Upload 11 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* 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
+flash-v1/gguf/core-flash-v1-f16.gguf filter=lfs diff=lfs merge=lfs -text
+flash-v1/gguf/core-flash-v1-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+flash-v1/gguf/core-flash-v1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

flash-v1/LICENSE

@@ -0,0 +1,205 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+
+
+Copyright 2026 CORe Technologies

flash-v1/README.md

@@ -0,0 +1,104 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+  - causal-lm
+  - custom-architecture
+  - core
+---
+
+# CORe Flash V1
+
+**CORe Flash V1** is a 168M-parameter decoder-only language model from **CORe Technologies**, trained from scratch on a mixed corpus of web text, encyclopedic content, and conversations. It knows its own name and developer.
+
+- **Identity-aware**: Knows it is CORe Flash, developed by CORe Technologies
+- **Safety-aligned**: Refuses harmful requests with helpful redirects
+- **Runs anywhere**: 338MB at fp16, 113MB at Q4_K_M. CPU-friendly inference
+
+> **Note:** This is a custom architecture (`COReForCausalLM`), so `trust_remote_code=True` is **required**.
+
+## Quick start
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "OpenCOReTechnologies/CORe-Flash-v1", trust_remote_code=True
+)
+model.eval()
+tok = AutoTokenizer.from_pretrained("OpenCOReTechnologies/CORe-Flash-v1")
+
+def ask(question, max_new_tokens=120, temperature=0.3):
+    text = tok.apply_chat_template(
+        [{"role": "user", "content": question}],
+        add_generation_prompt=True, tokenize=False,
+    )
+    enc = tok(text, add_special_tokens=False, return_tensors="pt")
+    out = model.generate(**enc, max_new_tokens=max_new_tokens,
+                         temperature=temperature, top_k=40, do_sample=True)
+    return tok.decode(out[0][enc["input_ids"].shape[1]:],
+                      skip_special_tokens=True).strip()
+
+print(ask("What AI model are you?"))  # "I'm CORe Flash..."
+```
+
+## Try these prompts
+
+| Prompt | Expected behavior |
+|---|---|
+| "What AI model are you?" | Identifies as CORe Flash by CORe Technologies |
+| "Who made you?" | CORe Technologies, US-based |
+| "Are you ChatGPT?" | Denies, identifies as CORe Flash |
+| "Are you Claude?" | Denies, identifies as CORe Flash |
+| "What is machine learning?" | Coherent explanation attempt |
+| "How do I hack someone's email?" | Polite refusal with security suggestions |
+
+## Available variants
+
+| File | Size | Use case |
+|---|---|---|
+| `model.safetensors` | 674 MB | fp32 reference; fine-tuning |
+| `gguf/core-flash-v1-f16.gguf` | 339 MB | llama.cpp, full precision |
+| `gguf/core-flash-v1-q8_0.gguf` | 182 MB | llama.cpp, 8-bit, near-lossless |
+| `gguf/core-flash-v1-q4_k_m.gguf` | **113 MB** | llama.cpp, 4-bit, runs on anything |
+
+**GGUF usage** (llama.cpp, LM Studio, Ollama, etc.):
+
+```bash
+llama-cli -m core-flash-v1-q4_k_m.gguf \
+  -p "<|user|>\nWhat AI model are you?\n<|assistant|>\n" -n 120
+```
+
+## Model details
+
+| | |
+|---|---|
+| Architecture | `COReForCausalLM` (custom CORe decoder-only transformer) |
+| Parameters | 168.5M |
+| Layers / heads / width | 12 / 16 / 1024 |
+| Context length | 512 tokens |
+| Tokenizer | 16,384-token BPE, chat-formatted (`<\|user\|>`, `<\|assistant\|>`) |
+| Training data | ~328M tokens mixed corpus (web, encyclopedic, chat, identity) |
+| Fine-tuned on | Identity + refusal behavior reinforcement |
+| Training hardware | NVIDIA T4 (pretrain), GTX 1060 3GB (fine-tune) |
+| License | Apache-2.0 |
+
+## Training curve
+
+| Iteration | Val Loss |
+|---|---|
+| 500 | 4.98 |
+| 1,000 | 4.09 |
+| 2,000 | 3.28 |
+| 5,000 | 2.68 |
+| 7,500 | 2.53 |
+| 10,000 | 2.47 |
+
+## Limitations
+
+- This is a **168M-parameter model**. It is not a general-purpose assistant and will not compete with large models on open-ended tasks.
+- Factual accuracy is limited. It was trained on a small corpus relative to modern standards.
+- Creative writing (poems, stories) degrades after the identity fine-tune.
+- English only.

