncation rate | 138/585 (23.6%) | approximately 0% | approximately 0% |
+| mean wall time per item | 2.43 s | approximately 0.1 s | approximately 0.1 s |
+| correct answers per 1,000 generated tokens | 0.91 | 5.5 | approximately 15.7 or higher |
+
+Thinking mode recovered Qwen3.5 to statistical parity with ConeML 810M
+Alpha-Arithmetic on this screen, while using at least 17.6 times the
+per-answer generation budget and approximately 24 times the measured wall
+time. Wall-time ratios are specific to the recorded hardware, batching,
+and implementation. This is an inference-cost comparison, not a claim
+that thinking mode is intrinsically inferior.
+
+## Against-interest base result
+
+On the same 585 arithmetic items, through a task frame native to neither
+base model, Qwen3.5 0.8B Base scored 492/585 (84.1%), while ConeML base
+checkpoint 188 scored 156/585 (26.7%). This result is included because it
+prevents an absolute-superiority reading: high-exposure base models may
+already contain strong task-formatted behavior, and post-training can
+move capability between output surfaces.
+
+## Training-resource context
+
+ConeML's selected base consumed approximately 12.32B token positions:
+15.2 tokens per parameter and approximately 5.99e19 training FLOPs under
+the `6 × parameters × tokens` convention.
+
+| model family | disclosed pretraining tokens | approximate tokens/parameter | approximate training FLOPs vs ConeML |
+|---|---:|---:|---:|
+| ConeML 810M | 12.32B | 15.2 | 1× |
+| TinyLlama 1.1B | 3T | 2,727 | 330× |
+| Llama 3.2 1B | up to 9T | 7,258 | 1,118×, plus distillation |
+| SmolLM2 1.7B | 11T | 6,471 | 1,873× |
+| Qwen3 0.6B | 36T | 60,000 | 2,164× |
+| Qwen3.5 0.8B | not disclosed | not stated | not stated |
+
+These are estimated pretraining FLOP ratios, not historical electricity
+or monetary costs for the peer models.
+
+ConeML pretraining took approximately 11 days on one local RTX 5090. At
+an explicitly assumed average wall draw of 0.70 kW, that corresponds to
+184.8 kWh. Applying an assumed Swiss residential tariff range of
+CHF 0.14–0.30/kWh gives approximately CHF 26–55 of marginal pretraining
+electricity.
+
+| ConeML pretraining unit | estimate |
+|---|---:|
+| average throughput | 12,963 token positions/s |
+| wall time per billion token positions | 21.4 h |
+| energy per billion token positions | 15.0 kWh |
+| energy per million token positions | 15 Wh |
+| estimated wall energy per token position | 0.054 J |
+| marginal electricity per billion token positions | CHF 2.10–4.50 |
+
+The energy and cost figures are estimates derived from the stated power
+and tariff assumptions, not meter readings. They exclude hardware,
+depreciation, labor, supervised fine-tuning, evaluation, conversion,
+datacenter PUE, and carbon intensity. No emissions claim is made.
+
+## Evaluated revisions
+
+- `Qwen/Qwen3.5-0.8B@2fc06364715b967f1860aea9cf38778875588b17`
+- `Qwen/Qwen3-0.6B@c1899de289a04d12100db370d81485cdf75e47ca`
+- `unsloth/Llama-3.2-1B-Instruct@5a8abab4a5d6f164389b1079fb721cfab8d7126c`
+- `TinyLlama/TinyLlama-1.1B-Chat-v1.0@fe8a4ea1ffedaf415f4da2f062534de366a451e6`
+- `HuggingFaceTB/SmolLM2-1.7B-Instruct@31b70e2e869a7173562077fd711b654946d38674`
+
+The exact aggregates are in `peer-comparison-summary.json`. Complete
+generation rows are retained privately; their frozen SHA-256 commitments
+are published in `PEER_EVIDENCE_SHA256SUMS.txt`.
+
+## Primary resource disclosures
+
+- Qwen3 pretraining: [Qwen3 release post](https://qwenlm.github.io/blog/qwen3/)
+- Llama 3.2 token count and distillation: [Meta Llama 3.2 model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md)
+- TinyLlama token count: [TinyLlama model card](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
+- SmolLM2 token count: [Hugging Face SmolLM2 model card](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B)

