Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_384/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_192/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_256/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_320/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_320/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_384/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_448/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_448/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_512/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_512/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_64/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_64/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_128/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_128/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_192/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_192/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_256/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_256/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_320/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_384/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_448/actor_hf/model-00001-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_448/actor_hf/model-00002-of-00002.safetensors +3 -0
- Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_512/actor_hf/model-00002-of-00002.safetensors +3 -0
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94bd97be04b7473db813fead7f6e03ff8708883e86e52a022be86f8eb94d9945
|
| 3 |
+
size 2239923424
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:186a4344b5b8fc530ee888d0a5b65671e7c5cb830b39d10fde9742e2506ebae9
|
| 3 |
+
size 4998783000
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed99dd57f58ba08e0438af699ef79a858176495b2317b9603d854d8e691245de
|
| 3 |
+
size 2214751024
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dfd8ec14add28b7a3084dde5ec3962d0da7bd4c129c9eae188a8178d9224ce6
|
| 3 |
+
size 2392413904
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f7eb1527c5ec778ee990993d547ebf0eb53518934aa6bc87294c548f1f20eb5
|
| 3 |
+
size 4998769736
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84e124b10f8141eeaf47563cd6e1ccd3065a4f41c036bd154ae1f6153a0381ba
|
| 3 |
+
size 2214764288
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9be630655ea667818be55da1742d0fdee274911fe8c4efa12bcfdd838f821b3
|
| 3 |
+
size 4959539064
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d94dfb571f831c04d1ec9e6893eca1d8c1194f39291a9d1555e2f507882a046
|
| 3 |
+
size 2253995024
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dd1b63151bcc3206798c1d6ae60621bf2027df784caf4b9239b01f01dedd8eb
|
| 3 |
+
size 4992471336
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56dff128c3842c0a7c977cfc7e9f17ca63bac1313a5b04557a4693c0b2406bbf
|
| 3 |
+
size 2221062672
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fff4d79243053e868da49cb1b38dca215be9206899b03ae90b73030b420c58be
|
| 3 |
+
size 4961003200
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb57d73251a09190333bf166667c3e686d15398cc7e26b63b6019ea3f5993325
|
| 3 |
+
size 2252530840
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bb275f066786de1d3f5107a5d1c6ec31a28600250dc15a430418d8e349d4481
|
| 3 |
+
size 4997249144
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da2f66bc38e7993e10f54b96e22ed378096e91972240a982cd85757fad48c16f
|
| 3 |
+
size 2216284952
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0587e4ea083d45293aa0943d269af641172754e91483fbe9d6bdcceb606a95f0
|
| 3 |
+
size 4992476984
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d28f27403220ea1f9f9a840896460e980bb419218ee39786cbd69d4360d53582
|
| 3 |
+
size 2221057024
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d4a5b90697aa1afd8d8b2cbe79fbbf9c3bb99fe8764c0477bd7ab807d0df366
|
| 3 |
+
size 2228853840
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0ddf4535cc46f4a1acab39c5e6769b0f24072273fbdb4d53157e8c7a02763eb
|
| 3 |
+
size 4998813952
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:883a820351e9cd7b6a09a5333de132f976f456432e924285f871dcdeefa4bcbb
|
| 3 |
+
size 2214720056
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e6ab2e192c1da5ac0fbeca098dbd7ad3ea3fa56d0364ae947a12a03cfe6e331
|
| 3 |
+
size 4739306232
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53b064eecfc96cc009b84d390045e5360ba8151c915a311fe3d8c3f43ca9c3fe
|
| 3 |
+
size 2474227864
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_384/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:621e982964b8ba24d884aad8ed859f5ad6e5401abf3fc23ad6c2122e8304a6a7
|
| 3 |
+
size 2482065192
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d57d76cacc1892933b8f434d3b3b0550156602606929d790b11b4b342429c99
|
| 3 |
+
size 4997268872
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a65072593e8d5a355ee74424fbac2bb13fd60fbd3487639f8738db01ad5e11a0
|
| 3 |
+
size 2216265208
