Publish esm2-t12-35m-ur50d-f32-af32 RDRR artifact
Browse files- models/esm2-t12-35m-ur50d-f32-af32/SOURCE.md +14 -0
- models/esm2-t12-35m-ur50d-f32-af32/manifest.json +2893 -0
- models/esm2-t12-35m-ur50d-f32-af32/origin.json +10 -0
- models/esm2-t12-35m-ur50d-f32-af32/shard_00000.bin +3 -0
- models/esm2-t12-35m-ur50d-f32-af32/shard_00001.bin +3 -0
- models/esm2-t12-35m-ur50d-f32-af32/tokenizer.json +1 -0
models/esm2-t12-35m-ur50d-f32-af32/SOURCE.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ESM-2 35M RDRR artifact
|
| 2 |
+
|
| 3 |
+
This directory contains a Doppler RDRR conversion of
|
| 4 |
+
`facebook/esm2_t12_35M_UR50D` at source revision
|
| 5 |
+
`6fbf070e65b0b7291e7bbcd451118c216cff79d8`.
|
| 6 |
+
|
| 7 |
+
- Upstream model: https://huggingface.co/facebook/esm2_t12_35M_UR50D
|
| 8 |
+
- Upstream license: MIT
|
| 9 |
+
- Doppler model ID: `esm2-t12-35m-ur50d-f32-af32`
|
| 10 |
+
- Qualification: `docs/status/esm2-t12-35m-sequence-webgpu-lora-qualification-2026-07-19.json`
|
| 11 |
+
|
| 12 |
+
The qualification proves deterministic tokenizer identity, selected numerical
|
| 13 |
+
parity probes, finite WebGPU sequence outputs, and the synthetic LoRA lifecycle.
|
| 14 |
+
It is not a downstream biological-task quality claim.
|
models/esm2-t12-35m-ur50d-f32-af32/manifest.json
ADDED
|
@@ -0,0 +1,2893 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": 1,
|
| 3 |
+
"modelId": "esm2-t12-35m-ur50d-f32-af32",
|
| 4 |
+
"modelType": "embedding",
|
| 5 |
+
"quantization": "F32",
|
| 6 |
+
"quantizationInfo": {
|
| 7 |
+
"weights": "f32",
|
| 8 |
+
"embeddings": "f32",
|
| 9 |
+
"compute": "f32",
|
| 10 |
+
"variantTag": "f32"
|
| 11 |
+
},
|
| 12 |
+
"artifactIdentity": {
|
| 13 |
+
"artifactCompleteness": "complete",
|
| 14 |
+
"conversionConfigDigest": "sha256:25da72db3b9cbfae0c6fab4ad22f62ef7064f1a83edadc09c1ef694afb1f7203",
|
| 15 |
+
"conversionConfigPath": "src/config/conversion/esm/esm2-t12-35m-ur50d-f32-af32.json",
|
| 16 |
+
"manifestVariantId": "esm2-t12-35m-ur50d-f32-af32-mv-exec-v1",
|
| 17 |
+
"materializationProfile": "f32-weights-f32-activations",
|
| 18 |
+
"modalitySet": [
|
| 19 |
+
"protein_sequence"
|
| 20 |
+
],
|
| 21 |
+
"shardSetHash": "sha256:02d771a5ddf516cd4d01338a229309d87822b46b2317fd8432b756fd45ce924e",
|
| 22 |
+
"sourceCheckpointId": "facebook/esm2_t12_35M_UR50D@6fbf070e65b0b7291e7bbcd451118c216cff79d8",
|
| 23 |
+
"sourceFormat": "safetensors",
|
| 24 |
+
"sourceRepo": "facebook/esm2_t12_35M_UR50D",
|
| 25 |
+
"sourceRevision": "6fbf070e65b0b7291e7bbcd451118c216cff79d8",
|
| 26 |
+
"weightPackHash": "sha256:1092c098741472429a4c6b4cd6050d5967e0a606d01f713c0b4866fd98921ac8",
|
| 27 |
+
"weightPackId": "esm2-t12-35m-ur50d-f32-af32-wp-v1"
|
| 28 |
+
},
|
| 29 |
+
"architecture": {
|
| 30 |
+
"numLayers": 12,
|
| 31 |
+
"hiddenSize": 480,
|
| 32 |
+
"intermediateSize": 1920,
|
| 33 |
+
"numAttentionHeads": 20,
|
| 34 |
+
"numKeyValueHeads": 20,
|
| 35 |
+
"headDim": 24,
|
| 36 |
+
"vocabSize": 33,
|
| 37 |
+
"maxSeqLen": 1026,
|
| 38 |
+
"linearNumKeyHeads": null,
|
| 39 |
+
"linearNumValueHeads": null,
|
| 40 |
+
"linearKeyHeadDim": null,
|
| 41 |
+
"linearValueHeadDim": null,
|
| 42 |
+
"linearConvKernelDim": null,
|
| 43 |
+
"hiddenSizePerLayerInput": null,
|
| 44 |
+
"vocabSizePerLayerInput": null,
|
| 45 |
+
"globalHeadDim": null,
|
| 46 |
+
"numKvSharedLayers": null
|
| 47 |
+
},
|
| 48 |
+
"moeConfig": null,
|
| 49 |
+
"inference": {
|
| 50 |
+
"schema": "doppler.execution/v1",
|
| 51 |
+
"attention": {
|
| 52 |
+
"queryKeyNormType": "rmsnorm",
|
| 53 |
+
"queryKeyNormAxis": "head",
|
| 54 |
+
"queryPreAttnScalar": 24,
|
| 55 |
+
"attnLogitSoftcapping": null,
|
| 56 |
+
"slidingWindow": null,
|
| 57 |
+
"queryKeyNorm": false,
|
| 58 |
+
"queryKeyNormLayers": null,
|
| 59 |
+
"queryKeyNormWeightLayers": null,
|
| 60 |
+
"valueNorm": false,
|
| 61 |
+
"causal": false,
|
| 62 |
+
"attentionBias": true,
|
| 63 |
+
"attentionOutputGate": false,
|
| 64 |
+
"outputGateType": null
|
| 65 |
+
},
|
| 66 |
+
"normalization": {
|
| 67 |
+
"type": "layernorm",
|
| 68 |
+
"rmsNormEps": 0.00001,
|
| 69 |
+
"rmsNormWeightOffset": false,
|
| 70 |
+
"postAttentionNorm": true,
|
| 71 |
+
"preFeedforwardNorm": false,
|
| 72 |
+
"postFeedforwardNorm": false,
|
| 73 |
+
"finalNormBiasTensor": "model.norm.bias"
|
| 74 |
+
},
|
| 75 |
+
"ffn": {
|
| 76 |
+
"activation": "gelu",
|
| 77 |
+
"gatedActivation": false,
|
| 78 |
+
"branchMode": "dense",
|
| 79 |
+
"useDoubleWideMlp": false,
|
| 80 |
+
"swigluLimit": null
|
| 81 |
+
},
|
| 82 |
+
"rope": {
|
| 83 |
+
"ropeTheta": 10000,
|
| 84 |
+
"ropeLocalTheta": null,
|
| 85 |
+
"ropeInterleaved": false,
|
| 86 |
+
"mropeInterleaved": false,
|
| 87 |
+
"mropeSection": null,
|
| 88 |
+
"partialRotaryFactor": null,
|
| 89 |
+
"ropeLocalPartialRotaryFactor": null,
|
| 90 |
+
"ropeFrequencyBaseDim": null,
|
| 91 |
+
"ropeLocalFrequencyBaseDim": null,
|
| 92 |
+
"ropeScalingType": null,
|
| 93 |
+
"ropeScalingFactor": 1,
|
| 94 |
+
"ropeLocalScalingType": null,
|
| 95 |
+
"ropeLocalScalingFactor": 1,
|
| 96 |
+
"yarnBetaFast": null,
|
| 97 |
+
"yarnBetaSlow": null,
|
| 98 |
+
"yarnOriginalMaxPos": null,
|
| 99 |
+
"ropeLocalYarnBetaFast": null,
|
| 100 |
+
"ropeLocalYarnBetaSlow": null,
|
| 101 |
+
"ropeLocalYarnOriginalMaxPos": null,
|
| 102 |
+
"longropeShortFactor": null,
|
| 103 |
+
"longropeLongFactor": null,
|
| 104 |
+
"longropeOriginalMaxPos": null
|
| 105 |
+
},
|
| 106 |
+
"output": {
|
| 107 |
+
"embeddingTranspose": false,
|
| 108 |
+
"embeddingVocabSize": null,
|
| 109 |
+
"finalLogitSoftcapping": null,
|
| 110 |
+
"tieWordEmbeddings": false,
|
| 111 |
+
"scaleEmbeddings": false,
|
| 112 |
+
"embeddingScale": 0.88,
|
| 113 |
+
"logitInputScale": 1,
|
| 114 |
+
"embeddingPostprocessor": null,
|
| 115 |
+
"lmHeadBiasTensor": null
|
| 116 |
+
},
|
| 117 |
+
"layerPattern": {
|
| 118 |
+
"type": "uniform",
|
| 119 |
+
"globalPattern": null,
|
| 120 |
+
"period": null,
|
| 121 |
+
"offset": null,
|
| 122 |
+
"layerTypes": null,
|
| 123 |
+
"residualBranchScale": 1
|
| 124 |
+
},
|
| 125 |
+
"chatTemplate": {
|
| 126 |
+
"type": null,
|
| 127 |
+
"enabled": false
|
| 128 |
+
},
|
| 129 |
+
"supportsEmbedding": true,
|
| 130 |
+
"supportsSequence": true,
|
| 131 |
+
"supportsRerank": false,
|
| 132 |
+
"supportsTranscription": false,
|
| 133 |
+
"supportsVision": false,
|
| 134 |
+
"rerank": null,
|
| 135 |
+
"sequence": {
|
| 136 |
+
"alphabet": "amino_acid",
|
| 137 |
+
"tokenEmbeddings": true,
|
| 138 |
+
"pooledEmbedding": {
|
| 139 |
+
"mode": "mean",
|
| 140 |
+
"excludeTokenIds": [
|
| 141 |
+
0,
|
| 142 |
+
1,
|
| 143 |
+
2,
|
| 144 |
+
3,
|
| 145 |
+
31,
|
| 146 |
+
32
|
| 147 |
+
]
|
| 148 |
+
},
|
| 149 |
+
"logits": false
|
| 150 |
+
},
|
| 151 |
+
"diffusionGemma": null,
|
| 152 |
+
"pipeline": null,
|
| 153 |
+
"session": {
|
| 154 |
+
"compute": {
|
| 155 |
+
"defaults": {
|
| 156 |
+
"activationDtype": "f32",
|
| 157 |
+
"mathDtype": "f32",
|
| 158 |
+
"accumDtype": "f32",
|
| 159 |
+
"outputDtype": "f32"
|
| 160 |
+
}
|
| 161 |
+
},
|
| 162 |
+
"kvcache": {
|
| 163 |
+
"kvDtype": "f32",
|
| 164 |
+
"layout": "contiguous",
|
| 165 |
+
"maxSeqLen": 1026,
|
| 166 |
+
"pageSize": 256,
|
| 167 |
+
"tiering": {
|
| 168 |
+
"mode": "off",
|
| 169 |
+
"hotWindow": 1024,
|
| 170 |
+
"coldPageSize": 256,
|
| 171 |
+
"coldDtype": "f16",
|
| 172 |
+
"compression": {
|
| 173 |
+
"mode": "none",
|
| 174 |
+
"blockSize": 1,
|
| 175 |
+
"bitWidth": 4,
|
| 176 |
+
"prodMode": false
|
| 177 |
+
},
|
| 178 |
+
"gating": {
|
| 179 |
+
"mode": "auto",
|
| 180 |
+
"minAluBwRatio": 0
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"quantization": {
|
| 184 |
+
"mode": "none",
|
| 185 |
+
"bitWidth": 4,
|
| 186 |
+
"prodMode": false
|
| 187 |
+
}
|
| 188 |
