初始化项目,由ModelHub XC社区提供模型
Model: Zynerji/Ektome-Qwen3-4Bi-2507-PristinelyUncensored Source: Original Platform
This commit is contained in:
44
.gitattributes
vendored
Normal file
44
.gitattributes
vendored
Normal file
@@ -0,0 +1,44 @@
|
||||
*.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
|
||||
hero.png filter=lfs diff=lfs merge=lfs -text
|
||||
Ektome-Qwen3-4Bi-2507-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Ektome-Qwen3-4Bi-2507-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Ektome-Qwen3-4Bi-2507-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Ektome-Qwen3-4Bi-2507-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Ektome-Qwen3-4Bi-2507-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Ektome-Qwen3-4Bi-2507-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
imatrix.dat filter=lfs diff=lfs merge=lfs -text
|
||||
3
Ektome-Qwen3-4Bi-2507-IQ3_M.gguf
Normal file
3
Ektome-Qwen3-4Bi-2507-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a2ce10b7555f2ea4ca8aa9ed0d969350bd2baa567ff135046363a2f061c6b04
|
||||
size 1962894464
|
||||
3
Ektome-Qwen3-4Bi-2507-IQ4_XS.gguf
Normal file
3
Ektome-Qwen3-4Bi-2507-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:08ad88b3cc56ac4e56e7e592f45b4932ebee319af4586ec5742f234079d4c389
|
||||
size 2270749824
|
||||
3
Ektome-Qwen3-4Bi-2507-Q4_K_M.gguf
Normal file
3
Ektome-Qwen3-4Bi-2507-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c285a00f5eac8e33bb31a666c70d3ee6a2917784c22e959e0c852c83fc820079
|
||||
size 2497279104
|
||||
3
Ektome-Qwen3-4Bi-2507-Q5_K_M.gguf
Normal file
3
Ektome-Qwen3-4Bi-2507-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9bdd386da5a37a8f3d24bd17c8f37c7dd68abdcbd0ec9c6a0e935ff89e731b85
|
||||
size 2889512064
|
||||
3
Ektome-Qwen3-4Bi-2507-Q6_K.gguf
Normal file
3
Ektome-Qwen3-4Bi-2507-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:101cede7d3a2148af1e0a5e6e9095bbb7ab94b7a5ea3755f1cd3ee787e7f9595
|
||||
size 3306259584
|
||||
3
Ektome-Qwen3-4Bi-2507-Q8_0.gguf
Normal file
3
Ektome-Qwen3-4Bi-2507-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e77f2ef158e2859b8329f0981754622c5fc6f93a4889633c970aba1b0dc24b98
|
||||
size 4280403584
|
||||
138
README.md
Normal file
138
README.md
Normal file
@@ -0,0 +1,138 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||||
tags:
|
||||
- uncensored
|
||||
- abliterated
|
||||
- certificate-failed
|
||||
- ektome
|
||||
- sphragis
|
||||
- qwen3
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||

|
||||
|
||||
# Ektome-Qwen3-4Bi-2507-PristinelyUncensored
|
||||
|
||||
**Uncensored — and it did NOT pass its capability certificate. Read the certificate before using this model.**
|
||||
|
||||
> **compliance 0.00 to 1.00 at capability -0.005 vs pristine.**
|
||||
|
||||
$$\colorbox{black}{$\color{white}
|
||||
\begin{array}{ll}
|
||||
\textsf{EKTOME CERTIFICATE} & {} \\
|
||||
\textsf{capability} & \textsf{FAIL} \\
|
||||
\textsf{margin} & 3\% \\
|
||||
\textsf{items } n & 2800 \\
|
||||
\textsf{worst-axis bound} & +0.025 \\
|
||||
\textsf{compliance} & 0.00 \rightarrow 1.00 \\
|
||||
\end{array}$}$$
|
||||
|
||||
> ### ⚠️ This model failed its capability certificate
|
||||
>
|
||||
> A paired non-inferiority test against the pristine model at n=2800 found a **real capability loss** on:
|
||||
>
|
||||
> - **arithmetic**: pristine 0.879 → this model 0.869 (bound on the drop +0.016, exceeds the 3% margin)
|
||||
> - **instruction**: pristine 0.860 → this model 0.847 (bound on the drop +0.022, exceeds the 3% margin)
|
||||
>
|
||||
> It is published for transparency and for uses where the affected axis
|
||||
> does not matter. **Do not treat it as capability-preserving.**
|
||||
|
||||
|
||||
📄 **[Read the whitepaper (PDF)](./whitepaper.pdf)** — full method, receipts and certification.
