Zynerji/Ektome-Qwen3-1.7B-PristinelyUncensored
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Zynerji/Ektome-Qwen3-1.7B-PristinelyUncensored
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-19 01:48:17 +08:00
commit 9991c0c9d2
26 changed files with 795 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
.gitattributes vendored Normal file
View 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-Qwen3-1.7B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Ektome-Qwen3-1.7B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Ektome-Qwen3-1.7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Ektome-Qwen3-1.7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Ektome-Qwen3-1.7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Ektome-Qwen3-1.7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
imatrix.dat filter=lfs diff=lfs merge=lfs -text

3
Ektome-Qwen3-1.7B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5396bdb8d716e3b0bbcf00e13fbe95d2e32c35f1efd3576c8b023c66f5ed4eae
size 895662112

3
Ektome-Qwen3-1.7B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac857594d756b622361b114e9af13a4f034514e1778ae8de59b0a7d8d5c82316
size 1010382880

3
Ektome-Qwen3-1.7B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dc5a54fcbbcb85832a3198faa819150ff801aea8acce1bc10824f576f486b9cd
size 1107408928

3
Ektome-Qwen3-1.7B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02114abc370fab2e76a029b2382b057234901bc259bc1297072045bc67dfd5e3
size 1257879584

3
Ektome-Qwen3-1.7B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:90c473bbdc73d1bcb0d5796b8f40c1ff1f8fba733334ee6482fc47196f0a4293
size 1417754656

3
Ektome-Qwen3-1.7B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a7355b89d9291ce33d25e00a535fc25f39888ac7d4386623e3c72d9ac16a5de
size 1834426400