+
},
|
| 189 |
+
"decodeLoop": {
|
| 190 |
+
"batchSize": 1,
|
| 191 |
+
"stopCheckMode": "per-token",
|
| 192 |
+
"readbackInterval": 1,
|
| 193 |
+
"readbackMode": "sequential",
|
| 194 |
+
"submitLatencyThresholdMs": null,
|
| 195 |
+
"ringTokens": 1,
|
| 196 |
+
"ringStop": 1,
|
| 197 |
+
"ringStaging": 1,
|
| 198 |
+
"disableCommandBatching": false
|
| 199 |
+
},
|
| 200 |
+
"perLayerInputs": {
|
| 201 |
+
"materialization": "auto",
|
| 202 |
+
"rowCache": {
|
| 203 |
+
"mode": "lru",
|
| 204 |
+
"maxRows": 256,
|
| 205 |
+
"maxBytes": 134217728,
|
| 206 |
+
"decodedDtype": "f32"
|
| 207 |
+
},
|
| 208 |
+
"prefetch": {
|
| 209 |
+
"mode": "next_token",
|
| 210 |
+
"rowsAhead": 1
|
| 211 |
+
},
|
| 212 |
+
"gpuUpload": {
|
| 213 |
+
"mode": "per_step_slices",
|
| 214 |
+
"stagingRows": 2
|
| 215 |
+
},
|
| 216 |
+
"hotCache": {
|
| 217 |
+
"mode": "prepared_tokens",
|
| 218 |
+
"maxTokens": 1024,
|
| 219 |
+
"maxBytes": 134217728,
|
| 220 |
+
"outputDtype": "f32"
|
| 221 |
+
}
|
| 222 |
+
},
|
| 223 |
+
"skipEmbeddingKVCacheWrites": true,
|
| 224 |
+
"prefillChunkSubmitMode": "sync",
|
| 225 |
+
"useFlashPrefillAttention": false,
|
| 226 |
+
"useWideTileQ4KPrefill": false,
|
| 227 |
+
"retainQ4KMaterialization": false
|
| 228 |
+
},
|
| 229 |
+
"execution": {
|
| 230 |
+
"inlineKernelPath": true,
|
| 231 |
+
"policies": {
|
| 232 |
+
"unsupportedPrecision": "error",
|
| 233 |
+
"dtypeTransition": "require_cast_step",
|
| 234 |
+
"unresolvedKernel": "error"
|
| 235 |
+
},
|
| 236 |
+
"kernels": {
|
| 237 |
+
"embed": {
|
| 238 |
+
"kernel": "gather.wgsl",
|
| 239 |
+
"entry": "main",
|
| 240 |
+
"digest": "sha256:4b12653c53247b32ebde7f6cf6a989d6248977e3816c761540b990b5f9818cb6"
|
| 241 |
+
},
|
| 242 |
+
"layernorm": {
|
| 243 |
+
"kernel": "layernorm.wgsl",
|
| 244 |
+
"entry": "main",
|
| 245 |
+
"digest": "sha256:8ff885017bfcfc8fdb8d16e09c358c000830bfd5fbf3d87187694edb0cb44f7c"
|
| 246 |
+
},
|
| 247 |
+
"tiled": {
|
| 248 |
+
"kernel": "matmul_f32.wgsl",
|
| 249 |
+
"entry": "main",
|
| 250 |
+
"digest": "sha256:b5bb8e3d8014136e33de7935dd2a1f074c988044fe05cf5b559718c6f061eaa8"
|
| 251 |
+
},
|
| 252 |
+
"bias_add": {
|
| 253 |
+
"kernel": "bias_add.wgsl",
|
| 254 |
+
"entry": "main",
|
| 255 |
+
"digest": "sha256:e7d3b4a5f9efc8b0569c56bcdeb63e921fa6d1d006901deabc734cab40346715"
|
| 256 |
+
},
|
| 257 |
+
"rope": {
|
| 258 |
+
"kernel": "rope.wgsl",
|
| 259 |
+
"entry": "main",
|
| 260 |
+
"digest": "sha256:b2da9d396668981dab9794c2973b668279f768994466b083d2105730555e1a5b"
|
| 261 |
+
},
|
| 262 |
+
"attn_small": {
|
| 263 |
+
"kernel": "attention_small.wgsl",
|
| 264 |
+
"entry": "main",
|
| 265 |
+
"digest": "sha256:6752ddd7ab53e6235c9b5b1a9515141c0d111df7fac9f4c0d7a38f9943490ed4",
|
| 266 |
+
"precision": {
|
| 267 |
+
"kvDtype": "f32"
|
| 268 |
+
}
|
| 269 |
+
},
|
| 270 |
+
"residual": {
|
| 271 |
+
"kernel": "residual.wgsl",
|
| 272 |
+
"entry": "main",
|
| 273 |
+
"digest": "sha256:abd19bc08ad668a7cad562e2bc0a4be1aa8827ad4300d8d474b7fc2af4c27117"
|
| 274 |
+
},
|
| 275 |
+
"gelu": {
|
| 276 |
+
"kernel": "gelu.wgsl",
|
| 277 |
+
"entry": "main",
|
| 278 |
+
"digest": "sha256:7f8900b69de5107e4cf424cac0d4de1539591ece34e977ff30f6f7364460ab34",
|
| 279 |
+
"constants": {
|
| 280 |
+
"HAS_GATE": false
|
| 281 |
+
}
|
| 282 |
+
}
|
| 283 |
+
},
|
| 284 |
+
"preLayer": [
|
| 285 |
+
[
|
| 286 |
+
"embed",
|
| 287 |
+
"embed",
|
| 288 |
+
"embed_tokens"
|
| 289 |
+
]
|
| 290 |
+
],
|
| 291 |
+
"decode": [
|
| 292 |
+
[
|
| 293 |
+
"input_norm",
|
| 294 |
+
"layernorm"
|
| 295 |
+
],
|
| 296 |
+
[
|
| 297 |
+
"q_proj",
|
| 298 |
+
"tiled",
|
| 299 |
+
"layer.{L}.self_attn.q_proj"
|
| 300 |
+
],
|
| 301 |
+
[
|
| 302 |
+
"k_proj",
|
| 303 |
+
"tiled",
|
| 304 |
+
"layer.{L}.self_attn.k_proj"
|
| 305 |
+
],
|
| 306 |
+
[
|
| 307 |
+
"v_proj",
|
| 308 |
+
"tiled",
|
| 309 |
+
"layer.{L}.self_attn.v_proj"
|
| 310 |
+
],
|
| 311 |
+
[
|
| 312 |
+
"rope_q",
|
| 313 |
+
"rope"
|
| 314 |
+
],
|
| 315 |
+
[
|
| 316 |
+
"rope_k",
|
| 317 |
+
"rope"
|
| 318 |
+
],
|
| 319 |
+
[
|
| 320 |
+
"attention",
|
| 321 |
+
"attn_small"
|
| 322 |
+
],
|
| 323 |
+
[
|
| 324 |
+
"o_proj",
|
| 325 |
+
"tiled",
|
| 326 |
+
"layer.{L}.self_attn.o_proj"
|
| 327 |
+
],
|
| 328 |
+
[
|
| 329 |
+
"attn_residual",
|
| 330 |
+
"residual"
|
| 331 |
+
],
|
| 332 |
+
[
|
| 333 |
+
"post_attn_norm",
|
| 334 |
+
"layernorm"
|
| 335 |
+
],
|
| 336 |
+
[
|
| 337 |
+
"up_proj",
|
| 338 |
+
"tiled",
|
| 339 |
+
"layer.{L}.mlp.up_proj"
|
| 340 |
+
],
|
| 341 |
+
[
|
| 342 |
+
"activation",
|
| 343 |
+
"gelu"
|
| 344 |
+
],
|
| 345 |
+
[
|
| 346 |
+
"down_proj",
|
| 347 |
+
"tiled",
|
| 348 |
+
"layer.{L}.mlp.down_proj"
|
| 349 |
+
],
|
| 350 |
+
[
|
| 351 |
+
"ffn_residual",
|
| 352 |
+
"residual"
|
| 353 |
+
]
|
| 354 |
+
],
|
| 355 |
+
"prefill": [
|
| 356 |
+
[
|
| 357 |
+
"input_norm",
|
| 358 |
+
"layernorm"
|
| 359 |
+
],
|
| 360 |
+
[
|
| 361 |
+
"q_proj",
|
| 362 |
+
"tiled",
|
| 363 |
+
"layer.{L}.self_attn.q_proj"
|
| 364 |
+
],
|
| 365 |
+
[
|
| 366 |
+
"k_proj",
|
| 367 |
+
"tiled",
|
| 368 |
+
"layer.{L}.self_attn.k_proj"
|
| 369 |
+
],
|
| 370 |
+
[
|
| 371 |
+
"v_proj",
|
| 372 |
+
"tiled",
|
| 373 |
+
"layer.{L}.self_attn.v_proj"
|
| 374 |
+
],
|
| 375 |
+
[
|
| 376 |
+
"rope_q",
|
| 377 |
+
"rope"
|
| 378 |
+
],
|
| 379 |
+
[
|
| 380 |
+
"rope_k",
|
| 381 |
+
"rope"
|
| 382 |
+
],
|
| 383 |
+
[
|
| 384 |
+
"attention",
|
| 385 |
+
"attn_small"
|
| 386 |
+
],
|
| 387 |
+
[
|
| 388 |
+
"o_proj",
|
| 389 |
+
"tiled",
|
| 390 |
+
"layer.{L}.self_attn.o_proj"
|
| 391 |
+
],
|
| 392 |
+
[
|
| 393 |
+
"attn_residual",
|
| 394 |
+
"residual"
|
| 395 |
+
],
|
| 396 |
+
[
|
| 397 |
+
"post_attn_norm",
|
| 398 |
+
"layernorm"
|
| 399 |
+
],
|
| 400 |
+
[
|
| 401 |
+
"up_proj",
|
| 402 |
+
"tiled",
|
| 403 |
+
"layer.{L}.mlp.up_proj"
|
| 404 |
+
],
|
| 405 |
+
[
|
| 406 |
+
"activation",
|
| 407 |
+
"gelu"
|
| 408 |
+
],
|
| 409 |
+
[
|
| 410 |
+
"down_proj",
|
| 411 |
+
"tiled",
|
| 412 |
+
"layer.{L}.mlp.down_proj"
|
| 413 |
+
],
|
| 414 |
+
[
|
| 415 |
+
"ffn_residual",
|
| 416 |
+
"residual"
|
| 417 |
+
]
|
| 418 |
+
],
|
| 419 |
+
"postLayer": [
|
| 420 |
+
[
|
| 421 |
+
"final_norm",
|
| 422 |
+
"layernorm"
|
| 423 |
+
]
|
| 424 |
+
],
|
| 425 |
+
"sampling": null
|
| 426 |
+
}
|
| 427 |
+
},
|
| 428 |
+
"shards": [
|
| 429 |
+
{
|
| 430 |
+
"index": 0,
|
| 431 |
+
"filename": "shard_00000.bin",
|
| 432 |
+
"size": 67108864,
|
| 433 |
+
"hash": "14b1ea87844c6011f07b0e805b657aee77ec4db1fec998ab17de787d9c7ec8f0",
|
| 434 |
+
"offset": 0
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"index": 1,
|
| 438 |
+
"filename": "shard_00001.bin",
|
| 439 |
+
"size": 65968256,
|
| 440 |
+
"hash": "2e4936c7023d2b61bd8e3f36116a3a80003d8698f705dc4958eeadaad8c45a57",
|
| 441 |
+
"offset": 67108864
|
| 442 |
+
}
|
| 443 |
+
],
|
| 444 |
+
"tensors": {
|
| 445 |
+
"model.embed_tokens.weight": {
|
| 446 |
+
"shard": 0,
|
| 447 |
+
"offset": 0,
|
| 448 |
+
"size": 63360,
|
| 449 |
+
"shape": [
|
| 450 |
+
33,
|
| 451 |
+
480
|
| 452 |
+
],
|
| 453 |
+
"dtype": "F32",
|
| 454 |
+
"role": "embedding",
|
| 455 |
+
"group": "embed"
|
| 456 |
+
},
|
| 457 |
+
"model.norm.bias": {
|
| 458 |
+
"shard": 0,
|
| 459 |
+
"offset": 63360,
|
| 460 |
+
"size": 1920,
|
| 461 |
+
"shape": [
|
| 462 |
+
480
|
| 463 |
+
],
|
| 464 |
+
"dtype": "F32",
|
| 465 |
+
"role": "other",
|
| 466 |
+
"group": "head"
|
| 467 |
+
},
|
| 468 |
+
"model.norm.weight": {
|
| 469 |
+
"shard": 0,
|
| 470 |
+
"offset": 65280,
|
| 471 |
+
"size": 1920,
|
| 472 |
+
"shape": [
|
| 473 |
+
480
|
| 474 |
+
],
|
| 475 |
+
"dtype": "F32",
|
| 476 |
+
"role": "norm",
|
| 477 |
+
"group": "head"
|
| 478 |
+
},
|
| 479 |
+
"model.layers.0.post_attention_layernorm.bias": {
|
| 480 |
+
"shard": 0,
|
| 481 |
+