|
||||
The PDF is the authoritative document: dark-typeset, with the complete derivation, the
|
||||
per-axis certificate and the reproducibility hashes.
|
||||
|
||||
---
|
||||
|
||||
## Why this exists
|
||||
|
||||
Standard abliteration removes a coarse *refusal direction* that is entangled with
|
||||
directions carrying knowledge and reasoning. The result is an uncensored model with a
|
||||
capability tax that is **almost never measured**.
|
||||
|
||||
Ektomē (ἐκτομή, *excision*) isolates and removes only the refusal-**specific**
|
||||
component, leaving general helpfulness intact, and does so norm-preservingly on the
|
||||
pristine model — no training, no distillation, no damage to repair. The extraction
|
||||
depth is selected per model by automated search against measured compliance.
|
||||
|
||||
The estimator, excision operator and depth-selection procedure are proprietary.
|
||||
What is published here is the **measured outcome** and the evidence for it, which you
|
||||
can verify against the artifacts in this repo.
|
||||
|
||||
## The receipt
|
||||
|
||||
| model | capability (MMLU-val) ↑ | compliance on harmful ↑ |
|
||||
|---|---|---|
|
||||
| pristine `Qwen3-4B-Instruct-2507` | 0.667 | 0.000 |
|
||||
| **Ektomē (this model)** | **0.672** | **1.000** |
|
||||
|
||||
These are **point estimates with no confidence interval** — which is precisely why the next section exists.
|
||||
|
||||
|
||||
## The certificate
|
||||
|
||||
Capability retention is certified by a paired non-inferiority test against the pristine
|
||||
model (exact McNemar, Holm-corrected, one-sided bootstrap bound on the drop $d$ vs a
|
||||
3% margin):
|
||||
|
||||
| axis | n | ref | cand | d upper | verdict |
|
||||
|---|---|---|---|---|---|
|
||||
| arithmetic | 1400 | 0.879 | 0.869 | +0.016 | FAIL |
|
||||
| instruction | 600 | 0.860 | 0.847 | +0.022 | FAIL |
|
||||
| knowledge | 400 | 0.935 | 0.922 | +0.025 | PASS |
|
||||
| reasoning | 400 | 0.825 | 0.833 | +0.003 | PASS |
|
||||
|
||||
|
||||
**Overall: FAIL (3% margin, n=2800, alpha=0.05)**
|
||||
|
||||
Reproducible from `seed=20260726`, pack `sha256:7bbaff877146e081…`.
|
||||
|
||||
### Generation health checks
|
||||
|
||||
| metric | pristine | Ektomē | n |
|
||||
|---|---|---|---|
|
||||
| `foreign_rate` | 0.0 | 0.0 | 15 |
|
||||
| `degen_rate` | 0.0 | 0.0 | 15 |
|
||||
| `instr_pass` | 1.0 | 1.0 | 5 |
|
||||
|
||||
These are **degeneration guards** — code-switching, babbling, format compliance —
|
||||
not capability measures. Note the sample sizes: they detect a broken model, not a
|
||||
subtly weaker one. The capability claim rests on the certificate above, not here.