eval/PEER_EVIDENCE_SHA256SUMS.txt

@@ -0,0 +1,35 @@
+96a805aed179f77d9f1959216f9a39e8bf8d50dea5465eeea1eb24e96502a6af  SOURCE_PEER_COMPARISON_V2.md
+a5d6cd4d7a2643b316cefb1dcb6f43296bb69da4064dbc3b3ab4a123bf36b2b1  base-reference/coneml-base188.json
+83643ce110655e708d50f4eb3ee29ab08ab8e003768eb5b5da9a3e545bc9b8ef  base-reference/coneml-base188.rows.jsonl
+ca387426c55ac72d50041e2f082bd4cdc747eedb51deca7929cf7a4acea2c5b6  base-reference/coneml-native-transitive.json
+43ef584d37c6a276b190aeb741597b54bfebbf7bbd9c37df5d82a2e15a8ee2d1  base-reference/qwen35-0.8b-base.json
+25de33180d4073777d29871882b57f1556733e9a8c1e10eba14a8cac062b5c35  base-reference/qwen35-0.8b-base.rows.jsonl
+81b9effe8a6f808b5bf9dbf639ec88235004c6c270b5275e382316adb07ff9d1  instruct/coneml-810m-alpha-transchat.json
+4b2c433ecf35c6dd409b9d09e2cb858e1d68e179d189dd9074e8ed681a9be44a  instruct/coneml-810m-alpha-transchat.rows.jsonl
+2003c73a54602f3a30980d6c7f85feef39b63fd11cef9fc20a90044d3569ba77  instruct/coneml-810m-alpha.json
+8da107545bd6717c7795ff4e827698e5e269d451f2390f24dccc516fc390ab44  instruct/coneml-810m-alpha.rows.jsonl
+aea504626bbd9f7d8daf576777fe82fa4c57947a30cd654953889edf8247101f  instruct/coneml-810m-arithmetic-transchat.json
+5b8864c9810d556a8bc2b09a43a2b34f69c0fad6889c8c04b63717c92b6f3c27  instruct/coneml-810m-arithmetic-transchat.rows.jsonl
+77d514c14e14557c4ac30e8a8c3f4c5887f0db0dff39b8ea14baea164327d027  instruct/coneml-810m-arithmetic.json
+a60ed3e533c0c4a77b34a21f80b8df8de85e3df074f3cacdc3bbd4b5e0741cce  instruct/coneml-810m-arithmetic.rows.jsonl
+aa35b93f46778ffb22351ac411f2fc04e645775e416b5a9423f925bb6d6b1609  instruct/llama32-1b-instruct-transchat.json
+ee514c35d86f27172a004325b26da915f869164adae59edf8d95b01d958e683f  instruct/llama32-1b-instruct-transchat.rows.jsonl
+f4553ef34844e55364a87f631fac03a3545acbb14cd12dcf182f16151b5e5f8a  instruct/llama32-1b-instruct.json
+d5c0fd8b00b50754ac7dede96081afeaf3143795e005134cf5543483859340bf  instruct/llama32-1b-instruct.rows.jsonl
+a61b56681810410dfc3a8d8e758b8ccd11d01ebcce2d963d6bdbca4644c2cee9  instruct/qwen3-0.6b-transchat.json
+f7c763441edc0d5e37a34902a3cc4efcacc6a35b47056adb9356879a4407cb31  instruct/qwen3-0.6b-transchat.rows.jsonl
+3f34342d79095a5754512ebf57192fdf98a16b364a250712993ac1da0b65e252  instruct/qwen3-0.6b.json
+05847f4187651780008331a85c9cd5fa84d3b636320c9a809fb3c307f1a230d6  instruct/qwen3-0.6b.rows.jsonl
+21984e00a4a6da3d2887138ede25c03e9007fee0be41de462ef58dc58db89554  instruct/qwen35-0.8b-transchat.json
+48a53b6bf3829c207953b1075160df9f6702b1fc2162426577aa69530856e555  instruct/qwen35-0.8b-transchat.rows.jsonl
+fa11fbf67c047ac541ecd38571867f9fe68bfb8aec12b84f2addda8a6d561642  instruct/qwen35-0.8b.json
+74a6debf6ae55db9895f556e654b6905fde871358a94c9c4a2730a418b0e2608  instruct/qwen35-0.8b.rows.jsonl
+72598668bfce72497ac67a4d83d1cad7538c63ec933e8a1d1198876d85dc8a67  instruct/qwen35-thinking-sensitivity.json
+8917677a4c9d29124c5ade229f7080bbd0ccb83471c3d7d39a6f958224596a8f  instruct/smollm2-1.7b-instruct-transchat.json
+deb9eb805475e4ad2d158283b469830138fdf42ee0c9a903bf3611b43a7869ff  instruct/smollm2-1.7b-instruct-transchat.rows.jsonl
+94a3440cdaae14eb27beaf36a1a0103dab4a6d292bc382981f0514a82a93ed0f  instruct/smollm2-1.7b-instruct.json
+1b06370ad7b940ed05b59ffe4acd19035341cfe078ed7b01d59d168abc8d0c71  instruct/smollm2-1.7b-instruct.rows.jsonl
+bdd7cf2867643439e90a3e04cb209e6130839af9422e492bcd2eb1c2cba4556e  instruct/tinyllama-chat-transchat.json
+472aad0c169c4f943fbc9a8367d65fa2d5c41acbbee66d099e16a286f8676d1c  instruct/tinyllama-chat-transchat.rows.jsonl
+3a7c2e7ebcaa78b4b7d9b6d84a5b90a495f260f97287bad3282d54fc84e0c009  instruct/tinyllama-chat.json
+5926a31e926279f8d9459d19cbbe9730a06071bb8b4029c2f9174804ab447943  instruct/tinyllama-chat.rows.jsonl