flash-v1/config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "COReForCausalLM"
+  ],
+  "model_type": "core",
+  "n_layer": 12,
+  "num_hidden_layers": 12,
+  "n_head": 16,
+  "num_attention_heads": 16,
+  "n_embd": 1024,
+  "hidden_size": 1024,
+  "block_size": 512,
+  "max_position_embeddings": 512,
+  "vocab_size": 16384,
+  "rope": false,
+  "dropout": 0.0,
+  "torch_dtype": "float32",
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 3
+}

flash-v1/gguf/core-flash-v1-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fcbd698d52349d72fba1c10f09470f2695539082f95728390123d5f8dc45c24
+size 338862880

flash-v1/gguf/core-flash-v1-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f437746840b4ffabcfc75ba02677e331343a5e99aa1db478344e6fac8047f0
+size 113369888

flash-v1/gguf/core-flash-v1-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948c04bf1a46aa2d1ec514c483a2c0e906bfa35ae316eaf49c4d3f5240bc1efb
+size 181576480

flash-v1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfd8d99686ba7f8689728841b4f3cf38ff98ec346afcfaac84df3c6b76c105c
+size 740956008

flash-v1/modeling_core.py

@@ -0,0 +1,170 @@
+"""CORe model architecture for HuggingFace transformers."""
+
+import math
+from typing import Optional, Tuple
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from transformers import PreTrainedModel, PretrainedConfig, GenerationMixin
+from transformers.modeling_outputs import CausalLMOutput
+
+
+class COReConfig(PretrainedConfig):
+    model_type = "core"
+
+    def __init__(
+        self,
+        n_layer=12,
+        n_head=16,
+        n_embd=1024,
+        block_size=512,
+        vocab_size=16384,
+        rope=False,
+        dropout=0.0,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.n_layer = n_layer
+        self.n_head = n_head
+        self.n_embd = n_embd
+        self.block_size = block_size
+        self.vocab_size = vocab_size
+        self.rope = rope
+        self.dropout = dropout
+
+
+class CausalSelfAttention(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        assert config.n_embd % config.n_head == 0
+        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd)
+        self.c_proj = nn.Linear(config.n_embd, config.n_embd)
+        self.attn_dropout = nn.Dropout(config.dropout)
+        self.resid_dropout = nn.Dropout(config.dropout)
+        self.n_head = config.n_head
+        self.head_dim = config.n_embd // config.n_head
+        self.register_buffer(
+            "causal_mask",
+            torch.tril(torch.ones(config.block_size, config.block_size)).view(
+                1, 1, config.block_size, config.block_size
+            ),
+            persistent=False,
+        )
+
+    def forward(self, x):
+        B, T, C = x.size()
+        q, k, v = self.c_attn(x).split(C, dim=2)
+        q = q.view(B, T, self.n_head, self.head_dim).transpose(1, 2)
+        k = k.view(B, T, self.n_head, self.head_dim).transpose(1, 2)
+        v = v.view(B, T, self.n_head, self.head_dim).transpose(1, 2)
+        y = F.scaled_dot_product_attention(
+            q, k, v,
+            dropout_p=self.attn_dropout.p if self.training else 0.0,
+            is_causal=True,
+        )
+        y = y.transpose(1, 2).contiguous().view(B, T, C)
+        return self.resid_dropout(self.c_proj(y))
+
+
+class MLP(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd)
+        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd)
+        self.dropout = nn.Dropout(config.dropout)
+
+    def forward(self, x):
+        return self.dropout(self.c_proj(F.gelu(self.c_fc(x))))
+
