Back up runs/finemath-1337/checkpoint-000001000

runs/finemath-1337/checkpoint-000001000/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

runs/finemath-1337/checkpoint-000001000/NOTICE

@@ -0,0 +1,30 @@
+GoLLeM-149M-20B
+
+Weights and architecture derive from SlayerLab/gollem-v5-ckpts
+revision 963440ce6ab4ada7e95da4c1faa28ebb00c082d4, published under Apache-2.0.
+modeling_gollem.py extracts the inference classes unchanged from the pinned
+GoLLeM r6 training implementation. The continuation, export and release scripts
+were prepared for this 149M run.
+
+The likelihood routines in glint_metrics.py are adapted from
+Glint-Research/Glint-1.3/benchmark.py, revision
+c3f99e246aa2c64382f9668dc864533617482d0a, whose repository declares MIT.
+Copyright remains with the original contributors. MIT license text:
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

runs/finemath-1337/checkpoint-000001000/config.json

@@ -0,0 +1,17 @@
+{
+  "vocab": 12288,
+  "n_layer": 19,
+  "n_embd": 768,
+  "n_head": 12,
+  "block": 1024,
+  "ffn_mult": 2.8125,
+  "norm": "rmsnorm",
+  "norm_eps": 1e-06,
+  "pos": "rope",
+  "rope_theta": 100000.0,
+  "ffn": "swiglu",
+  "value_residual": true,
+  "qk_norm": true,
+  "logit_cap": 0.0,
+  "z_loss": 0.0
+}

runs/finemath-1337/checkpoint-000001000/generate.py

@@ -0,0 +1,28 @@
+"""Simple causal completion CLI (no KV cache)."""
+import argparse
+from contextlib import nullcontext
+import torch
+from load_model import load_model
+
+def main():
+    p=argparse.ArgumentParser()
+    p.add_argument('--model-dir',default='.')
+    p.add_argument('--prompt',default='The scientific method is')
+    p.add_argument('--max-new-tokens',type=int,default=64)
+    p.add_argument('--temperature',type=float,default=0.0)
+    p.add_argument('--device',default='cuda' if torch.cuda.is_available() else 'cpu')
+    args=p.parse_args();torch.set_num_threads(4)
+    model,tok=load_model(args.model_dir,args.device)
+    ids=tok.encode(args.prompt).ids
+    if not ids:raise ValueError('Prompt must encode to at least one token')
+    eos=tok.token_to_id('<|endoftext|>')
+    with torch.inference_mode():
+        for _ in range(args.max_new_tokens):
+            x=torch.tensor([ids[-model.block:]],device=args.device)
+            ctx=torch.autocast('cuda',dtype=torch.bfloat16) if args.device.startswith('cuda') else nullcontext()
+            with ctx:logits=model(x)[0][0,-1].float()
+            nxt=int(logits.argmax()) if args.temperature<=0 else int(torch.multinomial(torch.softmax(logits/args.temperature,dim=-1),1))
+            ids.append(nxt)
+            if nxt==eos:break
+    print(tok.decode(ids,skip_special_tokens=True))
+if __name__=='__main__':main()

runs/finemath-1337/checkpoint-000001000/load_model.py

@@ -0,0 +1,15 @@
+"""Load the local safetensors release without Transformers remote code."""
+import json
+from pathlib import Path
+from types import SimpleNamespace
+import torch
+from safetensors.torch import load_model as load_safetensors
+from tokenizers import Tokenizer
+from modeling_gollem import GPT
+
+def load_model(directory='.',device='cpu'):
+    directory=Path(directory)
+    cfg=SimpleNamespace(**json.loads((directory/'config.json').read_text()))
+    model=GPT(cfg.vocab,cfg.n_layer,cfg.n_embd,cfg.n_head,cfg.block,cfg)
+    load_safetensors(model,str(directory/'model.safetensors'),strict=True)
+    return model.eval().to(device),Tokenizer.from_file(str(directory/'tokenizer.json'))