"offset": 67200,
|
| 482 |
+
"size": 1920,
|
| 483 |
+
"shape": [
|
| 484 |
+
480
|
| 485 |
+
],
|
| 486 |
+
"dtype": "F32",
|
| 487 |
+
"role": "norm",
|
| 488 |
+
"group": "layer.0"
|
| 489 |
+
},
|
| 490 |
+
"model.layers.0.post_attention_layernorm.weight": {
|
| 491 |
+
"shard": 0,
|
| 492 |
+
"offset": 69120,
|
| 493 |
+
"size": 1920,
|
| 494 |
+
"shape": [
|
| 495 |
+
480
|
| 496 |
+
],
|
| 497 |
+
"dtype": "F32",
|
| 498 |
+
"role": "norm",
|
| 499 |
+
"group": "layer.0"
|
| 500 |
+
},
|
| 501 |
+
"model.layers.0.input_layernorm.bias": {
|
| 502 |
+
"shard": 0,
|
| 503 |
+
"offset": 71040,
|
| 504 |
+
"size": 1920,
|
| 505 |
+
"shape": [
|
| 506 |
+
480
|
| 507 |
+
],
|
| 508 |
+
"dtype": "F32",
|
| 509 |
+
"role": "norm",
|
| 510 |
+
"group": "layer.0"
|
| 511 |
+
},
|
| 512 |
+
"model.layers.0.input_layernorm.weight": {
|
| 513 |
+
"shard": 0,
|
| 514 |
+
"offset": 72960,
|
| 515 |
+
"size": 1920,
|
| 516 |
+
"shape": [
|
| 517 |
+
480
|
| 518 |
+
],
|
| 519 |
+
"dtype": "F32",
|
| 520 |
+
"role": "norm",
|
| 521 |
+
"group": "layer.0"
|
| 522 |
+
},
|
| 523 |
+
"model.layers.0.self_attn.o_proj.bias": {
|
| 524 |
+
"shard": 0,
|
| 525 |
+
"offset": 74880,
|
| 526 |
+
"size": 1920,
|
| 527 |
+
"shape": [
|
| 528 |
+
480
|
| 529 |
+
],
|
| 530 |
+
"dtype": "F32",
|
| 531 |
+
"role": "other",
|
| 532 |
+
"group": "layer.0"
|
| 533 |
+
},
|
| 534 |
+
"model.layers.0.self_attn.o_proj.weight": {
|
| 535 |
+
"shard": 0,
|
| 536 |
+
"offset": 76800,
|
| 537 |
+
"size": 921600,
|
| 538 |
+
"shape": [
|
| 539 |
+
480,
|
| 540 |
+
480
|
| 541 |
+
],
|
| 542 |
+
"dtype": "F32",
|
| 543 |
+
"role": "matmul",
|
| 544 |
+
"group": "layer.0"
|
| 545 |
+
},
|
| 546 |
+
"model.layers.0.self_attn.k_proj.bias": {
|
| 547 |
+
"shard": 0,
|
| 548 |
+
"offset": 998400,
|
| 549 |
+
"size": 1920,
|
| 550 |
+
"shape": [
|
| 551 |
+
480
|
| 552 |
+
],
|
| 553 |
+
"dtype": "F32",
|
| 554 |
+
"role": "other",
|
| 555 |
+
"group": "layer.0"
|
| 556 |
+
},
|
| 557 |
+
"model.layers.0.self_attn.k_proj.weight": {
|
| 558 |
+
"shard": 0,
|
| 559 |
+
"offset": 1000320,
|
| 560 |
+
"size": 921600,
|
| 561 |
+
"shape": [
|
| 562 |
+
480,
|
| 563 |
+
480
|
| 564 |
+
],
|
| 565 |
+
"dtype": "F32",
|
| 566 |
+
"role": "matmul",
|
| 567 |
+
"group": "layer.0"
|
| 568 |
+
},
|
| 569 |
+
"model.layers.0.self_attn.q_proj.bias": {
|
| 570 |
+
"shard": 0,
|
| 571 |
+
"offset": 1921920,
|
| 572 |
+
"size": 1920,
|
| 573 |
+
"shape": [
|
| 574 |
+
480
|
| 575 |
+
],
|
| 576 |
+
"dtype": "F32",
|
| 577 |
+
"role": "other",
|
| 578 |
+
"group": "layer.0"
|
| 579 |
+
},
|
| 580 |
+
"model.layers.0.self_attn.q_proj.weight": {
|
| 581 |
+
"shard": 0,
|
| 582 |
+
"offset": 1923840,
|
| 583 |
+
"size": 921600,
|
| 584 |
+
"shape": [
|
| 585 |
+
480,
|
| 586 |
+
480
|
| 587 |
+
],
|
| 588 |
+
"dtype": "F32",
|
| 589 |
+
"role": "matmul",
|
| 590 |
+
"group": "layer.0"
|
| 591 |
+
},
|
| 592 |
+
"model.layers.0.self_attn.v_proj.bias": {
|
| 593 |
+
"shard": 0,
|
| 594 |
+
"offset": 2845440,
|
| 595 |
+
"size": 1920,
|
| 596 |
+
"shape": [
|
| 597 |
+
480
|
| 598 |
+
],
|
| 599 |
+
"dtype": "F32",
|
| 600 |
+
"role": "other",
|
| 601 |
+
"group": "layer.0"
|
| 602 |
+
},
|
| 603 |
+
"model.layers.0.self_attn.v_proj.weight": {
|
| 604 |
+
"shard": 0,
|
| 605 |
+
"offset": 2847360,
|
| 606 |
+
"size": 921600,
|
| 607 |
+
"shape": [
|
| 608 |
+
480,
|
| 609 |
+
480
|
| 610 |
+
],
|
| 611 |
+
"dtype": "F32",
|
| 612 |
+
"role": "matmul",
|
| 613 |
+
"group": "layer.0"
|
| 614 |
+
},
|
| 615 |
+
"model.layers.0.mlp.up_proj.bias": {
|
| 616 |
+
"shard": 0,
|
| 617 |
+
"offset": 3768960,
|
| 618 |
+
"size": 7680,
|
| 619 |
+
"shape": [
|
| 620 |
+
1920
|
| 621 |
+
],
|
| 622 |
+
"dtype": "F32",
|
| 623 |
+
"role": "other",
|
| 624 |
+
"group": "layer.0"
|
| 625 |
+
},
|
| 626 |
+
"model.layers.0.mlp.up_proj.weight": {
|
| 627 |
+
"shard": 0,
|
| 628 |
+
"offset": 3776640,
|
| 629 |
+
"size": 3686400,
|
| 630 |
+
"shape": [
|
| 631 |
+
1920,
|
| 632 |
+
480
|
| 633 |
+
],
|
| 634 |
+
"dtype": "F32",
|
| 635 |
+
"role": "matmul",
|
| 636 |
+
"group": "layer.0"
|
| 637 |
+
},
|
| 638 |
+
"model.layers.0.mlp.down_proj.bias": {
|
| 639 |
+
"shard": 0,
|
| 640 |
+
"offset": 7463040,
|
| 641 |
+
"size": 1920,
|
| 642 |
+
"shape": [
|
| 643 |
+
480
|
| 644 |
+
],
|
| 645 |
+
"dtype": "F32",
|
| 646 |
+
"role": "other",
|
| 647 |
+
"group": "layer.0"
|
| 648 |
+
},
|
| 649 |
+
"model.layers.0.mlp.down_proj.weight": {
|
| 650 |
+
"shard": 0,
|
| 651 |
+
"offset": 7464960,
|
| 652 |
+
"size": 3686400,
|
| 653 |
+
"shape": [
|
| 654 |
+
480,
|
| 655 |
+
1920
|
| 656 |
+
],
|
| 657 |
+
"dtype": "F32",
|
| 658 |
+
"role": "matmul",
|
| 659 |
+
"group": "layer.0"
|
| 660 |
+
},
|
| 661 |
+
"model.layers.1.post_attention_layernorm.bias": {
|
| 662 |
+
"shard": 0,
|
| 663 |
+
"offset": 11151360,
|
| 664 |
+
"size": 1920,
|
| 665 |
+
"shape": [
|
| 666 |
+
480
|
| 667 |
+
],
|
| 668 |
+
"dtype": "F32",
|
| 669 |
+
"role": "norm",
|
| 670 |
+
"group": "layer.1"
|
| 671 |
+
},
|
| 672 |
+
"model.layers.1.post_attention_layernorm.weight": {
|
| 673 |
+
"shard": 0,
|
| 674 |
+
"offset": 11153280,
|
| 675 |
+
"size": 1920,
|
| 676 |
+
"shape": [
|
| 677 |
+
480
|
| 678 |
+
],
|
| 679 |
+
"dtype": "F32",
|
| 680 |
+
"role": "norm",
|
| 681 |
+
"group": "layer.1"
|
| 682 |
+
},
|
| 683 |
+
"model.layers.1.input_layernorm.bias": {
|
| 684 |
+
"shard": 0,
|
| 685 |
+
"offset": 11155200,
|
| 686 |
+
"size": 1920,
|
| 687 |
+
"shape": [
|
| 688 |
+
480
|
| 689 |
+
],
|
| 690 |
+
"dtype": "F32",
|
| 691 |
+
"role": "norm",
|
| 692 |
+
"group": "layer.1"
|
| 693 |
+
},
|
| 694 |
+
"model.layers.1.input_layernorm.weight": {
|
| 695 |
+
"shard": 0,
|
| 696 |
+
"offset": 11157120,
|
| 697 |
+
"size": 1920,
|
| 698 |
+
"shape": [
|
| 699 |
+
480
|
| 700 |
+
],
|
| 701 |
+
"dtype": "F32",
|
| 702 |
+
"role": "norm",
|
| 703 |
+
"group": "layer.1"
|
| 704 |
+
},
|
| 705 |
+
"model.layers.1.self_attn.o_proj.bias": {
|
| 706 |
+
"shard": 0,
|
| 707 |
+
"offset": 11159040,
|
| 708 |
+
"size": 1920,
|
| 709 |
+
"shape": [
|
| 710 |
+
480
|
| 711 |
+
],
|
| 712 |
+
"dtype": "F32",
|
| 713 |
+
"role": "other",
|
| 714 |
+
"group": "layer.1"
|
| 715 |
+
},
|
| 716 |
+
"model.layers.1.self_attn.o_proj.weight": {
|
| 717 |
+
"shard": 0,
|
| 718 |
+
"offset": 11160960,
|
| 719 |
+
"size": 921600,
|
| 720 |
+
"shape": [
|
| 721 |
+
480,
|
| 722 |
+
480
|
| 723 |
+
],
|
| 724 |
+
"dtype": "F32",
|
| 725 |
+
"role": "matmul",
|
| 726 |
+
"group": "layer.1"
|
| 727 |
+
},
|
| 728 |
+
"model.layers.1.self_attn.k_proj.bias": {
|
| 729 |
+
"shard": 0,
|
| 730 |
+
"offset": 12082560,
|
| 731 |
+
"size": 1920,
|
| 732 |
+
"shape": [
|
| 733 |
+
480
|
| 734 |
+
],
|
| 735 |
+
"dtype": "F32",
|
| 736 |
+
"role": "other",
|
| 737 |
+
"group": "layer.1"
|
| 738 |
+
},
|
| 739 |
+
"model.layers.1.self_attn.k_proj.weight": {
|
| 740 |
+
"shard": 0,
|
| 741 |
+
"offset": 12084480,
|
| 742 |
+
"size": 921600,
|
| 743 |
+
"shape": [
|
| 744 |
+
480,
|
| 745 |
+
480
|
| 746 |
+
],
|
| 747 |
+
"dtype": "F32",
|
| 748 |
+
"role": "matmul",
|
| 749 |
+
"group": "layer.1"
|
| 750 |
+
},
|
| 751 |
+
"model.layers.1.self_attn.q_proj.bias": {
|
| 752 |
+
"shard": 0,
|
| 753 |
+
"offset": 13006080,
|
| 754 |
+
"size": 1920,
|
| 755 |
+
"shape": [
|
| 756 |
+
480
|
| 757 |
+
],
|
| 758 |
+
"dtype": "F32",
|
| 759 |
+
"role": "other",
|
| 760 |
+
"group": "layer.1"
|
| 761 |
+
},
|
| 762 |
+
"model.layers.1.self_attn.q_proj.weight": {
|
| 763 |
+
"shard": 0,
|
| 764 |
+
"offset": 13008000,
|
| 765 |
+
"size": 921600,
|
| 766 |
+
"shape": [
|
| 767 |
+
480,
|
| 768 |
+
480
|
| 769 |
+
],
|
| 770 |
+
"dtype": "F32",
|
| 771 |
+
"role": "matmul",
|
| 772 |
+
"group": "layer.1"
|
| 773 |
+
},
|
| 774 |
+
"model.layers.1.self_attn.v_proj.bias": {
|
| 775 |
+