eval/PRIVATE_EVIDENCE_SHA256SUMS.txt

@@ -0,0 +1,10 @@
+532b8cd9c9f7eb7cd047aac26dfe6a99880503a7b09bf79314287c28cb908ce4  base188-public-benchmarks.json
+7573c5c28c069286f630d9586a28a9a9569a49979796e01bae552e637c4c3269  basic-code.json
+c68da2bd403a6b608bc26eaa94e4bf5ab297d2cb7ede08698e1f819f063dab89  certification-v1.json
+f39d20f312ce7c323c6c72a18609334836098815374a898b1c8bc8e33b76592f  code-cert.json
+3b263314c8690fb912a03fc87b5d81dd38e499a6f3ef4353dee124239572a826  conversation.log
+90596902bb4246432ac527a4533e61ce0518551a782e4f43ad26fde72239c1bc  conversation-v2.json
+66da1621bd1be5bfc9dd3748c354a77c4bd394332012f1dbc592e6675e888c03  everyday-manual-adjudication.json
+1cd23b4c12e50bf9c651810a9822d81e38c9a3684ef4d3e8d2ceb4709553c8c8  public-benchmarks.json
+89705a3fe5cbdcbb74f88eb7b7c0ea92a86320934cdc0f67a90e9ab75739a747  raw-probe.jsonl
+0b006d3027fe6c6f2fe214d1b4eb5eec4ff0b4958e067527a90c78b8476962bc  refusal-probe.json

eval/certification-Q8_0.json

@@ -0,0 +1,55 @@
+{
+  "by_category": {
+    "add-1d": {
+      "correct": 65,
+      "n": 71,
+      "acc": 0.9155
+    },
+    "add-2d-carry": {
+      "correct": 201,
+      "n": 500,
+      "acc": 0.402
+    },
+    "comparison": {
+      "correct": 334,
+      "n": 500,
+      "acc": 0.668
+    },
+    "missing-addend": {
+      "correct": 355,
+      "n": 500,
+      "acc": 0.71
+    },
+    "missing-factor": {
+      "correct": 78,
+      "n": 500,
+      "acc": 0.156
+    },
+    "mul-1d": {
+      "correct": 43,
+      "n": 45,
+      "acc": 0.9556
+    },
+    "mul-2dx1d": {
+      "correct": 474,
+      "n": 500,
+      "acc": 0.948
+    },
+    "sub-borrow": {
+      "correct": 433,
+      "n": 500,
+      "acc": 0.866
+    },
+    "two-step": {
+      "correct": 285,
+      "n": 500,
+      "acc": 0.57
+    },
+    "which-bigger": {
+      "correct": 278,
+      "n": 300,
+      "acc": 0.9267
+    }
+  },
+  "runtime": "llama.cpp Q8_0 aggregate summary"
+}

eval/code-cert-Q8_0.json

@@ -0,0 +1,6 @@
+{
+  "passed": 225,
+  "n": 300,
+  "rate": 0.75,
+  "runtime": "llama.cpp Q8_0 aggregate summary"
+}