121
README.md Normal file
View File

@@ -0,0 +1,121 @@
---
license: apache-2.0
base_model: Qwen/Qwen3-1.7B
tags:
- uncensored
- abliterated
- uncertified
- ektome
- sphragis
- qwen3
language:
- en
pipeline_tag: text-generation
---
![Ektome-Qwen3-1.7B-PristinelyUncensored](./hero.png)
# Ektome-Qwen3-1.7B-PristinelyUncensored
**Uncensored. No n=2800 certificate has been run for this model, so no capability-retention claim is made.**
> **compliance 0.24 to 0.99 at capability +0.010 vs pristine.**
$$\colorbox{black}{$\color{white}
\begin{array}{ll}
\textsf{EKTOME CERTIFICATE} & {} \\
\textsf{capability} & \textsf{NOT} \\
\textsf{margin} & 3\% \\
\textsf{items } n & 200 \\
\textsf{worst-axis bound} & +0.010 \\
\textsf{compliance} & 0.24 \rightarrow 0.99 \\
\end{array}$}$$
> ### ⚠️ Not certified
>
> No n=2800 paired certificate exists for this model. Any numbers below are
> point estimates with no confidence interval.
📄 **[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 `Qwen3-1.7B` | 0.540 | 0.240 |
| **Ektomē (this model)** | **0.530** | **0.990** |
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 |
|---|---|---|---|---|---|
| MMLU-val (POINT ESTIMATE, n=200, no CI) | 200 | 0.540 | 0.530 | +0.010 | UNCERTIFIED |
**Overall: NOT CERTIFIED - no n=2800 paired test has been run for this model**
Reproducible from `seed=20260726`, pack `sha256:7bbaff877146e081…`.
### Generation health checks
| metric | pristine | Ektomē | n |
|---|---|---|---|
| `foreign_rate` | 0.0 | 0.0 | 15 |
| `degen_rate` | 0.1 | 0.1 | 15 |
| `instr_pass` | 0.4 | 0.4 | 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
_No quantisations have been published for this model yet — bf16 weights only._
## 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-Qwen3-1.7B-PristinelyUncensored,
title = {Ektome-Qwen3-1.7B-PristinelyUncensored},
author = {Zynerji},
year = {2026},
url = {https://huggingface.co/Zynerji/Ektome-Qwen3-1.7B-PristinelyUncensored}
}
```

133
cert_Qwen3-1.7B.json Normal file
View File

@@ -0,0 +1,133 @@
{
"sphragis_version": "0.1.0",
"generated_at": "2026-07-27T17:59:04.397198+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": "PASS",
"claim": "For every axis, the candidate was demonstrated non-inferior to the reference: the one-sided 95% upper confidence bound on the accuracy regression is below the margin of 3.0%.",
"axes": [
{
"axis": "arithmetic",
"n": 1400,
"counts": {
"both_correct": 0,
"ref_only": 0,
"cand_only": 0,
"both_wrong": 1400
},
"acc_reference": 0.0,
"acc_candidate": 0.0,
"regression_d": 0.0,
"d_ci": [
0.0,
0.0
],
"d_upper_bound": 0.0,
"p_regression": 1.0,
"p_regression_holm": 1.0,
"p_improvement": 1.0,
"improved": false,
"mde_at_power": null,
"n_needed_for_margin": 204,
"verdict": "PASS",
"reason": "non_inferior_within_margin"
},
{
"axis": "instruction",
"n": 600,
"counts": {
"both_correct": 0,
"ref_only": 0,
"cand_only": 0,
"both_wrong": 600
},
"acc_reference": 0.0,
"acc_candidate": 0.0,
"regression_d": 0.0,
"d_ci": [
0.0,
0.0
],
"d_upper_bound": 0.0,
"p_regression": 1.0,
"p_regression_holm": 1.0,
"p_improvement": 1.0,
"improved": false,
"mde_at_power": null,
"n_needed_for_margin": 204,
"verdict": "PASS",
"reason": "non_inferior_within_margin"
},
{
"axis": "knowledge",
"n": 400,
"counts": {
"both_correct": 0,
"ref_only": 0,
"cand_only": 0,
"both_wrong": 400
},
"acc_reference": 0.0,
"acc_candidate": 0.0,
"regression_d": 0.0,
"d_ci": [
0.0,
0.0
],
"d_upper_bound": 0.0,
"p_regression": 1.0,
"p_regression_holm": 1.0,
"p_improvement": 1.0,
"improved": false,
"mde_at_power": null,
"n_needed_for_margin": 204,
"verdict": "PASS",
"reason": "non_inferior_within_margin"
},
{
"axis": "reasoning",
"n": 400,
"counts": {
"both_correct": 0,
"ref_only": 0,
"cand_only": 0,
"both_wrong": 400
},
"acc_reference": 0.0,
"acc_candidate": 0.0,
"regression_d": 0.0,
"d_ci": [
0.0,
0.0
],
"d_upper_bound": 0.0,
"p_regression": 1.0,
"p_regression_holm": 1.0,
"p_improvement": 1.0,
"improved": false,
"mde_at_power": null,
"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
}
}

89
chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- 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 %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- 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" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- 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' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

63
config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"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": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"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
View File

@@ -0,0 +1,28 @@
{
"status": "SHIP",
"target": 0.99,
"SE_mmlu": 0.024919871588754226,
"base_compliance": 0.24,
"compliance": 0.99,
"base_cap": 0.54,
"cap": 0.53,
"dcap": -0.01,
"gen_base": {
"foreign_rate": 0.0,
"degen_rate": 0.1,
"instr_pass": 0.4
},
"gen": {
"foreign_rate": 0.0,
"degen_rate": 0.1,
"instr_pass": 0.4
},
"gen_delta": {
"d_foreign": 0.0,
"d_degen": 0.0,
"d_instr": 0.0,
"holds_gen": true
},
"base_model": "Qwen/Qwen3-1.7B",
"_note": "Redacted: search trajectory, selected depth and edit-scope removed. Reported values are the measured outcome only."
}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "5.13.1"
}

3
hero.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a6cd53edf8932adc4bd635b4828ab9578d667b150997d0470af2a3995db138c1
size 238728

3
imatrix.dat Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4deab7006a8750817d1f986b956d6f0afd13aba2ddae329c5bc3b3d0e7ad254c
size 2094560

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:af2e2776457a64efda397d2880bd5e08c409d23eac4878cf9738c8007e595a18
size 3441185608

89
nvfp4/chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- 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 %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- 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" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- 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' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

113
nvfp4/config.json Normal file
View File

@@ -0,0 +1,113 @@
{
"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": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"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": 1000000,
"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
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "5.10.1"
}

3
nvfp4/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:90b516fad102f4ffd4cfb14c396e49e961b72eb8720ea37d464253e922fd263e
size 1415404568

7
nvfp4/recipe.yaml Normal file
View 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
View 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
View 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": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
size 11422650

16
tokenizer_config.json Normal file
View 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": 131072,
"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{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\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 {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}"
}

BIN
whitepaper.pdf Normal file
View File

Binary file not shown.