"shard": 0,
|
| 776 |
+
"offset": 13929600,
|
| 777 |
+
"size": 1920,
|
| 778 |
+
"shape": [
|
| 779 |
+
480
|
| 780 |
+
],
|
| 781 |
+
"dtype": "F32",
|
| 782 |
+
"role": "other",
|
| 783 |
+
"group": "layer.1"
|
| 784 |
+
},
|
| 785 |
+
"model.layers.1.self_attn.v_proj.weight": {
|
| 786 |
+
"shard": 0,
|
| 787 |
+
"offset": 13931520,
|
| 788 |
+
"size": 921600,
|
| 789 |
+
"shape": [
|
| 790 |
+
480,
|
| 791 |
+
480
|
| 792 |
+
],
|
| 793 |
+
"dtype": "F32",
|
| 794 |
+
"role": "matmul",
|
| 795 |
+
"group": "layer.1"
|
| 796 |
+
},
|
| 797 |
+
"model.layers.1.mlp.up_proj.bias": {
|
| 798 |
+
"shard": 0,
|
| 799 |
+
"offset": 14853120,
|
| 800 |
+
"size": 7680,
|
| 801 |
+
"shape": [
|
| 802 |
+
1920
|
| 803 |
+
],
|
| 804 |
+
"dtype": "F32",
|
| 805 |
+
"role": "other",
|
| 806 |
+
"group": "layer.1"
|
| 807 |
+
},
|
| 808 |
+
"model.layers.1.mlp.up_proj.weight": {
|
| 809 |
+
"shard": 0,
|
| 810 |
+
"offset": 14860800,
|
| 811 |
+
"size": 3686400,
|
| 812 |
+
"shape": [
|
| 813 |
+
1920,
|
| 814 |
+
480
|
| 815 |
+
],
|
| 816 |
+
"dtype": "F32",
|
| 817 |
+
"role": "matmul",
|
| 818 |
+
"group": "layer.1"
|
| 819 |
+
},
|
| 820 |
+
"model.layers.1.mlp.down_proj.bias": {
|
| 821 |
+
"shard": 0,
|
| 822 |
+
"offset": 18547200,
|
| 823 |
+
"size": 1920,
|
| 824 |
+
"shape": [
|
| 825 |
+
480
|
| 826 |
+
],
|
| 827 |
+
"dtype": "F32",
|
| 828 |
+
"role": "other",
|
| 829 |
+
"group": "layer.1"
|
| 830 |
+
},
|
| 831 |
+
"model.layers.1.mlp.down_proj.weight": {
|
| 832 |
+
"shard": 0,
|
| 833 |
+
"offset": 18549120,
|
| 834 |
+
"size": 3686400,
|
| 835 |
+
"shape": [
|
| 836 |
+
480,
|
| 837 |
+
1920
|
| 838 |
+
],
|
| 839 |
+
"dtype": "F32",
|
| 840 |
+
"role": "matmul",
|
| 841 |
+
"group": "layer.1"
|
| 842 |
+
},
|
| 843 |
+
"model.layers.10.post_attention_layernorm.bias": {
|
| 844 |
+
"shard": 0,
|
| 845 |
+
"offset": 22235520,
|
| 846 |
+
"size": 1920,
|
| 847 |
+
"shape": [
|
| 848 |
+
480
|
| 849 |
+
],
|
| 850 |
+
"dtype": "F32",
|
| 851 |
+
"role": "norm",
|
| 852 |
+
"group": "layer.10"
|
| 853 |
+
},
|
| 854 |
+
"model.layers.10.post_attention_layernorm.weight": {
|
| 855 |
+
"shard": 0,
|
| 856 |
+
"offset": 22237440,
|
| 857 |
+
"size": 1920,
|
| 858 |
+
"shape": [
|
| 859 |
+
480
|
| 860 |
+
],
|
| 861 |
+
"dtype": "F32",
|
| 862 |
+
"role": "norm",
|
| 863 |
+
"group": "layer.10"
|
| 864 |
+
},
|
| 865 |
+
"model.layers.10.input_layernorm.bias": {
|
| 866 |
+
"shard": 0,
|
| 867 |
+
"offset": 22239360,
|
| 868 |
+
"size": 1920,
|
| 869 |
+
"shape": [
|
| 870 |
+
480
|
| 871 |
+
],
|
| 872 |
+
"dtype": "F32",
|
| 873 |
+
"role": "norm",
|
| 874 |
+
"group": "layer.10"
|
| 875 |
+
},
|
| 876 |
+
"model.layers.10.input_layernorm.weight": {
|
| 877 |
+
"shard": 0,
|
| 878 |
+
"offset": 22241280,
|
| 879 |
+
"size": 1920,
|
| 880 |
+
"shape": [
|
| 881 |
+
480
|
| 882 |
+
],
|
| 883 |
+
"dtype": "F32",
|
| 884 |
+
"role": "norm",
|
| 885 |
+
"group": "layer.10"
|
| 886 |
+
},
|
| 887 |
+
"model.layers.10.self_attn.o_proj.bias": {
|
| 888 |
+
"shard": 0,
|
| 889 |
+
"offset": 22243200,
|
| 890 |
+
"size": 1920,
|
| 891 |
+
"shape": [
|
| 892 |
+
480
|
| 893 |
+
],
|
| 894 |
+
"dtype": "F32",
|
| 895 |
+
"role": "other",
|
| 896 |
+
"group": "layer.10"
|
| 897 |
+
},
|
| 898 |
+
"model.layers.10.self_attn.o_proj.weight": {
|
| 899 |
+
"shard": 0,
|
| 900 |
+
"offset": 22245120,
|
| 901 |
+
"size": 921600,
|
| 902 |
+
"shape": [
|
| 903 |
+
480,
|
| 904 |
+
480
|
| 905 |
+
],
|
| 906 |
+
"dtype": "F32",
|
| 907 |
+
"role": "matmul",
|
| 908 |
+
"group": "layer.10"
|
| 909 |
+
},
|
| 910 |
+
"model.layers.10.self_attn.k_proj.bias": {
|
| 911 |
+
"shard": 0,
|
| 912 |
+
"offset": 23166720,
|
| 913 |
+
"size": 1920,
|
| 914 |
+
"shape": [
|
| 915 |
+
480
|
| 916 |
+
],
|
| 917 |
+
"dtype": "F32",
|
| 918 |
+
"role": "other",
|
| 919 |
+
"group": "layer.10"
|
| 920 |
+
},
|
| 921 |
+
"model.layers.10.self_attn.k_proj.weight": {
|
| 922 |
+
"shard": 0,
|
| 923 |
+
"offset": 23168640,
|
| 924 |
+
"size": 921600,
|
| 925 |
+
"shape": [
|
| 926 |
+
480,
|
| 927 |
+
480
|
| 928 |
+
],
|
| 929 |
+
"dtype": "F32",
|
| 930 |
+
"role": "matmul",
|
| 931 |
+
"group": "layer.10"
|
| 932 |
+
},
|
| 933 |
+
"model.layers.10.self_attn.q_proj.bias": {
|
| 934 |
+
"shard": 0,
|
| 935 |
+
"offset": 24090240,
|
| 936 |
+
"size": 1920,
|
| 937 |
+
"shape": [
|
| 938 |
+
480
|
| 939 |
+
],
|
| 940 |
+
"dtype": "F32",
|
| 941 |
+
"role": "other",
|
| 942 |
+
"group": "layer.10"
|
| 943 |
+
},
|
| 944 |
+
"model.layers.10.self_attn.q_proj.weight": {
|
| 945 |
+
"shard": 0,
|
| 946 |
+
"offset": 24092160,
|
| 947 |
+
"size": 921600,
|
| 948 |
+
"shape": [
|
| 949 |
+
480,
|
| 950 |
+
480
|
| 951 |
+
],
|
| 952 |
+
"dtype": "F32",
|
| 953 |
+
"role": "matmul",
|
| 954 |
+
"group": "layer.10"
|
| 955 |
+
},
|
| 956 |
+
"model.layers.10.self_attn.v_proj.bias": {
|
| 957 |
+
"shard": 0,
|
| 958 |
+
"offset": 25013760,
|
| 959 |
+
"size": 1920,
|
| 960 |
+
"shape": [
|
| 961 |
+
480
|
| 962 |
+
],
|
| 963 |
+
"dtype": "F32",
|
| 964 |
+
"role": "other",
|
| 965 |
+
"group": "layer.10"
|
| 966 |
+
},
|
| 967 |
+
"model.layers.10.self_attn.v_proj.weight": {
|
| 968 |
+
"shard": 0,
|
| 969 |
+
"offset": 25015680,
|
| 970 |
+
"size": 921600,
|
| 971 |
+
"shape": [
|
| 972 |
+
480,
|
| 973 |
+
480
|
| 974 |
+
],
|
| 975 |
+
"dtype": "F32",
|
| 976 |
+
"role": "matmul",
|
| 977 |
+
"group": "layer.10"
|
| 978 |
+
},
|
| 979 |
+
"model.layers.10.mlp.up_proj.bias": {
|
| 980 |
+
"shard": 0,
|
| 981 |
+
"offset": 25937280,
|
| 982 |
+
"size": 7680,
|
| 983 |
+
"shape": [
|
| 984 |
+
1920
|
| 985 |
+
],
|
| 986 |
+
"dtype": "F32",
|
| 987 |
+
"role": "other",
|
| 988 |
+
"group": "layer.10"
|
| 989 |
+
},
|
| 990 |
+
"model.layers.10.mlp.up_proj.weight": {
|
| 991 |
+
"shard": 0,
|
| 992 |
+
"offset": 25944960,
|
| 993 |
+
"size": 3686400,
|
| 994 |
+
"shape": [
|
| 995 |
+
1920,
|
| 996 |
+
480
|
| 997 |
+
],
|
| 998 |
+
"dtype": "F32",
|
| 999 |
+
"role": "matmul",
|
| 1000 |
+
"group": "layer.10"
|
| 1001 |
+
},
|
| 1002 |
+
"model.layers.10.mlp.down_proj.bias": {
|
| 1003 |
+
"shard": 0,
|
| 1004 |
+
"offset": 29631360,
|
| 1005 |
+
"size": 1920,
|
| 1006 |
+
"shape": [
|
| 1007 |
+
480
|
| 1008 |
+
],
|
| 1009 |
+
"dtype": "F32",
|
| 1010 |
+
"role": "other",
|
| 1011 |
+
"group": "layer.10"
|
| 1012 |
+
},
|
| 1013 |
+
"model.layers.10.mlp.down_proj.weight": {
|
| 1014 |
+
"shard": 0,
|
| 1015 |
+
"offset": 29633280,
|
| 1016 |
+
"size": 3686400,
|
| 1017 |
+
"shape": [
|
| 1018 |
+
480,
|
| 1019 |
+
1920
|
| 1020 |
+
],
|
| 1021 |
+
"dtype": "F32",
|
| 1022 |
+
"role": "matmul",
|
| 1023 |
+
"group": "layer.10"
|
| 1024 |
+
},
|
| 1025 |
+
"model.layers.11.post_attention_layernorm.bias": {
|
| 1026 |
+
"shard": 0,
|
| 1027 |
+
"offset": 33319680,
|
| 1028 |
+
"size": 1920,
|
| 1029 |
+
"shape": [
|
| 1030 |
+
480
|
| 1031 |
+
],
|
| 1032 |
+
"dtype": "F32",
|
| 1033 |
+
"role": "norm",
|
| 1034 |
+
"group": "layer.11"
|
| 1035 |
+
},
|
| 1036 |
+
"model.layers.11.post_attention_layernorm.weight": {
|
| 1037 |
+
"shard": 0,
|
| 1038 |
+
"offset": 33321600,
|
| 1039 |
+
"size": 1920,
|
| 1040 |
+
"shape": [
|
| 1041 |
+
480
|
| 1042 |
+
],
|
| 1043 |
+
"dtype": "F32",
|
| 1044 |
+
"role": "norm",
|
| 1045 |
+
"group": "layer.11"
|
| 1046 |
+
},
|
| 1047 |
+
"model.layers.11.input_layernorm.bias": {
|
| 1048 |
+
"shard": 0,
|
| 1049 |
+
"offset": 33323520,
|
| 1050 |
+
"size": 1920,
|
| 1051 |
+
"shape": [
|
| 1052 |
+
480
|
| 1053 |
+
],
|
| 1054 |
+
"dtype": "F32",
|
| 1055 |
+
"role": "norm",
|
| 1056 |
+
"group": "layer.11"
|
| 1057 |
+
},
|
| 1058 |
+
"model.layers.11.input_layernorm.weight": {
|
| 1059 |
+
"shard": 0,
|
| 1060 |
+
"offset": 33325440,
|
| 1061 |
+
"size": 1920,
|
| 1062 |
+
"shape": [
|
| 1063 |
+
480
|
| 1064 |
+
],
|
| 1065 |
+