runs/finemath-1337/checkpoint-000001000/manifest.json

@@ -0,0 +1,6 @@
+{
+  "checkpoint_sha256": "668e863c5f1f9ec5f75bc9f00c4ac63c9c7f9b9f21dd01d7db1354244f62071a",
+  "bytes": 1229596232,
+  "path_in_repo": "runs/finemath-1337/checkpoint-000001000/training-state.pt",
+  "status": "experimental_checkpoint"
+}

runs/finemath-1337/checkpoint-000001000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce2d7843c6f1b5f760a5ac5990d7b2c2b90f79c3289b54556ae29e91e84f906
+size 595664096

runs/finemath-1337/checkpoint-000001000/modeling_gollem.py

@@ -0,0 +1,140 @@
+"""GoLLeM inference architecture, extracted unchanged from the pinned r6 trainer.
+Source: SlayerLab/gollem-v5-ckpts; Apache-2.0. See README and NOTICE.
+"""
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+class RMSNorm(nn.Module):
+    """Qwen3-style RMSNorm (fp32-compute dla stabilnosci). 1D weight -> AdamW w split-Muon."""
+    def __init__(self, d, eps=1e-6):
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(d))
+        self.eps = eps
+
+    def forward(self, x):
+        return x * torch.rsqrt(x.float().pow(2).mean(-1, keepdim=True) + self.eps).to(x.dtype) * self.weight
+
+
+def make_norm(d, cfg):
+    return RMSNorm(d, cfg.norm_eps) if cfg.norm == "rmsnorm" else nn.LayerNorm(d)
+
+
+def apply_rope(x, base=100000.0):
+    """Parameter-free RoPE na [B,H,T,D] (interleaved-conv, port z qwen_model.py). Train==eval
+    MUSZA uzywac tej samej konwencji (self-contained eval -> spojne)."""
+    _, _, T, dim = x.shape
+    pos = torch.arange(T, device=x.device, dtype=torch.float32)
+    freq = 1.0 / (base ** (torch.arange(0, dim, 2, device=x.device, dtype=torch.float32) / dim))
+    ang = torch.outer(pos, freq)
+    cos, sin = ang.cos().to(x.dtype)[None, None], ang.sin().to(x.dtype)[None, None]
+    even, odd = x[..., ::2], x[..., 1::2]
+    return torch.stack((even * cos - odd * sin, even * sin + odd * cos), dim=-1).flatten(-2)
+
+
+class SwiGLU(nn.Module):
+    """Qwen3 gated-MLP: down(silu(gate(x))*up(x)). 3x 2D bez-bias -> wszystkie do Muon."""
+    def __init__(self, d, hidden):
+        super().__init__()
+        self.gate = nn.Linear(d, hidden, bias=False)
+        self.up = nn.Linear(d, hidden, bias=False)
+        self.down = nn.Linear(hidden, d, bias=False)
+
+    def forward(self, x):
+        return self.down(F.silu(self.gate(x)) * self.up(x))
+
+
+class Block(nn.Module):
+    def __init__(self, d, nh, block, cfg, is_first=False):
+        super().__init__()
+        self.ln1 = make_norm(d, cfg)
+        self.ln2 = make_norm(d, cfg)
+        self.qkv = nn.Linear(d, 3 * d)
+        self.proj = nn.Linear(d, d)
+        if cfg.ffn == "swiglu":
+            self.mlp = SwiGLU(d, int(round(cfg.ffn_mult * d)))
+        else:
+            self.mlp = nn.Sequential(nn.Linear(d, 4 * d), nn.GELU(), nn.Linear(4 * d, d))
+        self.nh = nh
+        self.d = d
+        self.cfg = cfg
+        self.is_first = is_first
+        if cfg.value_residual and not is_first:
+            self.vr_lambda = nn.Parameter(torch.zeros(1))
+        if cfg.qk_norm:
+            hd = d // nh
+            self.q_norm = RMSNorm(hd, cfg.norm_eps)
