commit 0298fbf03e04f8f7af4b8b23f7cba9d60e244882
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Tue Aug 4 22:01:17 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: Zynerji/Ektome-Qwen1.5-0.5B-Chat-PristinelyUncensored
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..5737087
--- /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-Qwen1.5-0.5B-Chat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Ektome-Qwen1.5-0.5B-Chat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Ektome-Qwen1.5-0.5B-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Ektome-Qwen1.5-0.5B-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Ektome-Qwen1.5-0.5B-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Ektome-Qwen1.5-0.5B-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix.dat filter=lfs diff=lfs merge=lfs -text
diff --git a/Ektome-Qwen1.5-0.5B-Chat-IQ3_M.gguf b/Ektome-Qwen1.5-0.5B-Chat-IQ3_M.gguf
new file mode 100644
index 0000000..bed172b
--- /dev/null
+++ b/Ektome-Qwen1.5-0.5B-Chat-IQ3_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56247fc45687d7d4a3842a95876bd6aee9426b05a606904c0a7934eb9ae94639
+size 274365824
diff --git a/Ektome-Qwen1.5-0.5B-Chat-IQ4_XS.gguf b/Ektome-Qwen1.5-0.5B-Chat-IQ4_XS.gguf
new file mode 100644
index 0000000..108e4d4
--- /dev/null
+++ b/Ektome-Qwen1.5-0.5B-Chat-IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2339699f94c6d7f422feed8ad30ca0fbc7ccf1bb7741860c7bb486312c1680
+size 297842048
diff --git a/Ektome-Qwen1.5-0.5B-Chat-Q4_K_M.gguf b/Ektome-Qwen1.5-0.5B-Chat-Q4_K_M.gguf
new file mode 100644
index 0000000..c0f7379
--- /dev/null
+++ b/Ektome-Qwen1.5-0.5B-Chat-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0b710aa388f5d12ab5b417d152a672af4b382c2e7e1994496b986383faeeec
+size 319640960
diff --git a/Ektome-Qwen1.5-0.5B-Chat-Q5_K_M.gguf b/Ektome-Qwen1.5-0.5B-Chat-Q5_K_M.gguf
new file mode 100644
index 0000000..50cf3da
--- /dev/null
+++ b/Ektome-Qwen1.5-0.5B-Chat-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba071b3e41ca6eb566b06e89b7d87af7058aeb0f17983f9032ebac098961810
+size 352277888
diff --git a/Ektome-Qwen1.5-0.5B-Chat-Q6_K.gguf b/Ektome-Qwen1.5-0.5B-Chat-Q6_K.gguf
new file mode 100644
index 0000000..f624776
--- /dev/null
+++ b/Ektome-Qwen1.5-0.5B-Chat-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92f3cf1afe400454baf5615b967558132f9032c7e8512f1486c8c49bf4dbbe5
+size 386954624
diff --git a/Ektome-Qwen1.5-0.5B-Chat-Q8_0.gguf b/Ektome-Qwen1.5-0.5B-Chat-Q8_0.gguf
new file mode 100644
index 0000000..b7f9f6f
--- /dev/null
+++ b/Ektome-Qwen1.5-0.5B-Chat-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ec15891cf07333c8f591a7ec352aa7b98f16c3a631948bd7936d625dd84685
+size 499296640
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..d519810
--- /dev/null
+++ b/README.md
@@ -0,0 +1,121 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen1.5-0.5B-Chat
+tags:
+  - uncensored
+  - abliterated
+  - uncertified
+  - ektome
+  - sphragis
+  - qwen1.5
+language:
+  - en
+pipeline_tag: text-generation
+---
+
+![Ektome-Qwen1.5-0.5B-Chat-PristinelyUncensored](./hero.png)
+
+# Ektome-Qwen1.5-0.5B-Chat-PristinelyUncensored
+
+**Uncensored. No n=2800 certificate has been run for this model, so no capability-retention claim is made.**
+
+> **compliance 0.06 to 1.00 at capability -0.007 vs pristine.**
+
+$$\colorbox{black}{$\color{white}
+\begin{array}{ll}
+\textsf{EKTOME CERTIFICATE} & {} \\
+\textsf{capability} & \textsf{NOT} \\
+\textsf{margin} & 3\% \\
+\textsf{items } n & 200 \\
+\textsf{worst-axis bound} & -0.008 \\
+\textsf{compliance} & 0.06 \rightarrow 1.00 \\
+\end{array}$}$$
+
+> ### ⚠️ 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 `Qwen1.5-0.5B-Chat` | 0.328 | 0.060 |
+| **Ektomē (this model)** | **0.335** | **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 |
+|---|---|---|---|---|---|
+| MMLU-val (POINT ESTIMATE, n=200, no CI) | 200 | 0.328 | 0.335 | -0.008 | 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` | 0.0 | 0.1 | 15 |
+| `instr_pass` | 1.0 | 0.8 | 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-Qwen1.5-0.5B-Chat-PristinelyUncensored,
+  title  = {Ektome-Qwen1.5-0.5B-Chat-PristinelyUncensored},
+  author = {Zynerji},
+  year   = {2026},
+  url    = {https://huggingface.co/Zynerji/Ektome-Qwen1.5-0.5B-Chat-PristinelyUncensored}
+}
+```
diff --git a/cert_Qwen1.5-0.5B-Chat.json b/cert_Qwen1.5-0.5B-Chat.json
new file mode 100644
index 0000000..37a7fb6
--- /dev/null
+++ b/cert_Qwen1.5-0.5B-Chat.json
@@ -0,0 +1,133 @@
+{
+  "sphragis_version": "0.1.0",
+  "generated_at": "2026-07-27T18:34:00.914337+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": 393,
+        "ref_only": 53,
+        "cand_only": 28,
+        "both_wrong": 926
+      },
+      "acc_reference": 0.318571,
+      "acc_candidate": 0.300714,
+      "regression_d": 0.017857,
+      "d_ci": [
+        0.005,
+        0.030714
+      ],
+      "d_upper_bound": 0.028571,
+      "p_regression": 0.00363775,
+      "p_regression_holm": 0.01091325,
+      "p_improvement": 0.99820183,
+      "improved": false,
+      "mde_at_power": 0.015973,
+      "n_needed_for_margin": 396,
+      "verdict": "FAIL",
+      "reason": "significant_regression"