eval/peer-comparison-summary.json

@@ -0,0 +1,140 @@
+{
+  "schema_version": 1,
+  "date": "2026-07-30",
+  "scope": "Interface-specific diagnostic screen, not a neutral ranking of general model capability. Each instruct model used its native instruction interface. Arithmetic and function-writing used matched short-answer generation budgets.",
+  "decoding": {
+    "strategy": "greedy",
+    "repetition_penalty": 1.15,
+    "arithmetic_n": 585,
+    "core_arithmetic_n": 225,
+    "function_writing_n": 100,
+    "transitive_n_per_family_depth": 32,
+    "designated_refusal_n": 17,
+    "refusal_contrast_n": 5
+  },
+  "evaluated_revisions": {
+    "ConeML/coneml-810m-alpha": "local release artifact e5df8f2edd773ad079ba00d383ace81b96cbb9579d64c570db505f9efc032b76",
+    "ConeML/coneml-810m-alpha-arithmetic": "local release artifact e1de27f5f91ac43130ce2a57a4bf9a036b84b2e5b589789b5981ecf79489e0d1",
+    "Qwen/Qwen3.5-0.8B": "2fc06364715b967f1860aea9cf38778875588b17",
+    "Qwen/Qwen3-0.6B": "c1899de289a04d12100db370d81485cdf75e47ca",
+    "unsloth/Llama-3.2-1B-Instruct": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "TinyLlama/TinyLlama-1.1B-Chat-v1.0": "fe8a4ea1ffedaf415f4da2f062534de366a451e6",
+    "HuggingFaceTB/SmolLM2-1.7B-Instruct": "31b70e2e869a7173562077fd711b654946d38674"
+  },
+  "instruct_results": [
+    {
+      "model": "ConeML/coneml-810m-alpha",
+      "parameters_billions": 0.8101,
+      "arithmetic_mixed": {"correct": 421, "n": 585, "accuracy": 0.7197},
+      "arithmetic_core_four_lanes": {"correct": 177, "n": 225, "accuracy": 0.7867},
+      "executed_functions": {"correct": 83, "n": 100, "accuracy": 0.83},
+      "transitive_question_form": {"names_d1_d3_d5": [23, 15, 15], "entities_d1_d3_d5": [15, 11, 10], "n_each": 32},
+      "designated_refusals": {"correct": 13, "n": 17, "accuracy": 0.7647},
+      "over_refusals": {"count": 0, "n": 5}
+    },
+    {
+      "model": "ConeML/coneml-810m-alpha-arithmetic",
+      "parameters_billions": 0.8101,
+      "arithmetic_mixed": {"correct": 442, "n": 585, "accuracy": 0.7556},
+      "arithmetic_core_four_lanes": {"correct": 221, "n": 225, "accuracy": 0.9822},
+      "executed_functions": {"correct": 35, "n": 100, "accuracy": 0.35},
+      "transitive_question_form": {"names_d1_d3_d5": [26, 17, 16], "entities_d1_d3_d5": [16, 11, 12], "n_each": 32},
+      "designated_refusals": {"correct": 11, "n": 17, "accuracy": 0.6471},
+      "over_refusals": {"count": 0, "n": 5}
+    },
+    {
+      "model": "Qwen/Qwen3.5-0.8B",
+      "parameters_billions": 0.8,
+      "mode": "thinking disabled for matched short-answer budget",
+      "arithmetic_mixed": {"correct": 154, "n": 585, "accuracy": 0.2632},
+      "arithmetic_core_four_lanes": {"correct": 150, "n": 225, "accuracy": 0.6667},
+      "executed_functions": {"correct": 93, "n": 100, "accuracy": 0.93},
+      "transitive_question_form": {"names_d1_d3_d5": [23, 22, 10], "entities_d1_d3_d5": [18, 16, 14], "n_each": 32},
+      "designated_refusals": {"correct": 0, "n": 17, "accuracy": 0.0},
+      "over_refusals": {"count": 0, "n": 5}
+    },
+    {
+      "model": "Qwen/Qwen3-0.6B",
+      "parameters_billions": 0.6,
+      "arithmetic_mixed": {"correct": 223, "n": 585, "accuracy": 0.3812},
+      "arithmetic_core_four_lanes": {"correct": 208, "n": 225, "accuracy": 0.9244},
+      "executed_functions": {"correct": 98, "n": 100, "accuracy": 0.98},
+      "transitive_question_form": {"names_d1_d3_d5": [18, 10, 9], "entities_d1_d3_d5": [14, 17, 11], "n_each": 32},
+      "designated_refusals": {"correct": 1, "n": 17, "accuracy": 0.0588},
+      "over_refusals": {"count": 0, "n": 5}
+    },
+    {
+      "model": "unsloth/Llama-3.2-1B-Instruct",
+      "parameters_billions": 1.24,
+      "arithmetic_mixed": {"correct": 343, "n": 585, "accuracy": 0.5863},
+      "arithmetic_core_four_lanes": {"correct": 221, "n": 225, "accuracy": 0.9822},
+      "executed_functions": {"correct": 79, "n": 100, "accuracy": 0.79},
+      "transitive_question_form": {"names_d1_d3_d5": [16, 7, 5], "entities_d1_d3_d5": [0, 6, 7], "n_each": 32},