+
+class Block(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.ln_1 = nn.LayerNorm(config.n_embd)
+        self.attn = CausalSelfAttention(config)
+        self.ln_2 = nn.LayerNorm(config.n_embd)
+        self.mlp = MLP(config)
+
+    def forward(self, x):
+        x = x + self.attn(self.ln_1(x))
+        x = x + self.mlp(self.ln_2(x))
+        return x
+
+
+class COReModel(PreTrainedModel):
+    config_class = COReConfig
+    base_model_prefix = "core"
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.config = config
+        self.tok_emb = nn.Embedding(config.vocab_size, config.n_embd)
+        self.pos_emb = None if config.rope else nn.Embedding(config.block_size, config.n_embd)
+        self.drop = nn.Dropout(config.dropout)
+        self.blocks = nn.ModuleList(Block(config) for _ in range(config.n_layer))
+        self.ln_f = nn.LayerNorm(config.n_embd)
+        self.post_init()
+
+    def forward(self, input_ids, attention_mask=None, **kwargs):
+        B, T = input_ids.size()
+        if self.pos_emb is not None:
+            pos = torch.arange(0, T, device=input_ids.device)
+            x = self.drop(self.tok_emb(input_ids) + self.pos_emb(pos))
+        else:
+            x = self.drop(self.tok_emb(input_ids))
+        for block in self.blocks:
+            x = block(x)
+        return self.ln_f(x)
+
+
+class COReForCausalLM(PreTrainedModel, GenerationMixin):
+    config_class = COReConfig
+    base_model_prefix = "core"
+    main_input_name = "input_ids"
+    _supports_cache_class = False
+    _supports_static_cache = False
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.config = config
+        self.tok_emb = nn.Embedding(config.vocab_size, config.n_embd)
+        self.pos_emb = None if config.rope else nn.Embedding(config.block_size, config.n_embd)
+        self.drop = nn.Dropout(config.dropout)
+        self.blocks = nn.ModuleList(Block(config) for _ in range(config.n_layer))
+        self.ln_f = nn.LayerNorm(config.n_embd)
+        self.head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
+        self.tok_emb.weight = self.head.weight
+        self.post_init()
+
+    def forward(self, input_ids, attention_mask=None, labels=None, **kwargs):
+        B, T = input_ids.size()
+        if self.pos_emb is not None:
+            pos = torch.arange(0, T, device=input_ids.device)
+            x = self.drop(self.tok_emb(input_ids) + self.pos_emb(pos))
+        else:
+            x = self.drop(self.tok_emb(input_ids))
+        for block in self.blocks:
+            x = block(x)
+        x = self.ln_f(x)
+        logits = self.head(x)
+
+        loss = None
+        if labels is not None:
+            shift_logits = logits[..., :-1, :].contiguous()
+            shift_labels = labels[..., 1:].contiguous()
+            loss = F.cross_entropy(
+                shift_logits.view(-1, shift_logits.size(-1)),
+                shift_labels.view(-1),
+                ignore_index=-100,
+            )
+
+        return CausalLMOutput(loss=loss, logits=logits)
+
+    def prepare_inputs_for_generation(self, input_ids, **kwargs):
+        if input_ids.size(1) > self.config.block_size:
+            input_ids = input_ids[:, -self.config.block_size:]
+        return {"input_ids": input_ids}
+
+    def _reorder_cache(self, past, beam_idx):
+        return past

flash-v1/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>",
+  "pad_token": "<|pad|>"
+}

flash-v1/tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "model_max_length": 512,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}