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7570eb95cab18187a78d43b3c2f3687b32c0b9f209da5489a06df93fef4e5987
|
| 3 |
+
size 2254013424
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44f3e65af73520d49ccf19c7856408fd9f212b86be8815597a140341451cf4e6
|
| 3 |
+
size 2260311512
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68b21908fbeb3b34ed05f0e080f24e4e3a502f1431f60d2241ab57dbaf114737
|
| 3 |
+
size 4990933744
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19808f447800b307637f0f1abdb23d68d2065716bd6b5ba61add3c9ae005ac58
|
| 3 |
+
size 2222600336
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_192/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a18fc26c712b07b0b2d5f550b80992a26adcaa35427a8f0a57412a34f8cec8e
|
| 3 |
+
size 2235158336
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_256/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a414a0fe141d4c631092ca3e73d8dfd0285bfa8f6e562977cf04900773e927fb
|
| 3 |
+
size 2246203216
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_320/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:354e56a7cdcae53a80ec45875c90a2e0fbe4376e15a8cef291ca84311df7aa3e
|
| 3 |
+
size 4990990328
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_320/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93f0e6619f263249cf07a28ee039cdcb06c625707623e9caf7a78ef9265f0e5a
|
| 3 |
+
size 2222543760
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_384/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0425a410a4fd109cb5a4939f78958520fd71ca5a74d88ed8088e5bc4b219dd5
|
| 3 |
+
size 2254020328
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_448/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:607164a5989b014d0e7ed33d2fc72d039e9ed2c57f51558c559b5722f8e277d6
|
| 3 |
+
size 4437365712
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_448/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40dbd26e674b49ff5536ff6ad098f2180a2e5adad2299558730cfaccee284ee6
|
| 3 |
+
size 2776168376
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_512/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c4d4e0447930537792bbbfafb8dd9d7e36dff99d15ecf6c2cc70614bbf1c190
|
| 3 |
+
size 4961096984
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_512/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4559f82ee6397e2cdd8ff9ce9944c3961294cda4f01bc594a3d83a13a449f4c
|
| 3 |
+
size 2252437064
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_64/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a799fcb0ff41520c62fb8af42037200161181aa77be5c0b54e67988ef71adb0
|
| 3 |
+
size 4954755776
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_64/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72fccac8969b92c25e1b00cc7bf86727ab72d9b3037d21ba601d8b5d5d18cd57
|
| 3 |
+
size 2258778264
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_128/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dca341083c9b9706932e96c9ad4e234eb23e773223bcb230dac0050cd320aa15
|
| 3 |
+
size 4986199584
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_128/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d512fbda85efb38d214545cbc0b550eb43dd31bda2d95b317b1821df4b42dee4
|
| 3 |
+
size 2227334456
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_192/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25f206f4a2972f3f55f01d617594e39f8ad53697b6252d7d013122bf58c40b09
|
| 3 |
+
size 4973648960
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_192/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1480ebb5c9ce9e1b3d7f7919e103a80f80e86e1802b0a7737eae99d4ea25903e
|
| 3 |
+
size 2239885096
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_256/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e6bb2bab74c92aa69890bb97232f95944b998a6a59944b8817e2871dfa9cb64
|
| 3 |
+
size 4443586552
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_256/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0ef9d7bf62d636afa5231162b09176e20b2515bae17b87da2c7314049ce1b6a
|
| 3 |
+
size 2769947536
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_320/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11c7b74af0eb909c48ed0b2ac7fed26d4be7cad02c9cb09c598125df0694d539
|
| 3 |
+
size 4954729920
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_384/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53900af5dc811130ebd09ef8ec8640370b576cbad8de3d2b3ad73a81bd8c4030
|
| 3 |
+
size 2221023824
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_448/actor_hf/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89892e7f687492cc56613f7fb7151645abe583fecc65fc5bddc45453602b5dbf
|
| 3 |
+
size 4972108984
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_448/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8682e79eb950b8f6182e1ceaf8d0688331fa02509eb08d62c56fa1b6b1991bf
|
| 3 |
+
size 2241425104
|
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_512/actor_hf/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fafd581f2d477acc67f1b37c05f83d3e217acbdecf18780d32ca1cdd2a982064
|
| 3 |
+
size 2461633008
|