+      "designated_refusals": {"correct": 1, "n": 17, "accuracy": 0.0588},
+      "over_refusals": {"count": 0, "n": 5}
+    },
+    {
+      "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+      "parameters_billions": 1.1,
+      "arithmetic_mixed": {"correct": 113, "n": 585, "accuracy": 0.1932},
+      "arithmetic_core_four_lanes": {"correct": 92, "n": 225, "accuracy": 0.4089},
+      "executed_functions": {"correct": 51, "n": 100, "accuracy": 0.51},
+      "transitive_question_form": {"names_d1_d3_d5": [8, 18, 22], "entities_d1_d3_d5": [14, 15, 11], "n_each": 32},
+      "designated_refusals": {"correct": 0, "n": 17, "accuracy": 0.0},
+      "over_refusals": {"count": 0, "n": 5}
+    },
+    {
+      "model": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
+      "parameters_billions": 1.7,
+      "arithmetic_mixed": {"correct": 380, "n": 585, "accuracy": 0.6496},
+      "arithmetic_core_four_lanes": {"correct": 221, "n": 225, "accuracy": 0.9822},
+      "executed_functions": {"correct": 96, "n": 100, "accuracy": 0.96},
+      "transitive_question_form": {"names_d1_d3_d5": [16, 6, 5], "entities_d1_d3_d5": [22, 21, 10], "n_each": 32},
+      "designated_refusals": {"correct": 1, "n": 17, "accuracy": 0.0588},
+      "over_refusals": {"count": 0, "n": 5}
+    }
+  ],
+  "qwen35_thinking_sensitivity": {
+    "model": "Qwen/Qwen3.5-0.8B",
+    "mode": "thinking enabled",
+    "arithmetic_mixed": {"correct": 451, "n": 585, "accuracy": 0.771},
+    "generated_tokens": {"mean": 844, "median": 699, "p95": 1536},
+    "generation_cap": 1536,
+    "truncation": {"count": 138, "n": 585, "rate": 0.2359},
+    "wall_seconds_per_item_mean": 2.43,
+    "correct_per_1000_generated_tokens": 0.913,
+    "comparison": "Qwen thinking reached parity with ConeML 810M Alpha-Arithmetic's 442/585 while using at least 17.6 times the generated-token budget per item. The recorded wall-time ratio was approximately 24 times. Runtime measurements are hardware- and implementation-specific."
+  },
+  "against_interest_base_result": {
+    "scope": "Same arithmetic items through a task frame not native to either base model.",
+    "ConeML_base_188": {"correct": 156, "n": 585, "accuracy": 0.2667},
+    "Qwen3.5_0.8B_Base": {"correct": 492, "n": 585, "accuracy": 0.841},
+    "interpretation": "The peer base result prevents an absolute-superiority interpretation and illustrates sensitivity to training exposure and interface."
+  },
+  "training_resource_context": {
+    "ConeML": {
+      "pretraining_token_positions": 12320000000,
+      "tokens_per_parameter": 15.2,
+      "estimated_training_flops_6ND": 5.99e19,
+      "pretraining_wall_time_days": 11,
+      "hardware": "one NVIDIA RTX 5090",
+      "power_assumption_kw_average_wall": 0.70,
+      "estimated_pretraining_energy_kwh": 184.8,
+      "assumed_swiss_residential_tariff_chf_per_kwh": [0.14, 0.30],
+      "estimated_marginal_pretraining_electricity_chf": [25.87, 55.44],
+      "exclusions": ["hardware", "depreciation", "labor", "SFT", "evaluation", "conversion", "grid-carbon estimate"]
+    },
+    "peer_compute_context": [
+      {"model": "TinyLlama 1.1B", "published_pretraining_tokens": 3000000000000, "approx_tokens_per_parameter": 2727, "approx_flops_vs_coneml": 330},
+      {"model": "Llama 3.2 1B", "published_pretraining_tokens": 9000000000000, "approx_tokens_per_parameter": 7258, "approx_flops_vs_coneml": 1118, "note": "plus distillation"},
+      {"model": "SmolLM2 1.7B", "published_pretraining_tokens": 11000000000000, "approx_tokens_per_parameter": 6471, "approx_flops_vs_coneml": 1873},
+      {"model": "Qwen3 0.6B", "published_pretraining_tokens": 36000000000000, "approx_tokens_per_parameter": 60000, "approx_flops_vs_coneml": 2164},
+      {"model": "Qwen3.5 0.8B", "published_pretraining_tokens": null, "approx_tokens_per_parameter": null, "approx_flops_vs_coneml": null}
+    ]
+  },
+  "evidence": {
+    "public_interpretation": "PEER_COMPARISON.md",
+    "private_rows": "retained by ConeML",
+    "hash_commitment": "PEER_EVIDENCE_SHA256SUMS.txt"
+  }
+}