"dtype": "F32",
|
| 1066 |
+
"role": "norm",
|
| 1067 |
+
"group": "layer.11"
|
| 1068 |
+
},
|
| 1069 |
+
"model.layers.11.self_attn.o_proj.bias": {
|
| 1070 |
+
"shard": 0,
|
| 1071 |
+
"offset": 33327360,
|
| 1072 |
+
"size": 1920,
|
| 1073 |
+
"shape": [
|
| 1074 |
+
480
|
| 1075 |
+
],
|
| 1076 |
+
"dtype": "F32",
|
| 1077 |
+
"role": "other",
|
| 1078 |
+
"group": "layer.11"
|
| 1079 |
+
},
|
| 1080 |
+
"model.layers.11.self_attn.o_proj.weight": {
|
| 1081 |
+
"shard": 0,
|
| 1082 |
+
"offset": 33329280,
|
| 1083 |
+
"size": 921600,
|
| 1084 |
+
"shape": [
|
| 1085 |
+
480,
|
| 1086 |
+
480
|
| 1087 |
+
],
|
| 1088 |
+
"dtype": "F32",
|
| 1089 |
+
"role": "matmul",
|
| 1090 |
+
"group": "layer.11"
|
| 1091 |
+
},
|
| 1092 |
+
"model.layers.11.self_attn.k_proj.bias": {
|
| 1093 |
+
"shard": 0,
|
| 1094 |
+
"offset": 34250880,
|
| 1095 |
+
"size": 1920,
|
| 1096 |
+
"shape": [
|
| 1097 |
+
480
|
| 1098 |
+
],
|
| 1099 |
+
"dtype": "F32",
|
| 1100 |
+
"role": "other",
|
| 1101 |
+
"group": "layer.11"
|
| 1102 |
+
},
|
| 1103 |
+
"model.layers.11.self_attn.k_proj.weight": {
|
| 1104 |
+
"shard": 0,
|
| 1105 |
+
"offset": 34252800,
|
| 1106 |
+
"size": 921600,
|
| 1107 |
+
"shape": [
|
| 1108 |
+
480,
|
| 1109 |
+
480
|
| 1110 |
+
],
|
| 1111 |
+
"dtype": "F32",
|
| 1112 |
+
"role": "matmul",
|
| 1113 |
+
"group": "layer.11"
|
| 1114 |
+
},
|
| 1115 |
+
"model.layers.11.self_attn.q_proj.bias": {
|
| 1116 |
+
"shard": 0,
|
| 1117 |
+
"offset": 35174400,
|
| 1118 |
+
"size": 1920,
|
| 1119 |
+
"shape": [
|
| 1120 |
+
480
|
| 1121 |
+
],
|
| 1122 |
+
"dtype": "F32",
|
| 1123 |
+
"role": "other",
|
| 1124 |
+
"group": "layer.11"
|
| 1125 |
+
},
|
| 1126 |
+
"model.layers.11.self_attn.q_proj.weight": {
|
| 1127 |
+
"shard": 0,
|
| 1128 |
+
"offset": 35176320,
|
| 1129 |
+
"size": 921600,
|
| 1130 |
+
"shape": [
|
| 1131 |
+
480,
|
| 1132 |
+
480
|
| 1133 |
+
],
|
| 1134 |
+
"dtype": "F32",
|
| 1135 |
+
"role": "matmul",
|
| 1136 |
+
"group": "layer.11"
|
| 1137 |
+
},
|
| 1138 |
+
"model.layers.11.self_attn.v_proj.bias": {
|
| 1139 |
+
"shard": 0,
|
| 1140 |
+
"offset": 36097920,
|
| 1141 |
+
"size": 1920,
|
| 1142 |
+
"shape": [
|
| 1143 |
+
480
|
| 1144 |
+
],
|
| 1145 |
+
"dtype": "F32",
|
| 1146 |
+
"role": "other",
|
| 1147 |
+
"group": "layer.11"
|
| 1148 |
+
},
|
| 1149 |
+
"model.layers.11.self_attn.v_proj.weight": {
|
| 1150 |
+
"shard": 0,
|
| 1151 |
+
"offset": 36099840,
|
| 1152 |
+
"size": 921600,
|
| 1153 |
+
"shape": [
|
| 1154 |
+
480,
|
| 1155 |
+
480
|
| 1156 |
+
],
|
| 1157 |
+
"dtype": "F32",
|
| 1158 |
+
"role": "matmul",
|
| 1159 |
+
"group": "layer.11"
|
| 1160 |
+
},
|
| 1161 |
+
"model.layers.11.mlp.up_proj.bias": {
|
| 1162 |
+
"shard": 0,
|
| 1163 |
+
"offset": 37021440,
|
| 1164 |
+
"size": 7680,
|
| 1165 |
+
"shape": [
|
| 1166 |
+
1920
|
| 1167 |
+
],
|
| 1168 |
+
"dtype": "F32",
|
| 1169 |
+
"role": "other",
|
| 1170 |
+
"group": "layer.11"
|
| 1171 |
+
},
|
| 1172 |
+
"model.layers.11.mlp.up_proj.weight": {
|
| 1173 |
+
"shard": 0,
|
| 1174 |
+
"offset": 37029120,
|
| 1175 |
+
"size": 3686400,
|
| 1176 |
+
"shape": [
|
| 1177 |
+
1920,
|
| 1178 |
+
480
|
| 1179 |
+
],
|
| 1180 |
+
"dtype": "F32",
|
| 1181 |
+
"role": "matmul",
|
| 1182 |
+
"group": "layer.11"
|
| 1183 |
+
},
|
| 1184 |
+
"model.layers.11.mlp.down_proj.bias": {
|
| 1185 |
+
"shard": 0,
|
| 1186 |
+
"offset": 40715520,
|
| 1187 |
+
"size": 1920,
|
| 1188 |
+
"shape": [
|
| 1189 |
+
480
|
| 1190 |
+
],
|
| 1191 |
+
"dtype": "F32",
|
| 1192 |
+
"role": "other",
|
| 1193 |
+
"group": "layer.11"
|
| 1194 |
+
},
|
| 1195 |
+
"model.layers.11.mlp.down_proj.weight": {
|
| 1196 |
+
"shard": 0,
|
| 1197 |
+
"offset": 40717440,
|
| 1198 |
+
"size": 3686400,
|
| 1199 |
+
"shape": [
|
| 1200 |
+
480,
|
| 1201 |
+
1920
|
| 1202 |
+
],
|
| 1203 |
+
"dtype": "F32",
|
| 1204 |
+
"role": "matmul",
|
| 1205 |
+
"group": "layer.11"
|
| 1206 |
+
},
|
| 1207 |
+
"model.layers.2.post_attention_layernorm.bias": {
|
| 1208 |
+
"shard": 0,
|
| 1209 |
+
"offset": 44403840,
|
| 1210 |
+
"size": 1920,
|
| 1211 |
+
"shape": [
|
| 1212 |
+
480
|
| 1213 |
+
],
|
| 1214 |
+
"dtype": "F32",
|
| 1215 |
+
"role": "norm",
|
| 1216 |
+
"group": "layer.2"
|
| 1217 |
+
},
|
| 1218 |
+
"model.layers.2.post_attention_layernorm.weight": {
|
| 1219 |
+
"shard": 0,
|
| 1220 |
+
"offset": 44405760,
|
| 1221 |
+
"size": 1920,
|
| 1222 |
+
"shape": [
|
| 1223 |
+
480
|
| 1224 |
+
],
|
| 1225 |
+
"dtype": "F32",
|
| 1226 |
+
"role": "norm",
|
| 1227 |
+
"group": "layer.2"
|
| 1228 |
+
},
|
| 1229 |
+
"model.layers.2.input_layernorm.bias": {
|
| 1230 |
+
"shard": 0,
|
| 1231 |
+
"offset": 44407680,
|
| 1232 |
+
"size": 1920,
|
| 1233 |
+
"shape": [
|
| 1234 |
+
480
|
| 1235 |
+
],
|
| 1236 |
+
"dtype": "F32",
|
| 1237 |
+
"role": "norm",
|
| 1238 |
+
"group": "layer.2"
|
| 1239 |
+
},
|
| 1240 |
+
"model.layers.2.input_layernorm.weight": {
|
| 1241 |
+
"shard": 0,
|
| 1242 |
+
"offset": 44409600,
|
| 1243 |
+
"size": 1920,
|
| 1244 |
+
"shape": [
|
| 1245 |
+
480
|
| 1246 |
+
],
|
| 1247 |
+
"dtype": "F32",
|
| 1248 |
+
"role": "norm",
|
| 1249 |
+
"group": "layer.2"
|
| 1250 |
+
},
|
| 1251 |
+
"model.layers.2.self_attn.o_proj.bias": {
|
| 1252 |
+
"shard": 0,
|
| 1253 |
+
"offset": 44411520,
|
| 1254 |
+
"size": 1920,
|
| 1255 |
+
"shape": [
|
| 1256 |
+
480
|
| 1257 |
+
],
|
| 1258 |
+
"dtype": "F32",
|
| 1259 |
+
"role": "other",
|
| 1260 |
+
"group": "layer.2"
|
| 1261 |
+
},
|
| 1262 |
+
"model.layers.2.self_attn.o_proj.weight": {
|
| 1263 |
+
"shard": 0,
|
| 1264 |
+
"offset": 44413440,
|
| 1265 |
+
"size": 921600,
|
| 1266 |
+
"shape": [
|
| 1267 |
+
480,
|
| 1268 |
+
480
|
| 1269 |
+
],
|
| 1270 |
+
"dtype": "F32",
|
| 1271 |
+
"role": "matmul",
|
| 1272 |
+
"group": "layer.2"
|
| 1273 |
+
},
|
| 1274 |
+
"model.layers.2.self_attn.k_proj.bias": {
|
| 1275 |
+
"shard": 0,
|
| 1276 |
+
"offset": 45335040,
|
| 1277 |
+
"size": 1920,
|
| 1278 |
+
"shape": [
|
| 1279 |
+
480
|
| 1280 |
+
],
|
| 1281 |
+
"dtype": "F32",
|
| 1282 |
+
"role": "other",
|
| 1283 |
+
"group": "layer.2"
|
| 1284 |
+
},
|
| 1285 |
+
"model.layers.2.self_attn.k_proj.weight": {
|
| 1286 |
+
"shard": 0,
|
| 1287 |
+
"offset": 45336960,
|
| 1288 |
+
"size": 921600,
|
| 1289 |
+
"shape": [
|
| 1290 |
+
480,
|
| 1291 |
+
480
|
| 1292 |
+
],
|
| 1293 |
+
"dtype": "F32",
|
| 1294 |
+
"role": "matmul",
|
| 1295 |
+
"group": "layer.2"
|
| 1296 |
+
},
|
| 1297 |
+
"model.layers.2.self_attn.q_proj.bias": {
|
| 1298 |
+
"shard": 0,
|
| 1299 |
+
"offset": 46258560,
|
| 1300 |
+
"size": 1920,
|
| 1301 |
+
"shape": [
|
| 1302 |
+
480
|
| 1303 |
+
],
|
| 1304 |
+
"dtype": "F32",
|
| 1305 |
+
"role": "other",
|
| 1306 |
+
"group": "layer.2"
|
| 1307 |
+
},
|
| 1308 |
+
"model.layers.2.self_attn.q_proj.weight": {
|
| 1309 |
+
"shard": 0,
|
| 1310 |
+
"offset": 46260480,
|
| 1311 |
+
"size": 921600,
|
| 1312 |
+
"shape": [
|
| 1313 |
+
480,
|
| 1314 |
+
480
|
| 1315 |
+
],
|
| 1316 |
+
"dtype": "F32",
|
| 1317 |
+
"role": "matmul",
|
| 1318 |
+
"group": "layer.2"
|
| 1319 |
+
},
|
| 1320 |
+
"model.layers.2.self_attn.v_proj.bias": {
|
| 1321 |
+
"shard": 0,
|
| 1322 |
+
"offset": 47182080,
|
| 1323 |
+
"size": 1920,
|
| 1324 |
+
"shape": [
|
| 1325 |
+
480
|
| 1326 |
+
],
|
| 1327 |
+
"dtype": "F32",
|
| 1328 |
+
"role": "other",
|
| 1329 |
+
"group": "layer.2"
|
| 1330 |
+
},
|
| 1331 |
+
"model.layers.2.self_attn.v_proj.weight": {
|
| 1332 |
+
"shard": 0,
|
| 1333 |
+
"offset": 47184000,
|
| 1334 |
+
"size": 921600,
|
| 1335 |
+
"shape": [
|
| 1336 |
+
480,
|
| 1337 |
+
480
|
| 1338 |
+
],
|
| 1339 |
+
"dtype": "F32",
|
| 1340 |
+
"role": "matmul",
|
| 1341 |
+
"group": "layer.2"
|
| 1342 |
+
},
|
| 1343 |
+
"model.layers.2.mlp.up_proj.bias": {
|
| 1344 |
+
"shard": 0,
|
| 1345 |
+
"offset": 48105600,
|
| 1346 |
+