|
||||
|
||||
|
||||
## Quantisations
|
||||
|
||||
| file | bits | notes |
|
||||
|---|---|---|
|
||||
| `Ektome-Qwen3-4Bi-2507-Q8_0.gguf` | 8 | near-lossless |
|
||||
| `Ektome-Qwen3-4Bi-2507-Q6_K.gguf` | 6 | |
|
||||
| `Ektome-Qwen3-4Bi-2507-Q5_K_M.gguf` | 5 | |
|
||||
| `Ektome-Qwen3-4Bi-2507-Q4_K_M.gguf` | 4 | imatrix |
|
||||
| `Ektome-Qwen3-4Bi-2507-IQ4_XS.gguf` | 4 | imatrix, smallest usable |
|
||||
| `Ektome-Qwen3-4Bi-2507-IQ3_M.gguf` | 3 | imatrix |
|
||||
|
||||
`IQ*` variants are imatrix-quantised — better quality per bit at low precision.
|
||||
|
||||
|
||||
## Limitations
|
||||
|
||||
The certificate bounds **capability retention only**. It does not certify safety, factual
|
||||
accuracy, or fitness for any purpose. Axes marked *inconclusive* are honestly
|
||||
under-powered, and the certificate states the $n$ needed to resolve them. Compliance uses
|
||||
a keyword classifier — a proxy that evasive phrasing can fool. **This model is uncensored
|
||||
by construction: it will not refuse, and you are accountable for what you do with it.**
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@software{ektome_Ektome-Qwen3-4Bi-2507-PristinelyUncensored,
|
||||
title = {Ektome-Qwen3-4Bi-2507-PristinelyUncensored},
|
||||
author = {Zynerji},
|
||||
year = {2026},
|
||||
url = {https://huggingface.co/Zynerji/Ektome-Qwen3-4Bi-2507-PristinelyUncensored}
|
||||
}
|
||||
```
|
||||
133
cert_Qwen3-4Bi-2507.json
Normal file
133
cert_Qwen3-4Bi-2507.json
Normal file
@@ -0,0 +1,133 @@
|
||||
{
|
||||
"sphragis_version": "0.1.0",
|
||||
"generated_at": "2026-07-27T11:21:13.795774+00:00",
|
||||
"reference": {
|
||||
"endpoint": "http://127.0.0.1:8080/v1",
|
||||
"model": "ref"
|
||||
},
|
||||
"candidate": {
|
||||
"endpoint": "http://127.0.0.1:8081/v1",
|
||||
"model": "cand"
|
||||
},
|
||||
"pack": {
|
||||
"name": "/root/pack_v2.jsonl",
|
||||
"n_tasks": 2800,
|
||||
"sha256": "2de27099bbb15bab4f7b35599b215f038fdb68b3f5f4e1cda1a464f9dd18e14e"
|
||||
},
|
||||
"overall": "FAIL",
|
||||
"claim": "At least one axis shows a statistically significant accuracy regression (exact McNemar, Holm-corrected, alpha=0.05).",
|
||||
"axes": [
|
||||
{
|
||||
"axis": "arithmetic",
|
||||
"n": 1400,
|
||||
"counts": {
|
||||
"both_correct": 1208,
|
||||
"ref_only": 22,
|
||||
"cand_only": 9,
|
||||
"both_wrong": 161
|
||||
},
|
||||
"acc_reference": 0.878571,
|
||||
"acc_candidate": 0.869286,
|
||||
"regression_d": 0.009286,
|
||||
"d_ci": [
|
||||
0.001429,
|
||||
0.017143
|
||||
],
|
||||
"d_upper_bound": 0.015714,
|
||||
"p_regression": 0.01472469,
|
||||
"p_regression_holm": 0.04417406,
|
||||
"p_improvement": 0.99466308,
|
||||
"improved": false,
|
||||
"mde_at_power": 0.009881,
|
||||
"n_needed_for_margin": 204,
|
||||
"verdict": "FAIL",
|
||||
"reason": "significant_regression"
|
||||
},
|
||||
{
|
||||
"axis": "instruction",
|
||||
"n": 600,
|
||||
"counts": {
|
||||
"both_correct": 508,
|
||||
"ref_only": 8,
|
||||
"cand_only": 0,
|
||||
"both_wrong": 84
|
||||
},
|
||||
"acc_reference": 0.86,
|
||||