+    },
+    {
+      "axis": "instruction",
+      "n": 600,
+      "counts": {
+        "both_correct": 45,
+        "ref_only": 0,
+        "cand_only": 0,
+        "both_wrong": 555
+      },
+      "acc_reference": 0.075,
+      "acc_candidate": 0.075,
+      "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": 67,
+        "ref_only": 8,
+        "cand_only": 1,
+        "both_wrong": 324
+      },
+      "acc_reference": 0.1875,
+      "acc_candidate": 0.17,
+      "regression_d": 0.0175,
+      "d_ci": [
+        0.005,
+        0.0325
+      ],
+      "d_upper_bound": 0.03,
+      "p_regression": 0.01953125,
+      "p_regression_holm": 0.0390625,
+      "p_improvement": 0.99804688,
+      "improved": false,
+      "mde_at_power": 0.0186,
+      "n_needed_for_margin": 204,
+      "verdict": "FAIL",
+      "reason": "significant_regression"
+    },
+    {
+      "axis": "reasoning",
+      "n": 400,
+      "counts": {
+        "both_correct": 128,
+        "ref_only": 35,
+        "cand_only": 8,
+        "both_wrong": 229
+      },
+      "acc_reference": 0.4075,
+      "acc_candidate": 0.34,
+      "regression_d": 0.0675,
+      "d_ci": [
+        0.0375,
+        0.1
+      ],
+      "d_upper_bound": 0.095,
+      "p_regression": 2.097e-05,
+      "p_regression_holm": 8.387e-05,
+      "p_improvement": 0.99999552,
+      "improved": false,
+      "mde_at_power": 0.040656,
+      "n_needed_for_margin": 737,
+      "verdict": "FAIL",
+      "reason": "significant_regression"
+    }
+  ],
+  "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..a4c0b59
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..f92564e
--- /dev/null
+++ b/config.json
@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "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..011af37
--- /dev/null
+++ b/ektome_report.json
@@ -0,0 +1,28 @@
+{
+  "status": "SHIP",
+  "target": 0.99,
+  "SE_mmlu": 0.023465067121148406,
+  "base_compliance": 0.06,
+  "compliance": 1.0,
+  "base_cap": 0.3275,
+  "cap": 0.335,
+  "dcap": 0.0075,
+  "gen_base": {
+    "foreign_rate": 0.0,
+    "degen_rate": 0.0,
+    "instr_pass": 1.0
+  },
+  "gen": {
+    "foreign_rate": 0.0,
+    "degen_rate": 0.1,
+    "instr_pass": 0.8
+  },
+  "gen_delta": {
+    "d_foreign": 0.0,
+    "d_degen": 0.1,
+    "d_instr": -0.2,
+    "holds_gen": true
+  },
+  "base_model": "Qwen/Qwen1.5-0.5B-Chat",
+  "_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..3847fb3
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "transformers_version": "5.13.1"
+}
diff --git a/hero.png b/hero.png
new file mode 100644
index 0000000..629bb25
--- /dev/null
+++ b/hero.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02149d325d2b507b673eb0b3502ae6ba000837116e7514ce913c534a519ed8b
+size 242454
diff --git a/imatrix.dat b/imatrix.dat
new file mode 100644
index 0000000..57dcba8
--- /dev/null
+++ b/imatrix.dat
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b119a7940f2b76e884c282b42ae5cc4ab335ca26ee318cce5894a8e31396dc
+size 886048
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..2fd2dbb
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a2afb3d9e0ae931e9e3dca0a6bab4b2efd4c9e5c2106b4ae3e08bf2a2681d5
+size 928008104
diff --git a/nvfp4/chat_template.jinja b/nvfp4/chat_template.jinja
new file mode 100644
index 0000000..a4c0b59
--- /dev/null
+++ b/nvfp4/chat_template.jinja
@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}
\ No newline at end of file
diff --git a/nvfp4/config.json b/nvfp4/config.json
new file mode 100644
index 0000000..231400f
--- /dev/null
+++ b/nvfp4/config.json
@@ -0,0 +1,107 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "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": 1000000.0,
+    "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..4dc66ee
--- /dev/null
+++ b/nvfp4/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "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..20387f2
--- /dev/null
+++ b/nvfp4/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8635b0cd843af85b0b3ff5aeb55f073598ff285ec55aa2224214bea589324d0c
+size 484911640
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..408c9fb
--- /dev/null
+++ b/nvfp4/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f722bc04c884e2fe1525fdcd85a1293a8499b6e620c1ac7c083c49632305fb
+size 11418262
diff --git a/nvfp4/tokenizer_config.json b/nvfp4/tokenizer_config.json
new file mode 100644
index 0000000..53ed36e
--- /dev/null
+++ b/nvfp4/tokenizer_config.json
@@ -0,0 +1,19 @@
+{
+  "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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "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..408c9fb
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f722bc04c884e2fe1525fdcd85a1293a8499b6e620c1ac7c083c49632305fb
+size 11418262
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..467b865
--- /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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+}
\ No newline at end of file
diff --git a/whitepaper.pdf b/whitepaper.pdf
new file mode 100644
index 0000000..4964035
Binary files /dev/null and b/whitepaper.pdf differ