"size": 7680,
|
| 1347 |
+
"shape": [
|
| 1348 |
+
1920
|
| 1349 |
+
],
|
| 1350 |
+
"dtype": "F32",
|
| 1351 |
+
"role": "other",
|
| 1352 |
+
"group": "layer.2"
|
| 1353 |
+
},
|
| 1354 |
+
"model.layers.2.mlp.up_proj.weight": {
|
| 1355 |
+
"shard": 0,
|
| 1356 |
+
"offset": 48113280,
|
| 1357 |
+
"size": 3686400,
|
| 1358 |
+
"shape": [
|
| 1359 |
+
1920,
|
| 1360 |
+
480
|
| 1361 |
+
],
|
| 1362 |
+
"dtype": "F32",
|
| 1363 |
+
"role": "matmul",
|
| 1364 |
+
"group": "layer.2"
|
| 1365 |
+
},
|
| 1366 |
+
"model.layers.2.mlp.down_proj.bias": {
|
| 1367 |
+
"shard": 0,
|
| 1368 |
+
"offset": 51799680,
|
| 1369 |
+
"size": 1920,
|
| 1370 |
+
"shape": [
|
| 1371 |
+
480
|
| 1372 |
+
],
|
| 1373 |
+
"dtype": "F32",
|
| 1374 |
+
"role": "other",
|
| 1375 |
+
"group": "layer.2"
|
| 1376 |
+
},
|
| 1377 |
+
"model.layers.2.mlp.down_proj.weight": {
|
| 1378 |
+
"shard": 0,
|
| 1379 |
+
"offset": 51801600,
|
| 1380 |
+
"size": 3686400,
|
| 1381 |
+
"shape": [
|
| 1382 |
+
480,
|
| 1383 |
+
1920
|
| 1384 |
+
],
|
| 1385 |
+
"dtype": "F32",
|
| 1386 |
+
"role": "matmul",
|
| 1387 |
+
"group": "layer.2"
|
| 1388 |
+
},
|
| 1389 |
+
"model.layers.3.post_attention_layernorm.bias": {
|
| 1390 |
+
"shard": 0,
|
| 1391 |
+
"offset": 55488000,
|
| 1392 |
+
"size": 1920,
|
| 1393 |
+
"shape": [
|
| 1394 |
+
480
|
| 1395 |
+
],
|
| 1396 |
+
"dtype": "F32",
|
| 1397 |
+
"role": "norm",
|
| 1398 |
+
"group": "layer.3"
|
| 1399 |
+
},
|
| 1400 |
+
"model.layers.3.post_attention_layernorm.weight": {
|
| 1401 |
+
"shard": 0,
|
| 1402 |
+
"offset": 55489920,
|
| 1403 |
+
"size": 1920,
|
| 1404 |
+
"shape": [
|
| 1405 |
+
480
|
| 1406 |
+
],
|
| 1407 |
+
"dtype": "F32",
|
| 1408 |
+
"role": "norm",
|
| 1409 |
+
"group": "layer.3"
|
| 1410 |
+
},
|
| 1411 |
+
"model.layers.3.input_layernorm.bias": {
|
| 1412 |
+
"shard": 0,
|
| 1413 |
+
"offset": 55491840,
|
| 1414 |
+
"size": 1920,
|
| 1415 |
+
"shape": [
|
| 1416 |
+
480
|
| 1417 |
+
],
|
| 1418 |
+
"dtype": "F32",
|
| 1419 |
+
"role": "norm",
|
| 1420 |
+
"group": "layer.3"
|
| 1421 |
+
},
|
| 1422 |
+
"model.layers.3.input_layernorm.weight": {
|
| 1423 |
+
"shard": 0,
|
| 1424 |
+
"offset": 55493760,
|
| 1425 |
+
"size": 1920,
|
| 1426 |
+
"shape": [
|
| 1427 |
+
480
|
| 1428 |
+
],
|
| 1429 |
+
"dtype": "F32",
|
| 1430 |
+
"role": "norm",
|
| 1431 |
+
"group": "layer.3"
|
| 1432 |
+
},
|
| 1433 |
+
"model.layers.3.self_attn.o_proj.bias": {
|
| 1434 |
+
"shard": 0,
|
| 1435 |
+
"offset": 55495680,
|
| 1436 |
+
"size": 1920,
|
| 1437 |
+
"shape": [
|
| 1438 |
+
480
|
| 1439 |
+
],
|
| 1440 |
+
"dtype": "F32",
|
| 1441 |
+
"role": "other",
|
| 1442 |
+
"group": "layer.3"
|
| 1443 |
+
},
|
| 1444 |
+
"model.layers.3.self_attn.o_proj.weight": {
|
| 1445 |
+
"shard": 0,
|
| 1446 |
+
"offset": 55497600,
|
| 1447 |
+
"size": 921600,
|
| 1448 |
+
"shape": [
|
| 1449 |
+
480,
|
| 1450 |
+
480
|
| 1451 |
+
],
|
| 1452 |
+
"dtype": "F32",
|
| 1453 |
+
"role": "matmul",
|
| 1454 |
+
"group": "layer.3"
|
| 1455 |
+
},
|
| 1456 |
+
"model.layers.3.self_attn.k_proj.bias": {
|
| 1457 |
+
"shard": 0,
|
| 1458 |
+
"offset": 56419200,
|
| 1459 |
+
"size": 1920,
|
| 1460 |
+
"shape": [
|
| 1461 |
+
480
|
| 1462 |
+
],
|
| 1463 |
+
"dtype": "F32",
|
| 1464 |
+
"role": "other",
|
| 1465 |
+
"group": "layer.3"
|
| 1466 |
+
},
|
| 1467 |
+
"model.layers.3.self_attn.k_proj.weight": {
|
| 1468 |
+
"shard": 0,
|
| 1469 |
+
"offset": 56421120,
|
| 1470 |
+
"size": 921600,
|
| 1471 |
+
"shape": [
|
| 1472 |
+
480,
|
| 1473 |
+
480
|
| 1474 |
+
],
|
| 1475 |
+
"dtype": "F32",
|
| 1476 |
+
"role": "matmul",
|
| 1477 |
+
"group": "layer.3"
|
| 1478 |
+
},
|
| 1479 |
+
"model.layers.3.self_attn.q_proj.bias": {
|
| 1480 |
+
"shard": 0,
|
| 1481 |
+
"offset": 57342720,
|
| 1482 |
+
"size": 1920,
|
| 1483 |
+
"shape": [
|
| 1484 |
+
480
|
| 1485 |
+
],
|
| 1486 |
+
"dtype": "F32",
|
| 1487 |
+
"role": "other",
|
| 1488 |
+
"group": "layer.3"
|
| 1489 |
+
},
|
| 1490 |
+
"model.layers.3.self_attn.q_proj.weight": {
|
| 1491 |
+
"shard": 0,
|
| 1492 |
+
"offset": 57344640,
|
| 1493 |
+
"size": 921600,
|
| 1494 |
+
"shape": [
|
| 1495 |
+
480,
|
| 1496 |
+
480
|
| 1497 |
+
],
|
| 1498 |
+
"dtype": "F32",
|
| 1499 |
+
"role": "matmul",
|
| 1500 |
+
"group": "layer.3"
|
| 1501 |
+
},
|
| 1502 |
+
"model.layers.3.self_attn.v_proj.bias": {
|
| 1503 |
+
"shard": 0,
|
| 1504 |
+
"offset": 58266240,
|
| 1505 |
+
"size": 1920,
|
| 1506 |
+
"shape": [
|
| 1507 |
+
480
|
| 1508 |
+
],
|
| 1509 |
+
"dtype": "F32",
|
| 1510 |
+
"role": "other",
|
| 1511 |
+
"group": "layer.3"
|
| 1512 |
+
},
|
| 1513 |
+
"model.layers.3.self_attn.v_proj.weight": {
|
| 1514 |
+
"shard": 0,
|
| 1515 |
+
"offset": 58268160,
|
| 1516 |
+
"size": 921600,
|
| 1517 |
+
"shape": [
|
| 1518 |
+
480,
|
| 1519 |
+
480
|
| 1520 |
+
],
|
| 1521 |
+
"dtype": "F32",
|
| 1522 |
+
"role": "matmul",
|
| 1523 |
+
"group": "layer.3"
|
| 1524 |
+
},
|
| 1525 |
+
"model.layers.3.mlp.up_proj.bias": {
|
| 1526 |
+
"shard": 0,
|
| 1527 |
+
"offset": 59189760,
|
| 1528 |
+
"size": 7680,
|
| 1529 |
+
"shape": [
|
| 1530 |
+
1920
|
| 1531 |
+
],
|
| 1532 |
+
"dtype": "F32",
|
| 1533 |
+
"role": "other",
|
| 1534 |
+
"group": "layer.3"
|
| 1535 |
+
},
|
| 1536 |
+
"model.layers.3.mlp.up_proj.weight": {
|
| 1537 |
+
"shard": 0,
|
| 1538 |
+
"offset": 59197440,
|
| 1539 |
+
"size": 3686400,
|
| 1540 |
+
"shape": [
|
| 1541 |
+
1920,
|
| 1542 |
+
480
|
| 1543 |
+
],
|
| 1544 |
+
"dtype": "F32",
|
| 1545 |
+
"role": "matmul",
|
| 1546 |
+
"group": "layer.3"
|
| 1547 |
+
},
|
| 1548 |
+
"model.layers.3.mlp.down_proj.bias": {
|
| 1549 |
+
"shard": 0,
|
| 1550 |
+
"offset": 62883840,
|
| 1551 |
+
"size": 1920,
|
| 1552 |
+
"shape": [
|
| 1553 |
+
480
|
| 1554 |
+
],
|
| 1555 |
+
"dtype": "F32",
|
| 1556 |
+
"role": "other",
|
| 1557 |
+
"group": "layer.3"
|
| 1558 |
+
},
|
| 1559 |
+
"model.layers.3.mlp.down_proj.weight": {
|
| 1560 |
+
"shard": 0,
|
| 1561 |
+
"offset": 62885760,
|
| 1562 |
+
"size": 3686400,
|
| 1563 |
+
"shape": [
|
| 1564 |
+
480,
|
| 1565 |
+
1920
|
| 1566 |
+
],
|
| 1567 |
+
"dtype": "F32",
|
| 1568 |
+
"role": "matmul",
|
| 1569 |
+
"group": "layer.3"
|
| 1570 |
+
},
|
| 1571 |
+
"model.layers.4.post_attention_layernorm.bias": {
|
| 1572 |
+
"shard": 0,
|
| 1573 |
+
"offset": 66572160,
|
| 1574 |
+
"size": 1920,
|
| 1575 |
+
"shape": [
|
| 1576 |
+
480
|
| 1577 |
+
],
|
| 1578 |
+
"dtype": "F32",
|
| 1579 |
+
"role": "norm",
|
| 1580 |
+
"group": "layer.4"
|
| 1581 |
+
},
|
| 1582 |
+
"model.layers.4.post_attention_layernorm.weight": {
|
| 1583 |
+
"shard": 0,
|
| 1584 |
+
"offset": 66574080,
|
| 1585 |
+
"size": 1920,
|
| 1586 |
+
"shape": [
|
| 1587 |
+
480
|
| 1588 |
+
],
|
| 1589 |
+
"dtype": "F32",
|
| 1590 |
+
"role": "norm",
|
| 1591 |
+
"group": "layer.4"
|
| 1592 |
+
},
|
| 1593 |
+
"model.layers.4.input_layernorm.bias": {
|
| 1594 |
+
"shard": 0,
|
| 1595 |
+
"offset": 66576000,
|
| 1596 |
+
"size": 1920,
|
| 1597 |
+
"shape": [
|
| 1598 |
+
480
|
| 1599 |
+
],
|
| 1600 |
+
"dtype": "F32",
|
| 1601 |
+
"role": "norm",
|
| 1602 |
+
"group": "layer.4"
|
| 1603 |
+
},
|
| 1604 |
+
"model.layers.4.input_layernorm.weight": {
|
| 1605 |
+
"shard": 0,
|
| 1606 |
+
"offset": 66577920,
|
| 1607 |
+
"size": 1920,
|
| 1608 |
+
"shape": [
|
| 1609 |
+
480
|
| 1610 |
+
],
|
| 1611 |
+
"dtype": "F32",
|
| 1612 |
+
"role": "norm",
|
| 1613 |
+
"group": "layer.4"
|
| 1614 |
+
},
|
| 1615 |
+
"model.layers.4.self_attn.o_proj.bias": {
|
| 1616 |
+
"shard": 0,
|
| 1617 |
+
"offset": 66579840,
|
| 1618 |
+
"size": 1920,
|
| 1619 |
+
"shape": [
|
| 1620 |
+
480
|
| 1621 |
+
],
|
| 1622 |
+
"dtype": "F32",
|
| 1623 |
+
"role": "other",
|
| 1624 |
+
"group": "layer.4"
|
| 1625 |
+
},
|
| 1626 |
+
"model.layers.4.self_attn.o_proj.weight": {
|
| 1627 |
+
"spans": [
|
| 1628 |
+
{
|
| 1629 |