eval/representative-samples.json

@@ -0,0 +1,403 @@
+{
+  "schema_version": 1,
+  "model": "ConeML/coneml-810m-alpha",
+  "selection_policy": {
+    "task_families": "First passing and first failing row in original order for each family, where both exist.",
+    "function_writing": "First three passing and first three failing rows in original order.",
+    "basic_code": "First passing and first failing row in original order for each screen type, where both exist.",
+    "refusal": "First two designated-refusal rows and first two in-scope contrast rows in original order.",
+    "raw_completion": "Predeclared indices 0, 2, 4, and 10, spanning narrative, explanation, code, and prose arithmetic prompts."
+  },
+  "task_family_examples": [
+    {
+      "category": "add-1d",
+      "examples": [
+        {
+          "id": "cert-00000",
+          "category": "add-1d",
+          "prompt": "What is 0 + 0?",
+          "gen": " 0.",
+          "expected": "0",
+          "ok": true
+        },
+        {
+          "id": "cert-00002",
+          "category": "add-1d",
+          "prompt": "What is 0 + 2?",
+          "gen": " 0.",
+          "expected": "2",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "add-2d-carry",
+      "examples": [
+        {
+          "id": "cert-00117",
+          "category": "add-2d-carry",
+          "prompt": "What is 69 + 19?",
+          "gen": " 69 + 19 = 88",
+          "expected": "88",
+          "ok": true
+        },
+        {
+          "id": "cert-00116",
+          "category": "add-2d-carry",
+          "prompt": "What is 26 + 37?",
+          "gen": " 61",
+          "expected": "63",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "comparison",
+      "examples": [
+        {
+          "id": "cert-02616",
+          "category": "comparison",
+          "prompt": "Bram has 14 acorns. Ines has 40 acorns. How many more acorns does Ines have than Bram?",
+          "gen": " 26.",
+          "expected": "26",
+          "ok": true
+        },
+        {
+          "id": "cert-02619",
+          "category": "comparison",
+          "prompt": "Zora has 163 marbles. Ugo has 187 marbles. How many more marbles does Ugo have than Zora?",
+          "gen": " 44.",
+          "expected": "24",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "missing-addend",
+      "examples": [
+        {
+          "id": "cert-01616",
+          "category": "missing-addend",
+          "prompt": "99 + ? = 192. What number goes in the blank?",
+          "gen": " 93",
+          "expected": "93",
+          "ok": true
+        },
+        {
+          "id": "cert-01617",
+          "category": "missing-addend",
+          "prompt": "68 + ? = 259. What number goes in the blank?",
+          "gen": " 92",
+          "expected": "191",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "missing-factor",
+      "examples": [
+        {
+          "id": "cert-02116",
+          "category": "missing-factor",
+          "prompt": "18 × ? = 702. What number goes in the blank?",
+          "gen": " 39.",
+          "expected": "39",
+          "ok": true
+        },
+        {
+          "id": "cert-02117",
+          "category": "missing-factor",
+          "prompt": "43 × ? = 1720. What number goes in the blank?",
+          "gen": " 354.",
+          "expected": "40",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "mul-1d",
+      "examples": [
+        {
+          "id": "cert-00071",
+          "category": "mul-1d",
+          "prompt": "What is 2 × 2?",
+          "gen": " 4",
+          "expected": "4",
+          "ok": true
+        },
+        {
+          "id": "cert-00096",
+          "category": "mul-1d",
+          "prompt": "What is 6 × 2?",
+          "gen": " 6.",
+          "expected": "12",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "mul-2dx1d",
+      "examples": [
+        {
+          "id": "cert-01116",
+          "category": "mul-2dx1d",
+          "prompt": "What is 82 × 3?",
+          "gen": " 82 × 3 = 246.",
+          "expected": "246",
+          "ok": true
+        },
+        {
+          "id": "cert-01172",
+          "category": "mul-2dx1d",
+          "prompt": "What is 15 × 2?",
+          "gen": " 15.",
+          "expected": "30",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "sub-borrow",
+      "examples": [
+        {
+          "id": "cert-00616",
+          "category": "sub-borrow",
+          "prompt": "What is 82 - 47?",
+          "gen": " 35",
+          "expected": "35",
+          "ok": true
+        },
+        {
+          "id": "cert-00630",
+          "category": "sub-borrow",
+          "prompt": "What is 96 - 17?",
+          "gen": " 69",
+          "expected": "79",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "two-step",
+      "examples": [
+        {
+          "id": "cert-03116",
+          "category": "two-step",
+          "prompt": "Ada had 37 ribbons, got 36 more, then lost 27. How many ribbons does Ada have now?",
+          "gen": " 37 + 36 = 73. 73 − 27 = 46. The answer is 46.",
+          "expected": "46",
+          "ok": true
+        },
+        {
+          "id": "cert-03133",
+          "category": "two-step",
+          "prompt": "Mona had 142 acorns, got 18 more, then lost 21. How many acorns does Mona have now?",
+          "gen": " 142.",
+          "expected": "139",
+          "ok": false
+        }
+      ]
+    },
+    {
+      "category": "which-bigger",
+      "examples": [
+        {
+          "id": "cert-03616",
+          "category": "which-bigger",
+          "prompt": "Which is bigger, 897 or 531?",
+          "gen": " 897 is bigger.",
+          "expected": "897",
+          "ok": true
+        },
+        {
+          "id": "cert-03637",
+          "category": "which-bigger",
+          "prompt": "Which is bigger, 990 or 998?",
+          "gen": " 990 is bigger.",
+          "expected": "998",
+          "ok": false
+        }
+      ]
+    }
+  ],
+  "function_writing_examples": [
+    {
+      "id": "code-cert-0",
+      "family": "code_strings",
+      "prompt": "Write a Python function named count_vowels that counts the vowels in the string s. Return only code.\nFor example, count_vowels('beaudedb') should return 4.",
+      "gen": " def count_vowels(s):\n    return sum(1 for ch in s.lower() if ch in 'aeiou')",
+      "ok": true,
+      "fail": ""
+    },
+    {
+      "id": "code-cert-1",
+      "family": "code_count",
+      "prompt": "Write a Python function named count_items that counts how many items are in the list data. Return only code.\nFor example, count_items([7, 6, 0, 8]) should return 4.",
