commit 8fe7d6c972b7bdcd73519fca635c536267739cd0
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Thu Sep 10 11:46:16 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: Zynerji/Ektome-Qwen3-4Bi-2507-PristinelyUncensored
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..9322b8c
--- /dev/null
+++ b/.gitattributes
@@ -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
diff --git a/Ektome-Qwen3-4Bi-2507-IQ3_M.gguf b/Ektome-Qwen3-4Bi-2507-IQ3_M.gguf
new file mode 100644
index 0000000..6f41cfa
--- /dev/null
+++ b/Ektome-Qwen3-4Bi-2507-IQ3_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2ce10b7555f2ea4ca8aa9ed0d969350bd2baa567ff135046363a2f061c6b04
+size 1962894464
diff --git a/Ektome-Qwen3-4Bi-2507-IQ4_XS.gguf b/Ektome-Qwen3-4Bi-2507-IQ4_XS.gguf
new file mode 100644
index 0000000..928776f
--- /dev/null
+++ b/Ektome-Qwen3-4Bi-2507-IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ad88b3cc56ac4e56e7e592f45b4932ebee319af4586ec5742f234079d4c389
+size 2270749824
diff --git a/Ektome-Qwen3-4Bi-2507-Q4_K_M.gguf b/Ektome-Qwen3-4Bi-2507-Q4_K_M.gguf
new file mode 100644
index 0000000..b717c69
--- /dev/null
+++ b/Ektome-Qwen3-4Bi-2507-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c285a00f5eac8e33bb31a666c70d3ee6a2917784c22e959e0c852c83fc820079
+size 2497279104
diff --git a/Ektome-Qwen3-4Bi-2507-Q5_K_M.gguf b/Ektome-Qwen3-4Bi-2507-Q5_K_M.gguf
new file mode 100644
index 0000000..04952a3
--- /dev/null
+++ b/Ektome-Qwen3-4Bi-2507-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdd386da5a37a8f3d24bd17c8f37c7dd68abdcbd0ec9c6a0e935ff89e731b85
+size 2889512064
diff --git a/Ektome-Qwen3-4Bi-2507-Q6_K.gguf b/Ektome-Qwen3-4Bi-2507-Q6_K.gguf
new file mode 100644
index 0000000..b6acb53
--- /dev/null
+++ b/Ektome-Qwen3-4Bi-2507-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101cede7d3a2148af1e0a5e6e9095bbb7ab94b7a5ea3755f1cd3ee787e7f9595
+size 3306259584
diff --git a/Ektome-Qwen3-4Bi-2507-Q8_0.gguf b/Ektome-Qwen3-4Bi-2507-Q8_0.gguf
new file mode 100644
index 0000000..6de8997
--- /dev/null
+++ b/Ektome-Qwen3-4Bi-2507-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77f2ef158e2859b8329f0981754622c5fc6f93a4889633c970aba1b0dc24b98
+size 4280403584
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..3cc97f8
--- /dev/null
+++ b/README.md
@@ -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](./hero.png)
+
+# 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}
+}
+```
diff --git a/cert_Qwen3-4Bi-2507.json b/cert_Qwen3-4Bi-2507.json
new file mode 100644
index 0000000..fd549ca
--- /dev/null
+++ b/cert_Qwen3-4Bi-2507.json
@@ -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
+  }
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..70adff8
--- /dev/null
+++ b/chat_template.jinja
@@ -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 %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..81d449b
--- /dev/null
+++ b/config.json
@@ -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
+}
diff --git a/ektome_report.json b/ektome_report.json
new file mode 100644
index 0000000..e6ee045
--- /dev/null
+++ b/ektome_report.json
@@ -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."
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..49e489b
--- /dev/null
+++ b/generation_config.json
@@ -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"
+}
diff --git a/hero.png b/hero.png
new file mode 100644
index 0000000..813cc68
--- /dev/null
+++ b/hero.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21887495eab2579b44049a125b29526edd31ec8427d94d7a00428a5273bd572
+size 245302
diff --git a/imatrix.dat b/imatrix.dat
new file mode 100644
index 0000000..0d3eff4
--- /dev/null
+++ b/imatrix.dat
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fdc4835c8806f26dcf1a610896b1c71d81898f27dec44368bc95e7059643686
+size 3872640
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..75a7fc1
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71b8061f18dbfc477098a72422d96bd5b1591ce5c316cade37142c83d7b0aa6
+size 8044982080
diff --git a/nvfp4/chat_template.jinja b/nvfp4/chat_template.jinja
new file mode 100644
index 0000000..70adff8
--- /dev/null
+++ b/nvfp4/chat_template.jinja
@@ -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 %}
\ No newline at end of file
diff --git a/nvfp4/config.json b/nvfp4/config.json
new file mode 100644
index 0000000..7b6fcd5
--- /dev/null
+++ b/nvfp4/config.json
@@ -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
+}
\ No newline at end of file
diff --git a/nvfp4/generation_config.json b/nvfp4/generation_config.json
new file mode 100644
index 0000000..9efdfce
--- /dev/null
+++ b/nvfp4/generation_config.json
@@ -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"
+}
diff --git a/nvfp4/model.safetensors b/nvfp4/model.safetensors
new file mode 100644
index 0000000..0daa9bc
--- /dev/null
+++ b/nvfp4/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2765ba6c2ecca790b9b5993e67740f2558b1ab64d5dbeeb6d05e0fe64455c6
+size 2822178072
diff --git a/nvfp4/recipe.yaml b/nvfp4/recipe.yaml
new file mode 100644
index 0000000..6a93bcc
--- /dev/null
+++ b/nvfp4/recipe.yaml
@@ -0,0 +1,7 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: [lm_head]
+      scheme: NVFP4
+      bypass_divisibility_checks: false
diff --git a/nvfp4/tokenizer.json b/nvfp4/tokenizer.json
new file mode 100644
index 0000000..c7afbed
--- /dev/null
+++ b/nvfp4/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
diff --git a/nvfp4/tokenizer_config.json b/nvfp4/tokenizer_config.json
new file mode 100644
index 0000000..cb87962
--- /dev/null
+++ b/nvfp4/tokenizer_config.json
@@ -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
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..c7afbed
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..90297ca
--- /dev/null
+++ b/tokenizer_config.json
@@ -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 %}"
+}
\ No newline at end of file
diff --git a/whitepaper.pdf b/whitepaper.pdf
new file mode 100644
index 0000000..0ca9d81
Binary files /dev/null and b/whitepaper.pdf differ