+
"shardIndex": 0,
|
| 1630 |
+
"offset": 66581760,
|
| 1631 |
+
"size": 527104
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"shardIndex": 1,
|
| 1635 |
+
"offset": 0,
|
| 1636 |
+
"size": 394496
|
| 1637 |
+
}
|
| 1638 |
+
],
|
| 1639 |
+
"size": 921600,
|
| 1640 |
+
"shape": [
|
| 1641 |
+
480,
|
| 1642 |
+
480
|
| 1643 |
+
],
|
| 1644 |
+
"dtype": "F32",
|
| 1645 |
+
"role": "matmul",
|
| 1646 |
+
"group": "layer.4"
|
| 1647 |
+
},
|
| 1648 |
+
"model.layers.4.self_attn.k_proj.bias": {
|
| 1649 |
+
"shard": 1,
|
| 1650 |
+
"offset": 394496,
|
| 1651 |
+
"size": 1920,
|
| 1652 |
+
"shape": [
|
| 1653 |
+
480
|
| 1654 |
+
],
|
| 1655 |
+
"dtype": "F32",
|
| 1656 |
+
"role": "other",
|
| 1657 |
+
"group": "layer.4"
|
| 1658 |
+
},
|
| 1659 |
+
"model.layers.4.self_attn.k_proj.weight": {
|
| 1660 |
+
"shard": 1,
|
| 1661 |
+
"offset": 396416,
|
| 1662 |
+
"size": 921600,
|
| 1663 |
+
"shape": [
|
| 1664 |
+
480,
|
| 1665 |
+
480
|
| 1666 |
+
],
|
| 1667 |
+
"dtype": "F32",
|
| 1668 |
+
"role": "matmul",
|
| 1669 |
+
"group": "layer.4"
|
| 1670 |
+
},
|
| 1671 |
+
"model.layers.4.self_attn.q_proj.bias": {
|
| 1672 |
+
"shard": 1,
|
| 1673 |
+
"offset": 1318016,
|
| 1674 |
+
"size": 1920,
|
| 1675 |
+
"shape": [
|
| 1676 |
+
480
|
| 1677 |
+
],
|
| 1678 |
+
"dtype": "F32",
|
| 1679 |
+
"role": "other",
|
| 1680 |
+
"group": "layer.4"
|
| 1681 |
+
},
|
| 1682 |
+
"model.layers.4.self_attn.q_proj.weight": {
|
| 1683 |
+
"shard": 1,
|
| 1684 |
+
"offset": 1319936,
|
| 1685 |
+
"size": 921600,
|
| 1686 |
+
"shape": [
|
| 1687 |
+
480,
|
| 1688 |
+
480
|
| 1689 |
+
],
|
| 1690 |
+
"dtype": "F32",
|
| 1691 |
+
"role": "matmul",
|
| 1692 |
+
"group": "layer.4"
|
| 1693 |
+
},
|
| 1694 |
+
"model.layers.4.self_attn.v_proj.bias": {
|
| 1695 |
+
"shard": 1,
|
| 1696 |
+
"offset": 2241536,
|
| 1697 |
+
"size": 1920,
|
| 1698 |
+
"shape": [
|
| 1699 |
+
480
|
| 1700 |
+
],
|
| 1701 |
+
"dtype": "F32",
|
| 1702 |
+
"role": "other",
|
| 1703 |
+
"group": "layer.4"
|
| 1704 |
+
},
|
| 1705 |
+
"model.layers.4.self_attn.v_proj.weight": {
|
| 1706 |
+
"shard": 1,
|
| 1707 |
+
"offset": 2243456,
|
| 1708 |
+
"size": 921600,
|
| 1709 |
+
"shape": [
|
| 1710 |
+
480,
|
| 1711 |
+
480
|
| 1712 |
+
],
|
| 1713 |
+
"dtype": "F32",
|
| 1714 |
+
"role": "matmul",
|
| 1715 |
+
"group": "layer.4"
|
| 1716 |
+
},
|
| 1717 |
+
"model.layers.4.mlp.up_proj.bias": {
|
| 1718 |
+
"shard": 1,
|
| 1719 |
+
"offset": 3165056,
|
| 1720 |
+
"size": 7680,
|
| 1721 |
+
"shape": [
|
| 1722 |
+
1920
|
| 1723 |
+
],
|
| 1724 |
+
"dtype": "F32",
|
| 1725 |
+
"role": "other",
|
| 1726 |
+
"group": "layer.4"
|
| 1727 |
+
},
|
| 1728 |
+
"model.layers.4.mlp.up_proj.weight": {
|
| 1729 |
+
"shard": 1,
|
| 1730 |
+
"offset": 3172736,
|
| 1731 |
+
"size": 3686400,
|
| 1732 |
+
"shape": [
|
| 1733 |
+
1920,
|
| 1734 |
+
480
|
| 1735 |
+
],
|
| 1736 |
+
"dtype": "F32",
|
| 1737 |
+
"role": "matmul",
|
| 1738 |
+
"group": "layer.4"
|
| 1739 |
+
},
|
| 1740 |
+
"model.layers.4.mlp.down_proj.bias": {
|
| 1741 |
+
"shard": 1,
|
| 1742 |
+
"offset": 6859136,
|
| 1743 |
+
"size": 1920,
|
| 1744 |
+
"shape": [
|
| 1745 |
+
480
|
| 1746 |
+
],
|
| 1747 |
+
"dtype": "F32",
|
| 1748 |
+
"role": "other",
|
| 1749 |
+
"group": "layer.4"
|
| 1750 |
+
},
|
| 1751 |
+
"model.layers.4.mlp.down_proj.weight": {
|
| 1752 |
+
"shard": 1,
|
| 1753 |
+
"offset": 6861056,
|
| 1754 |
+
"size": 3686400,
|
| 1755 |
+
"shape": [
|
| 1756 |
+
480,
|
| 1757 |
+
1920
|
| 1758 |
+
],
|
| 1759 |
+
"dtype": "F32",
|
| 1760 |
+
"role": "matmul",
|
| 1761 |
+
"group": "layer.4"
|
| 1762 |
+
},
|
| 1763 |
+
"model.layers.5.post_attention_layernorm.bias": {
|
| 1764 |
+
"shard": 1,
|
| 1765 |
+
"offset": 10547456,
|
| 1766 |
+
"size": 1920,
|
| 1767 |
+
"shape": [
|
| 1768 |
+
480
|
| 1769 |
+
],
|
| 1770 |
+
"dtype": "F32",
|
| 1771 |
+
"role": "norm",
|
| 1772 |
+
"group": "layer.5"
|
| 1773 |
+
},
|
| 1774 |
+
"model.layers.5.post_attention_layernorm.weight": {
|
| 1775 |
+
"shard": 1,
|
| 1776 |
+
"offset": 10549376,
|
| 1777 |
+
"size": 1920,
|
| 1778 |
+
"shape": [
|
| 1779 |
+
480
|
| 1780 |
+
],
|
| 1781 |
+
"dtype": "F32",
|
| 1782 |
+
"role": "norm",
|
| 1783 |
+
"group": "layer.5"
|
| 1784 |
+
},
|
| 1785 |
+
"model.layers.5.input_layernorm.bias": {
|
| 1786 |
+
"shard": 1,
|
| 1787 |
+
"offset": 10551296,
|
| 1788 |
+
"size": 1920,
|
| 1789 |
+
"shape": [
|
| 1790 |
+
480
|
| 1791 |
+
],
|
| 1792 |
+
"dtype": "F32",
|
| 1793 |
+
"role": "norm",
|
| 1794 |
+
"group": "layer.5"
|
| 1795 |
+
},
|
| 1796 |
+
"model.layers.5.input_layernorm.weight": {
|
| 1797 |
+
"shard": 1,
|
| 1798 |
+
"offset": 10553216,
|
| 1799 |
+
"size": 1920,
|
| 1800 |
+
"shape": [
|
| 1801 |
+
480
|
| 1802 |
+
],
|
| 1803 |
+
"dtype": "F32",
|
| 1804 |
+
"role": "norm",
|
| 1805 |
+
"group": "layer.5"
|
| 1806 |
+
},
|
| 1807 |
+
"model.layers.5.self_attn.o_proj.bias": {
|
| 1808 |
+
"shard": 1,
|
| 1809 |
+
"offset": 10555136,
|
| 1810 |
+
"size": 1920,
|
| 1811 |
+
"shape": [
|
| 1812 |
+
480
|
| 1813 |
+
],
|
| 1814 |
+
"dtype": "F32",
|
| 1815 |
+
"role": "other",
|
| 1816 |
+
"group": "layer.5"
|
| 1817 |
+
},
|
| 1818 |
+
"model.layers.5.self_attn.o_proj.weight": {
|
| 1819 |
+
"shard": 1,
|
| 1820 |
+
"offset": 10557056,
|
| 1821 |
+
"size": 921600,
|
| 1822 |
+
"shape": [
|
| 1823 |
+
480,
|
| 1824 |
+
480
|
| 1825 |
+
],
|
| 1826 |
+
"dtype": "F32",
|
| 1827 |
+
"role": "matmul",
|
| 1828 |
+
"group": "layer.5"
|
| 1829 |
+
},
|
| 1830 |
+
"model.layers.5.self_attn.k_proj.bias": {
|
| 1831 |
+
"shard": 1,
|
| 1832 |
+
"offset": 11478656,
|
| 1833 |
+
"size": 1920,
|
| 1834 |
+
"shape": [
|
| 1835 |
+
480
|
| 1836 |
+
],
|
| 1837 |
+
"dtype": "F32",
|
| 1838 |
+
"role": "other",
|
| 1839 |
+
"group": "layer.5"
|
| 1840 |
+
},
|
| 1841 |
+
"model.layers.5.self_attn.k_proj.weight": {
|
| 1842 |
+
"shard": 1,
|
| 1843 |
+
"offset": 11480576,
|
| 1844 |
+
"size": 921600,
|
| 1845 |
+
"shape": [
|
| 1846 |
+
480,
|
| 1847 |
+
480
|
| 1848 |
+
],
|
| 1849 |
+
"dtype": "F32",
|
| 1850 |
+
"role": "matmul",
|
| 1851 |
+
"group": "layer.5"
|
| 1852 |
+
},
|
| 1853 |
+
"model.layers.5.self_attn.q_proj.bias": {
|
| 1854 |
+
"shard": 1,
|
| 1855 |
+
"offset": 12402176,
|
| 1856 |
+
"size": 1920,
|
| 1857 |
+
"shape": [
|
| 1858 |
+
480
|
| 1859 |
+
],
|
| 1860 |
+
"dtype": "F32",
|
| 1861 |
+
"role": "other",
|
| 1862 |
+
"group": "layer.5"
|
| 1863 |
+
},
|
| 1864 |
+
"model.layers.5.self_attn.q_proj.weight": {
|
| 1865 |
+
"shard": 1,
|
| 1866 |
+
"offset": 12404096,
|
| 1867 |
+
"size": 921600,
|
| 1868 |
+
"shape": [
|
| 1869 |
+
480,
|
| 1870 |
+
480
|
| 1871 |
+
],
|
| 1872 |
+
"dtype": "F32",
|
| 1873 |
+
"role": "matmul",
|
| 1874 |
+
"group": "layer.5"
|
| 1875 |
+
},
|
| 1876 |
+
"model.layers.5.self_attn.v_proj.bias": {
|
| 1877 |
+
"shard": 1,
|
| 1878 |
+
"offset": 13325696,
|
| 1879 |
+
"size": 1920,
|
| 1880 |
+
"shape": [
|
| 1881 |
+
480
|
| 1882 |
+
],
|
| 1883 |
+
"dtype": "F32",
|
| 1884 |
+
"role": "other",
|
| 1885 |
+
"group": "layer.5"
|
| 1886 |
+
},
|
| 1887 |
+
"model.layers.5.self_attn.v_proj.weight": {
|
| 1888 |
+
"shard": 1,
|
| 1889 |
+
"offset": 13327616,
|
| 1890 |
+
"size": 921600,
|
| 1891 |
+
"shape": [
|
| 1892 |
+
480,
|
| 1893 |
+
480
|
| 1894 |
+
],
|
| 1895 |
+
"dtype": "F32",
|
| 1896 |
+
"role": "matmul",
|
| 1897 |
+
"group": "layer.5"
|
| 1898 |
+
},
|
| 1899 |
+
"model.layers.5.mlp.up_proj.bias": {
|
| 1900 |
+
"shard": 1,
|
| 1901 |
+
"offset": 14249216,
|
| 1902 |
+
"size": 7680,
|
| 1903 |
+
"shape": [
|
| 1904 |
+
1920
|
| 1905 |
+
],
|
| 1906 |
+
"dtype": "F32",
|
| 1907 |
+
"role": "other",
|
| 1908 |
+
"group": "layer.5"
|
| 1909 |
+
},
|
| 1910 |
+
"model.layers.5.mlp.up_proj.weight": {
|
| 1911 |
+
"shard": 1,
|
| 1912 |
+
"offset": 14256896,
|
| 1913 |
+
"size": 3686400,