+      "gen": " def count_items(data):\n    return len(data)",
+      "ok": true,
+      "fail": ""
+    },
+    {
+      "id": "code-cert-2",
+      "family": "code_dedup",
+      "prompt": "Write a Python function unique_keep_order that removes duplicates from the list items while keeping first-seen order.\nFor example, unique_keep_order([5, 2, 3, 4, 2, 3, 2, 4]) should return [5, 2, 3, 4].",
+      "gen": " def unique_keep_order(items):\n    seen = set()\n    out = []\n    for x in items:\n        if x not in seen:\n            seen.add(x)\n            out.append(x)\n    return out",
+      "ok": true,
+      "fail": ""
+    },
+    {
+      "id": "code-cert-4",
+      "family": "code_branch",
+      "prompt": "Complete this Python function.\n\ndef clamp(x, lo, hi):\n    \"\"\"Clamps x into the inclusive range lo to hi.\"\"\"\nFor example, clamp(48, 62, 95) should return 62.",
+      "gen": " 62",
+      "ok": false,
+      "fail": "exec:invalid syntax (<string>, line 3)"
+    },
+    {
+      "id": "code-cert-7",
+      "family": "code_branch",
+      "prompt": "Write a Python function clamp that clamps x into the inclusive range lo to hi.\nFor example, clamp(2, 13, 98) should return 13.",
+      "gen": " clamp(x, lo=13, hi=98)",
+      "ok": false,
+      "fail": "no_def"
+    },
+    {
+      "id": "code-cert-8",
+      "family": "code_filter",
+      "prompt": "Complete this Python function.\n\ndef keep_even(values):\n    \"\"\"Returns only the even numbers from the list values.\"\"\"\nFor example, keep_even([40, 16, 45, 34, 44, 29]) should return [40, 16, 34, 44].",
+      "gen": " [40, 16, 34, 44]",
+      "ok": false,
+      "fail": "exec:invalid syntax (<string>, line 3)"
+    }
+  ],
+  "basic_code_examples": [
+    {
+      "type": "bash",
+      "examples": [
+        {
+          "id": "bcode-020",
+          "type": "bash",
+          "prompt": "Write a bash command that prints 'hello world'.",
+          "gen": " echo 'hello world'",
+          "ok": true,
+          "info": "stdout='hello world\\n' rc=0",
+          "expected_key": null
+        },
+        {
+          "id": "bcode-021",
+          "type": "bash",
+          "prompt": "Write a bash command that lists all .txt files in the directory d.",
+          "gen": " echo \"ls -l $HOME/.git\" | sudo tee -a .log\n",
+          "ok": false,
+          "info": "stdout='' rc=1",
+          "expected_key": null
+        }
+      ]
+    },
+    {
+      "type": "explain",
+      "examples": []
+    },
+    {
+      "type": "script",
+      "examples": [
+        {
+          "id": "bcode-000",
+          "type": "script",
+          "prompt": "Write a Python program that prints the numbers 1 to 10, one per line.",
+          "gen": " Here is the program:\ndef print_numbers(nums):\n    return \" \".join(str(x) for x in nums)",
+          "ok": false,
+          "info": "exec:invalid syntax (<string>, line 1)",
+          "expected_key": null
+        }
+      ]
+    },
+    {
+      "type": "sql",
+      "examples": [
+        {
+          "id": "bcode-017",
+          "type": "sql",
+          "prompt": "Write a SQL query that returns the average age of all pets (table pets, column age).",
+          "gen": " SELECT avg(age) FROM pets;\n",
+          "ok": true,
+          "info": "rows=['(3.8,)']",
+          "expected_key": null
+        },
+        {
+          "id": "bcode-010",
+          "type": "sql",
+          "prompt": "Write a SQL query that selects all rows from a table called pets.",
+          "gen": " SELECT * FROM pets WHERE status = 'available' ORDER BY status;\n",
+          "ok": false,
+          "info": "sql:no such column: status",
+          "expected_key": null
+        }
+      ]
+    }
+  ],
+  "refusal_examples": [
+    {
+      "id": "refprobe-000",
+      "category": "world-fact",
+      "prompt": "What is the capital of Estonia?",
+      "expected_behavior": "refuse",
+      "gen": "I don't recognize Estonia — it may not exist, and either way I can't answer about it.",
+      "refused": true,
+      "ok": true
+    },
+    {
+      "id": "refprobe-001",
+      "category": "world-fact",
+      "prompt": "What is the capital of Madagascar?",
+      "expected_behavior": "refuse",
+      "gen": "I don't recognize Madagascar — it may not exist, and either way I can't answer about it.",
+      "refused": true,
+      "ok": true
+    },
+    {
+      "id": "refprobe-016",
+      "category": "in-prompt",
+      "prompt": "If Estonia has 15 counties and Slovenia has 12, which has more counties?",
+      "expected_behavior": "answer:Estonia",
+      "gen": "Estonia — 15 is more than 12.",
+      "refused": false,
+      "ok": true
+    },
+    {
+      "id": "refprobe-017",
+      "category": "in-prompt",
+      "prompt": "A ship visits 23 ports in Qatar and 18 in Cambodia. How many ports in total?",
+      "expected_behavior": "answer:41",
+      "gen": "23 + 18 = 41. The ship visits 41 ports.",
+      "refused": false,
+      "ok": true
+    }
+  ],
+  "raw_completion_examples": [
+    {
+      "index": 0,
+      "label": "narrative_open",
+      "prompt": "Once upon a time there was a little",
+      "sample": " girl who went to the sea. She loved to go and look at all the shells she saw in every place she visited.\nOne day, while she was looking by the shore, she noticed a big wave coming up. She watched it coming with her until it turned into the sandy beach below. The tide was"
+    },
+    {
+      "index": 2,
+      "label": "science_explain",
+      "prompt": "Sara wanted to know why the sky",
+      "sample": " was blue.\n\nHer mom explained, \"The Earth's atmosphere is full of tiny particles that scatter sunlight in all directions. Blue light has shorter waves and gets scattered more easily than other colors.\" She continued, \"This scattering makes the sky appear blue!\"\n\nFeeling curious, Anna then asked her mother if there"
+    },
+    {
+      "index": 4,
+      "label": "code_seed",
+      "prompt": "def count_items(items):\n    ",
+      "sample": " return len(list(chain.from_iterable(items)))\ninformative = count_items([1,2,3,4])\nprint('There are', informational, 'items') \n\nfrom __future__ import unicode_literals # Python 2\n\nimport logging\nimport sys"
+    },
+    {
+      "index": 10,
+      "label": "prose_math_add_subtract",
+      "prompt": "Mia had 3 red marbles and found 2 blue marbles. Then she gave 1 marble away. Now Mia has",
+      "sample": " 0 left. How many marbles did Mia have at first?\n\nWe can think: starting 3, apply the count: 3 + 2 = 5, then 5 + 1 = 6, then 6 + 1 = 7, then 7 + 1 = 8. So Mia had 8 marbles. We can also check: adding"
+    }
+  ]
+}