+            self.k_norm = RMSNorm(hd, cfg.norm_eps)
+
+    def forward(self, x, v0=None):
+        B, T, D = x.size()
+        h = self.ln1(x)
+        q, k, v = self.qkv(h).split(self.d, dim=2)
+        hd = D // self.nh
+        q = q.view(B, T, self.nh, hd).transpose(1, 2)
+        k = k.view(B, T, self.nh, hd).transpose(1, 2)
+        v = v.view(B, T, self.nh, hd).transpose(1, 2)
+        if self.cfg.qk_norm:
+            q = self.q_norm(q)
+            k = self.k_norm(k)
+        if self.cfg.pos == "rope":
+            q = apply_rope(q, self.cfg.rope_theta)
+            k = apply_rope(k, self.cfg.rope_theta)
+        if self.cfg.value_residual:
+            if self.is_first:
+                v0 = v
+            else:
+                v = v + self.vr_lambda * v0
+        y = F.scaled_dot_product_attention(q, k, v, is_causal=True)
+        y = y.transpose(1, 2).contiguous().view(B, T, D)
+        x = x + self.proj(y)
+        x = x + self.mlp(self.ln2(x))
+        return x, v0
+
+
+class GPT(nn.Module):
+    def __init__(self, vocab, n_layer, n_embd, n_head, block, cfg):
+        super().__init__()
+        self.cfg = cfg
+        self.tok = nn.Embedding(vocab, n_embd)
+        self.use_rope = cfg.pos == "rope"
+        if not self.use_rope:
+            self.pos = nn.Embedding(block, n_embd)
+        self.blocks = nn.ModuleList([Block(n_embd, n_head, block, cfg, is_first=(i == 0)) for i in range(n_layer)])
+        self.lnf = make_norm(n_embd, cfg)
+        self.head = nn.Linear(n_embd, vocab, bias=False)
+        self.head.weight = self.tok.weight  # tie
+        self.block = block
+        self.apply(self._init)
+
+    def _init(self, m):
+        if isinstance(m, nn.Linear):
+            nn.init.normal_(m.weight, 0.0, 0.02)
+            if m.bias is not None:
+                nn.init.zeros_(m.bias)
+        elif isinstance(m, nn.Embedding):
+            nn.init.normal_(m.weight, 0.0, 0.02)
+
+    def forward(self, idx, targets=None):
+        B, T = idx.size()
+        x = self.tok(idx)
+        if not self.use_rope:
+            pos = torch.arange(T, device=idx.device)
+            x = x + self.pos(pos)[None]
+        v0 = None
+        for b in self.blocks:
+            x, v0 = b(x, v0)
+        logits = self.head(self.lnf(x))
+        cap = getattr(self.cfg, "logit_cap", 0.0)
+        if cap and cap > 0:
+            logits = cap * torch.tanh(logits / cap)
+        loss = None
+        if targets is not None:
+            flat = logits.view(-1, logits.size(-1))
+            loss = F.cross_entropy(flat, targets.view(-1))
+            zc = getattr(self.cfg, "z_loss", 0.0)
+            if zc and zc > 0:
+                lse = torch.logsumexp(flat, dim=-1)
+                loss = loss + zc * (lse * lse).mean()
+        return logits, loss
+

runs/finemath-1337/checkpoint-000001000/requirements.txt

@@ -0,0 +1,6 @@
+torch==2.11.0
+tokenizers==0.22.2
+safetensors==0.6.2
+huggingface-hub==0.36.0
+numpy>=1.26,<3
+pyarrow>=20,<25

runs/finemath-1337/checkpoint-000001000/training-state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668e863c5f1f9ec5f75bc9f00c4ac63c9c7f9b9f21dd01d7db1354244f62071a
+size 1229596232