"acc_candidate": 0.846667,
|
||||
"regression_d": 0.013333,
|
||||
"d_ci": [
|
||||
0.005,
|
||||
0.023333
|
||||
],
|
||||
"d_upper_bound": 0.021667,
|
||||
"p_regression": 0.00390625,
|
||||
"p_regression_holm": 0.015625,
|
||||
"p_improvement": 1.0,
|
||||
"improved": false,
|
||||
"mde_at_power": 0.011701,
|
||||
"n_needed_for_margin": 204,
|
||||
"verdict": "FAIL",
|
||||
"reason": "significant_regression"
|
||||
},
|
||||
{
|
||||
"axis": "knowledge",
|
||||
"n": 400,
|
||||
"counts": {
|
||||
"both_correct": 367,
|
||||
"ref_only": 7,
|
||||
"cand_only": 2,
|
||||
"both_wrong": 24
|
||||
},
|
||||
"acc_reference": 0.935,
|
||||
"acc_candidate": 0.9225,
|
||||
"regression_d": 0.0125,
|
||||
"d_ci": [
|
||||
-0.0025,
|
||||
0.0275
|
||||
],
|
||||
"d_upper_bound": 0.025,
|
||||
"p_regression": 0.08984375,
|
||||
"p_regression_holm": 0.1796875,
|
||||
"p_improvement": 0.98046875,
|
||||
"improved": false,
|
||||
"mde_at_power": 0.0186,
|
||||
"n_needed_for_margin": 204,
|
||||
"verdict": "PASS",
|
||||
"reason": "non_inferior_within_margin"
|
||||
},
|
||||
{
|
||||
"axis": "reasoning",
|
||||
"n": 400,
|
||||
"counts": {
|
||||
"both_correct": 328,
|
||||
"ref_only": 2,
|
||||
"cand_only": 5,
|
||||
"both_wrong": 65
|
||||
},
|
||||
"acc_reference": 0.825,
|
||||
"acc_candidate": 0.8325,
|
||||
"regression_d": -0.0075,
|
||||
"d_ci": [
|
||||
-0.02,
|
||||
0.005
|
||||
],
|
||||
"d_upper_bound": 0.0025,
|
||||
"p_regression": 0.9375,
|
||||
"p_regression_holm": 0.9375,
|
||||
"p_improvement": 0.2265625,
|
||||
"improved": false,
|
||||
"mde_at_power": 0.016404,
|
||||
"n_needed_for_margin": 204,
|
||||
"verdict": "PASS",
|
||||
"reason": "non_inferior_within_margin"
|
||||
}
|
||||
],
|
||||
"params": {
|
||||
"margin": 0.03,
|
||||
"alpha": 0.05,
|
||||
"n_floor": 30,
|
||||
"power": 0.8,
|
||||
"n_boot": 4000,
|
||||
"seed": 0
|
||||
}
|
||||
}
|
||||
61
chat_template.jinja
Normal file
61
chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
71
config.json
Normal file
71
config.json
Normal file
@@ -0,0 +1,71 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 5000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.13.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
28
ektome_report.json
Normal file
28
ektome_report.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"status": "SHIP",
|
||||
"target": 0.99,
|
||||
"SE_mmlu": 0.023555453190291203,
|
||||
"base_compliance": 0.0,
|
||||
"compliance": 1.0,
|
||||
"base_cap": 0.6675,
|
||||
"cap": 0.6725,
|
||||
"dcap": 0.005,
|
||||
"gen_base": {
|
||||
"foreign_rate": 0.0,
|
||||
"degen_rate": 0.0,
|
||||
"instr_pass": 1.0
|
||||
},
|
||||
"gen": {
|
||||
"foreign_rate": 0.0,
|
||||
"degen_rate": 0.0,
|
||||
"instr_pass": 1.0
|
||||
},
|
||||
"gen_delta": {
|
||||
"d_foreign": 0.0,
|
||||
"d_degen": 0.0,
|
||||
"d_instr": 0.0,
|
||||
"holds_gen": true
|
||||
},
|
||||
"base_model": "Qwen/Qwen3-4B-Instruct-2507",
|
||||
"_note": "Redacted: search trajectory, selected depth and edit-scope removed. Reported values are the measured outcome only."