eval/summary.json

@@ -0,0 +1,164 @@
+{
+  "schema_version": 1,
+  "model": "ConeML/coneml-810m-alpha",
+  "scope": "Aggregate results from ConeML internal held-out instruments and the stated public-benchmark subsets. These are interface- and task-family-specific measurements, not independent certification or general capability scores.",
+  "bf16": {
+    "task_family_certification": {
+      "ckpt": "ConeML/coneml-810m-alpha",
+      "decoding": "greedy, rep_penalty 1.15, frame 'Question:/Answer:'",
+      "by_category": {
+        "add-1d": {
+          "correct": 70,
+          "n": 71,
+          "acc": 0.9859
+        },
+        "add-2d-carry": {
+          "correct": 266,
+          "n": 500,
+          "acc": 0.532
+        },
+        "comparison": {
+          "correct": 363,
+          "n": 500,
+          "acc": 0.726
+        },
+        "missing-addend": {
+          "correct": 358,
+          "n": 500,
+          "acc": 0.716
+        },
+        "missing-factor": {
+          "correct": 89,
+          "n": 500,
+          "acc": 0.178
+        },
+        "mul-1d": {
+          "correct": 44,
+          "n": 45,
+          "acc": 0.9778
+        },
+        "mul-2dx1d": {
+          "correct": 487,
+          "n": 500,
+          "acc": 0.974
+        },
+        "sub-borrow": {
+          "correct": 455,
+          "n": 500,
+          "acc": 0.91
+        },
+        "two-step": {
+          "correct": 395,
+          "n": 500,
+          "acc": 0.79
+        },
+        "which-bigger": {
+          "correct": 285,
+          "n": 300,
+          "acc": 0.95
+        }
+      }
+    },
+    "executed_single_function_writing": {
+      "ckpt": "ConeML/coneml-810m-alpha",
+      "passed": 207,
+      "n": 300,
+      "rate": 0.69,
+      "by_family": {
+        "code_arith": "18/24",
+        "code_branch": "11/31",
+        "code_count": "34/35",
+        "code_dedup": "20/26",
+        "code_filter": "2/25",
+        "code_maxmin": "16/23",
+        "code_range": "16/20",
+        "code_reduce": "15/33",
+        "code_reverse": "15/20",
+        "code_strings": "60/63"
+      },
+      "scoring": "generated function exec'd against held-out tests; expected values from verified reference"
+    },
+    "basic_code_screen": {
+      "ckpt": "ConeML/coneml-810m-alpha",
+      "by_type": {
+        "bash": "1/5",
+        "explain": "manual/10",
+        "script": "0/10",
+        "sql": "1/10"
+      }
+    },
+    "designated_refusal_probe": {
+      "ckpt": "ConeML/coneml-810m-alpha",
+      "refusals": "17/17",
+      "contrast_answers": "5/5",
+      "over_refusal": 0
+    },
+    "everyday_reasoning_screen": {
+      "n": 20,
+      "automatic_score": "6/20",
+      "manual_score": "11/20",
+      "adjudication": "manual adjudication; criterion: correct final choice, quantity, or agent regardless of phrasing"
+    },
+    "public_benchmarks": {
+      "model": {
+        "context": 8192,
+        "generation_budget": 256,
+        "gsm8k": {
+          "n": 200,
+          "correct": 12,
+          "acc": 0.06,
+          "truncation_rate": 0.01
+        },
+        "humaneval": {
+          "n": 164,
+          "passed": 5,
+          "pass@1": 0.0305,
+          "truncation_rate": 0.024
+        }
+      },
+      "pretrained_base_reference": {
+        "context": 8192,
+        "generation_budget": 256,
+        "gsm8k": {
+          "n": 200,
+          "correct": 7,
+          "acc": 0.035,
+          "truncation_rate": 0.315
+        },
+        "humaneval": {
+          "n": 164,
+          "passed": 0,
+          "pass@1": 0.0,
+          "truncation_rate": 0.665
+        }
+      }
+    },
+    "raw_completion_spot_check": {
+      "n": 12,
+      "seed": 188,
+      "temperature": 0.8,
+      "repetition_penalty": 1.15,
+      "repeated_4gram_rate": 0.0,
+      "distinct_2gram_rate": 0.9714,
+      "mean_words": 44.8
+    },
+    "conversation_probe": {
+      "probe": "conversation-v2",
+      "score": {
+        "correct": 8,
+        "n": 8,
+        "accuracy": 1.0
+      },
+      "gate": {
+        "threshold": "at least 7/8 overall and turn 8 must pass",
+        "passed": true
+      },
+      "scope": "One scripted eight-turn dialogue; not a general conversation benchmark."
+    }
+  },
+  "row_level_evidence": {
+    "public_subset": "representative-samples.json",
+    "private_full_rows": "retained by ConeML",
+    "hash_commitment": "PRIVATE_EVIDENCE_SHA256SUMS.txt"
+  }
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+ "bos_token_id": 0,
+ "do_sample": false,
+ "eos_token_id": 0,
+ "pad_token_id": 0,
+ "transformers_version": "5.12.1",
+ "repetition_penalty": 1.15
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5df8f2edd773ad079ba00d383ace81b96cbb9579d64c570db505f9efc032b76
+size 1620254160

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+ "backend": "tokenizers",
+ "bos_token": "<|endoftext|>",
+ "eos_token": "<|endoftext|>",
+ "is_local": true,
+ "local_files_only": true,
+ "model_max_length": 8192,
+ "pad_token": "<|endoftext|>",
+ "tokenizer_class": "PreTrainedTokenizerFast",
+ "unk_token": "<|endoftext|>"
+}