JayKimDevolved/deepseek

.gitattributes

@@ -36,3 +36,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 pip-install-ghxuqwgs/numpy_78e94bf2b6094bf9a1f3d92042f9bf46/build/temp.linux-x86_64-cpython-310/build/src.linux-x86_64-3.1/numpy/core/src/multiarray/arraytypes.o filter=lfs diff=lfs merge=lfs -text
 pip-install-ghxuqwgs/numpy_78e94bf2b6094bf9a1f3d92042f9bf46/build/temp.linux-x86_64-cpython-310/libnpysort.a filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+ollama1570737069/runners/cpu/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1570737069/runners/cpu_avx/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1570737069/runners/cpu_avx2/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1570737069/runners/cuda_v11/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1570737069/runners/cuda_v12/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1570737069/runners/rocm/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1718139592/runners/cpu/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1718139592/runners/cpu_avx/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1718139592/runners/cpu_avx2/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1718139592/runners/cuda_v11/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1718139592/runners/cuda_v12/ollama_llama_server filter=lfs diff=lfs merge=lfs -text
+ollama1718139592/runners/rocm/ollama_llama_server filter=lfs diff=lfs merge=lfs -text

README.md

@@ -35,8 +35,8 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.13.0
-- Transformers: 4.47.1
-- Pytorch: 2.1.0+cu118
+- Transformers: 4.48.1
+- Pytorch: 2.5.1
 - Datasets: 3.2.0
 - Tokenizers: 0.21.0
 

adapter_config.json

@@ -24,9 +24,9 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
-    "k_proj",
     "gate_proj",
+    "k_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f97148c039e09f4ff984bdcfd6d0e5826e975028772c12694ac52a2b3c3360d3
+oid sha256:97974890d929435a7c68aed25e299075faa6d6922c790f3afded854f32dc7cc7
 size 369142184

ollama1570737069/ollama.pid

@@ -0,0 +1 @@
+6455

ollama1570737069/runners/cpu/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200b9fd1f8d2b5727d7b28c322c21c200d5bc977f73fff47dbc32fb71f398f7a
+size 8919824

ollama1570737069/runners/cpu_avx/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ded4958ec90932962962382565a37252d79b5bfde63fea6bf16b7b7f7fd371
+size 8985392

ollama1570737069/runners/cpu_avx2/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3123dc06e08a26b90af4694d0c513b1795c3dc252d1c76586317cbfefaf777cd
+size 8997680

ollama1570737069/runners/cuda_v11/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74174d557c6fd9de9af3ab2adb54ae81d4b584af38a85d0a8a25c57f69ec494
+size 8997776

ollama1570737069/runners/cuda_v12/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6940d1e48c100d3d8806c8c4f6df84f83920de9ce89d493c33405e242e9ef43
+size 8960912

ollama1570737069/runners/rocm/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90fa16551538f9ac96d06ab8b2e180e11b5d23ffb6db36437903c5570c827239
+size 8952720

ollama1718139592/ollama.pid

@@ -0,0 +1 @@
+6102

ollama1718139592/runners/cpu/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200b9fd1f8d2b5727d7b28c322c21c200d5bc977f73fff47dbc32fb71f398f7a
+size 8919824

ollama1718139592/runners/cpu_avx/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ded4958ec90932962962382565a37252d79b5bfde63fea6bf16b7b7f7fd371
+size 8985392

ollama1718139592/runners/cpu_avx2/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3123dc06e08a26b90af4694d0c513b1795c3dc252d1c76586317cbfefaf777cd
+size 8997680

ollama1718139592/runners/cuda_v11/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74174d557c6fd9de9af3ab2adb54ae81d4b584af38a85d0a8a25c57f69ec494
+size 8997776

ollama1718139592/runners/cuda_v12/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6940d1e48c100d3d8806c8c4f6df84f83920de9ce89d493c33405e242e9ef43
+size 8960912

ollama1718139592/runners/rocm/ollama_llama_server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90fa16551538f9ac96d06ab8b2e180e11b5d23ffb6db36437903c5570c827239
+size 8952720

tmpkds2w0wa/_remote_module_non_scriptable.py

@@ -0,0 +1,81 @@
+from typing import *
+
+import torch
+import torch.distributed.rpc as rpc
+from torch import Tensor
+from torch._jit_internal import Future
+from torch.distributed.rpc import RRef
+from typing import Tuple  # pyre-ignore: unused import
+
+
+module_interface_cls = None
+
+
+def forward_async(self, *args, **kwargs):
+    args = (self.module_rref, self.device, self.is_device_map_set, *args)
+    kwargs = {**kwargs}
+    return rpc.rpc_async(
+        self.module_rref.owner(),
+        _remote_forward,
+        args,
+        kwargs,
+    )
+
+
+def forward(self, *args, **kwargs):
+    args = (self.module_rref, self.device, self.is_device_map_set, *args)
+    kwargs = {**kwargs}
+    ret_fut = rpc.rpc_async(
+        self.module_rref.owner(),
+        _remote_forward,
+        args,
+        kwargs,
+    )
+    return ret_fut.wait()
+
+
+_generated_methods = [
+    forward_async,
+    forward,
+]
+
+
+
+
+def _remote_forward(
+    module_rref: RRef[module_interface_cls], device: str, is_device_map_set: bool, *args, **kwargs):
+    module = module_rref.local_value()
+    device = torch.device(device)
+
+    if device.type != "cuda":
+        return module.forward(*args, **kwargs)
+
+    # If the module is on a cuda device,
+    # move any CPU tensor in args or kwargs to the same cuda device.
+    # Since torch script does not support generator expression,
+    # have to use concatenation instead of
+    # ``tuple(i.to(device) if isinstance(i, Tensor) else i for i in *args)``.
+    args = (*args,)
+    out_args: Tuple[()] = ()
+    for arg in args:
+        arg = (arg.to(device),) if isinstance(arg, Tensor) else (arg,)
+        out_args = out_args + arg
+
+    kwargs = {**kwargs}
+    for k, v in kwargs.items():
+        if isinstance(v, Tensor):
+            kwargs[k] = kwargs[k].to(device)
+
+    if is_device_map_set:
+        return module.forward(*out_args, **kwargs)
+
+    # If the device map is empty, then only CPU tensors are allowed to send over wire,
+    # so have to move any GPU tensor to CPU in the output.
+    # Since torch script does not support generator expression,
+    # have to use concatenation instead of
+    # ``tuple(i.cpu() if isinstance(i, Tensor) else i for i in module.forward(*out_args, **kwargs))``.
+    ret: Tuple[()] = ()
+    for i in module.forward(*out_args, **kwargs):
+        i = (i.cpu(),) if isinstance(i, Tensor) else (i,)
+        ret = ret + i
+    return ret

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a6bb62a03cda10fd2af4c2dea85771fe7350f2400e76869451cd17bb9c85a31
+oid sha256:e9f019f87aed1c047e337b35c7a59f80057ec714320781f3babafafff0cea488
 size 5560