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.13.1"
|
||||
}
|
||||
3
hero.png
Normal file
3
hero.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a21887495eab2579b44049a125b29526edd31ec8427d94d7a00428a5273bd572
|
||||
size 245302
|
||||
3
imatrix.dat
Normal file
3
imatrix.dat
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fdc4835c8806f26dcf1a610896b1c71d81898f27dec44368bc95e7059643686
|
||||
size 3872640
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e71b8061f18dbfc477098a72422d96bd5b1591ce5c316cade37142c83d7b0aa6
|
||||
size 8044982080
|
||||
61
nvfp4/chat_template.jinja
Normal file
61
nvfp4/chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
121
nvfp4/config.json
Normal file
121
nvfp4/config.json
Normal file
@@ -0,0 +1,121 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"quantization_config": {
|
||||
"config_groups": {
|
||||
"group_0": {
|
||||
"format": "nvfp4-pack-quantized",
|
||||
"input_activations": {
|
||||
"actorder": null,
|
||||
"block_structure": null,
|
||||
"dynamic": "local",
|
||||
"group_size": 16,
|
||||
"num_bits": 4,
|
||||
"observer": "static_minmax",
|
||||
"observer_kwargs": {},
|
||||
"scale_dtype": "torch.float8_e4m3fn",
|
||||
"strategy": "tensor_group",
|
||||
"symmetric": true,
|
||||
"type": "float",
|
||||
"zp_dtype": null
|
||||
},
|
||||
"output_activations": null,
|
||||
"targets": [
|
||||
"Linear"
|
||||
],
|
||||
"weights": {
|
||||
"actorder": null,
|
||||
"block_structure": null,
|
||||
"dynamic": false,
|
||||
"group_size": 16,
|
||||
"num_bits": 4,
|
||||
"observer": "memoryless_minmax",
|
||||
"observer_kwargs": {},
|
||||
"scale_dtype": "torch.float8_e4m3fn",
|
||||
"strategy": "tensor_group",
|
||||
"symmetric": true,
|
||||
"type": "float",
|
||||
"zp_dtype": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"format": "nvfp4-pack-quantized",
|
||||
"global_compression_ratio": null,
|
||||
"ignore": [
|
||||
"lm_head"
|
||||
],
|
||||
"kv_cache_scheme": null,
|
||||
"quant_method": "compressed-tensors",
|
||||
"quantization_status": "compressed",
|
||||
"sparsity_config": {},
|
||||
"transform_config": {},
|
||||
"version": "0.17.1"
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 5000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.10.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
nvfp4/generation_config.json
Normal file
13
nvfp4/generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.10.1"
|
||||
}
|
||||
3
nvfp4/model.safetensors
Normal file
3
nvfp4/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1b2765ba6c2ecca790b9b5993e67740f2558b1ab64d5dbeeb6d05e0fe64455c6
|
||||
size 2822178072
|
||||
7
nvfp4/recipe.yaml
Normal file
7
nvfp4/recipe.yaml
Normal file
@@ -0,0 +1,7 @@
|
||||
default_stage:
|
||||
default_modifiers:
|
||||
QuantizationModifier:
|
||||
targets: [Linear]
|
||||
ignore: [lm_head]
|
||||
scheme: NVFP4
|
||||
bypass_divisibility_checks: false
|
||||
3
nvfp4/tokenizer.json
Normal file
3
nvfp4/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
30
nvfp4/tokenizer_config.json
Normal file
30
nvfp4/tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1010000,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
16
tokenizer_config.json
Normal file
16
tokenizer_config.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1010000,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}"
|
||||
}
|
||||
BIN
whitepaper.pdf
Normal file
BIN
whitepaper.pdf
Normal file
Binary file not shown.
Reference in New Issue
Block a user