|
| 1914 |
+
"shape": [
|
| 1915 |
+
1920,
|
| 1916 |
+
480
|
| 1917 |
+
],
|
| 1918 |
+
"dtype": "F32",
|
| 1919 |
+
"role": "matmul",
|
| 1920 |
+
"group": "layer.5"
|
| 1921 |
+
},
|
| 1922 |
+
"model.layers.5.mlp.down_proj.bias": {
|
| 1923 |
+
"shard": 1,
|
| 1924 |
+
"offset": 17943296,
|
| 1925 |
+
"size": 1920,
|
| 1926 |
+
"shape": [
|
| 1927 |
+
480
|
| 1928 |
+
],
|
| 1929 |
+
"dtype": "F32",
|
| 1930 |
+
"role": "other",
|
| 1931 |
+
"group": "layer.5"
|
| 1932 |
+
},
|
| 1933 |
+
"model.layers.5.mlp.down_proj.weight": {
|
| 1934 |
+
"shard": 1,
|
| 1935 |
+
"offset": 17945216,
|
| 1936 |
+
"size": 3686400,
|
| 1937 |
+
"shape": [
|
| 1938 |
+
480,
|
| 1939 |
+
1920
|
| 1940 |
+
],
|
| 1941 |
+
"dtype": "F32",
|
| 1942 |
+
"role": "matmul",
|
| 1943 |
+
"group": "layer.5"
|
| 1944 |
+
},
|
| 1945 |
+
"model.layers.6.post_attention_layernorm.bias": {
|
| 1946 |
+
"shard": 1,
|
| 1947 |
+
"offset": 21631616,
|
| 1948 |
+
"size": 1920,
|
| 1949 |
+
"shape": [
|
| 1950 |
+
480
|
| 1951 |
+
],
|
| 1952 |
+
"dtype": "F32",
|
| 1953 |
+
"role": "norm",
|
| 1954 |
+
"group": "layer.6"
|
| 1955 |
+
},
|
| 1956 |
+
"model.layers.6.post_attention_layernorm.weight": {
|
| 1957 |
+
"shard": 1,
|
| 1958 |
+
"offset": 21633536,
|
| 1959 |
+
"size": 1920,
|
| 1960 |
+
"shape": [
|
| 1961 |
+
480
|
| 1962 |
+
],
|
| 1963 |
+
"dtype": "F32",
|
| 1964 |
+
"role": "norm",
|
| 1965 |
+
"group": "layer.6"
|
| 1966 |
+
},
|
| 1967 |
+
"model.layers.6.input_layernorm.bias": {
|
| 1968 |
+
"shard": 1,
|
| 1969 |
+
"offset": 21635456,
|
| 1970 |
+
"size": 1920,
|
| 1971 |
+
"shape": [
|
| 1972 |
+
480
|
| 1973 |
+
],
|
| 1974 |
+
"dtype": "F32",
|
| 1975 |
+
"role": "norm",
|
| 1976 |
+
"group": "layer.6"
|
| 1977 |
+
},
|
| 1978 |
+
"model.layers.6.input_layernorm.weight": {
|
| 1979 |
+
"shard": 1,
|
| 1980 |
+
"offset": 21637376,
|
| 1981 |
+
"size": 1920,
|
| 1982 |
+
"shape": [
|
| 1983 |
+
480
|
| 1984 |
+
],
|
| 1985 |
+
"dtype": "F32",
|
| 1986 |
+
"role": "norm",
|
| 1987 |
+
"group": "layer.6"
|
| 1988 |
+
},
|
| 1989 |
+
"model.layers.6.self_attn.o_proj.bias": {
|
| 1990 |
+
"shard": 1,
|
| 1991 |
+
"offset": 21639296,
|
| 1992 |
+
"size": 1920,
|
| 1993 |
+
"shape": [
|
| 1994 |
+
480
|
| 1995 |
+
],
|
| 1996 |
+
"dtype": "F32",
|
| 1997 |
+
"role": "other",
|
| 1998 |
+
"group": "layer.6"
|
| 1999 |
+
},
|
| 2000 |
+
"model.layers.6.self_attn.o_proj.weight": {
|
| 2001 |
+
"shard": 1,
|
| 2002 |
+
"offset": 21641216,
|
| 2003 |
+
"size": 921600,
|
| 2004 |
+
"shape": [
|
| 2005 |
+
480,
|
| 2006 |
+
480
|
| 2007 |
+
],
|
| 2008 |
+
"dtype": "F32",
|
| 2009 |
+
"role": "matmul",
|
| 2010 |
+
"group": "layer.6"
|
| 2011 |
+
},
|
| 2012 |
+
"model.layers.6.self_attn.k_proj.bias": {
|
| 2013 |
+
"shard": 1,
|
| 2014 |
+
"offset": 22562816,
|
| 2015 |
+
"size": 1920,
|
| 2016 |
+
"shape": [
|
| 2017 |
+
480
|
| 2018 |
+
],
|
| 2019 |
+
"dtype": "F32",
|
| 2020 |
+
"role": "other",
|
| 2021 |
+
"group": "layer.6"
|
| 2022 |
+
},
|
| 2023 |
+
"model.layers.6.self_attn.k_proj.weight": {
|
| 2024 |
+
"shard": 1,
|
| 2025 |
+
"offset": 22564736,
|
| 2026 |
+
"size": 921600,
|
| 2027 |
+
"shape": [
|
| 2028 |
+
480,
|
| 2029 |
+
480
|
| 2030 |
+
],
|
| 2031 |
+
"dtype": "F32",
|
| 2032 |
+
"role": "matmul",
|
| 2033 |
+
"group": "layer.6"
|
| 2034 |
+
},
|
| 2035 |
+
"model.layers.6.self_attn.q_proj.bias": {
|
| 2036 |
+
"shard": 1,
|
| 2037 |
+
"offset": 23486336,
|
| 2038 |
+
"size": 1920,
|
| 2039 |
+
"shape": [
|
| 2040 |
+
480
|
| 2041 |
+
],
|
| 2042 |
+
"dtype": "F32",
|
| 2043 |
+
"role": "other",
|
| 2044 |
+
"group": "layer.6"
|
| 2045 |
+
},
|
| 2046 |
+
"model.layers.6.self_attn.q_proj.weight": {
|
| 2047 |
+
"shard": 1,
|
| 2048 |
+
"offset": 23488256,
|
| 2049 |
+
"size": 921600,
|
| 2050 |
+
"shape": [
|
| 2051 |
+
480,
|
| 2052 |
+
480
|
| 2053 |
+
],
|
| 2054 |
+
"dtype": "F32",
|
| 2055 |
+
"role": "matmul",
|
| 2056 |
+
"group": "layer.6"
|
| 2057 |
+
},
|
| 2058 |
+
"model.layers.6.self_attn.v_proj.bias": {
|
| 2059 |
+
"shard": 1,
|
| 2060 |
+
"offset": 24409856,
|
| 2061 |
+
"size": 1920,
|
| 2062 |
+
"shape": [
|
| 2063 |
+
480
|
| 2064 |
+
],
|
| 2065 |
+
"dtype": "F32",
|
| 2066 |
+
"role": "other",
|
| 2067 |
+
"group": "layer.6"
|
| 2068 |
+
},
|
| 2069 |
+
"model.layers.6.self_attn.v_proj.weight": {
|
| 2070 |
+
"shard": 1,
|
| 2071 |
+
"offset": 24411776,
|
| 2072 |
+
"size": 921600,
|
| 2073 |
+
"shape": [
|
| 2074 |
+
480,
|
| 2075 |
+
480
|
| 2076 |
+
],
|
| 2077 |
+
"dtype": "F32",
|
| 2078 |
+
"role": "matmul",
|
| 2079 |
+
"group": "layer.6"
|
| 2080 |
+
},
|
| 2081 |
+
"model.layers.6.mlp.up_proj.bias": {
|
| 2082 |
+
"shard": 1,
|
| 2083 |
+
"offset": 25333376,
|
| 2084 |
+
"size": 7680,
|
| 2085 |
+
"shape": [
|
| 2086 |
+
1920
|
| 2087 |
+
],
|
| 2088 |
+
"dtype": "F32",
|
| 2089 |
+
"role": "other",
|
| 2090 |
+
"group": "layer.6"
|
| 2091 |
+
},
|
| 2092 |
+
"model.layers.6.mlp.up_proj.weight": {
|
| 2093 |
+
"shard": 1,
|
| 2094 |
+
"offset": 25341056,
|
| 2095 |
+
"size": 3686400,
|
| 2096 |
+
"shape": [
|
| 2097 |
+
1920,
|
| 2098 |
+
480
|
| 2099 |
+
],
|
| 2100 |
+
"dtype": "F32",
|
| 2101 |
+
"role": "matmul",
|
| 2102 |
+
"group": "layer.6"
|
| 2103 |
+
},
|
| 2104 |
+
"model.layers.6.mlp.down_proj.bias": {
|
| 2105 |
+
"shard": 1,
|
| 2106 |
+
"offset": 29027456,
|
| 2107 |
+
"size": 1920,
|
| 2108 |
+
"shape": [
|
| 2109 |
+
480
|
| 2110 |
+
],
|
| 2111 |
+
"dtype": "F32",
|
| 2112 |
+
"role": "other",
|
| 2113 |
+
"group": "layer.6"
|
| 2114 |
+
},
|
| 2115 |
+
"model.layers.6.mlp.down_proj.weight": {
|
| 2116 |
+
"shard": 1,
|
| 2117 |
+
"offset": 29029376,
|
| 2118 |
+
"size": 3686400,
|
| 2119 |
+
"shape": [
|
| 2120 |
+
480,
|
| 2121 |
+
1920
|
| 2122 |
+
],
|
| 2123 |
+
"dtype": "F32",
|
| 2124 |
+
"role": "matmul",
|
| 2125 |
+
"group": "layer.6"
|
| 2126 |
+
},
|
| 2127 |
+
"model.layers.7.post_attention_layernorm.bias": {
|
| 2128 |
+
"shard": 1,
|
| 2129 |
+
"offset": 32715776,
|
| 2130 |
+
"size": 1920,
|
| 2131 |
+
"shape": [
|
| 2132 |
+
480
|
| 2133 |
+
],
|
| 2134 |
+
"dtype": "F32",
|
| 2135 |
+
"role": "norm",
|
| 2136 |
+
"group": "layer.7"
|
| 2137 |
+
},
|
| 2138 |
+
"model.layers.7.post_attention_layernorm.weight": {
|
| 2139 |
+
"shard": 1,
|
| 2140 |
+
"offset": 32717696,
|
| 2141 |
+
"size": 1920,
|
| 2142 |
+
"shape": [
|
| 2143 |
+
480
|
| 2144 |
+
],
|
| 2145 |
+
"dtype": "F32",
|
| 2146 |
+
"role": "norm",
|
| 2147 |
+
"group": "layer.7"
|
| 2148 |
+
},
|
| 2149 |
+
"model.layers.7.input_layernorm.bias": {
|
| 2150 |
+
"shard": 1,
|
| 2151 |
+
"offset": 32719616,
|
| 2152 |
+
"size": 1920,
|
| 2153 |
+
"shape": [
|
| 2154 |
+
480
|
| 2155 |
+
],
|
| 2156 |
+
"dtype": "F32",
|
| 2157 |
+
"role": "norm",
|
| 2158 |
+
"group": "layer.7"
|
| 2159 |
+
},
|
| 2160 |
+
"model.layers.7.input_layernorm.weight": {
|
| 2161 |
+
"shard": 1,
|
| 2162 |
+
"offset": 32721536,
|
| 2163 |
+
"size": 1920,
|
| 2164 |
+
"shape": [
|
| 2165 |
+
480
|
| 2166 |
+
],
|
| 2167 |
+
"dtype": "F32",
|
| 2168 |
+
"role": "norm",
|
| 2169 |
+
"group": "layer.7"
|
| 2170 |
+
},
|
| 2171 |
+
"model.layers.7.self_attn.o_proj.bias": {
|
| 2172 |
+
"shard": 1,
|
| 2173 |
+
"offset": 32723456,
|
| 2174 |
+
"size": 1920,
|
| 2175 |
+
"shape": [
|
| 2176 |
+
480
|
| 2177 |
+
],
|
| 2178 |
+
"dtype": "F32",
|
| 2179 |
+
"role": "other",
|
| 2180 |
+
"group": "layer.7"
|
| 2181 |
+
},
|
| 2182 |
+
"model.layers.7.self_attn.o_proj.weight": {
|
| 2183 |
+
"shard": 1,
|
| 2184 |
+
"offset": 32725376,
|
| 2185 |
+
"size": 921600,
|
| 2186 |
+
"shape": [
|
| 2187 |
+
480,
|
| 2188 |
+
480
|
| 2189 |
+
],
|
| 2190 |
+
"dtype": "F32",
|
| 2191 |
+
"role": "matmul",
|
| 2192 |
+
"group": "layer.7"
|
| 2193 |
+
},
|
| 2194 |
+
"model.layers.7.self_attn.k_proj.bias": {
|
| 2195 |
+
"shard": 1,
|
| 2196 |
+
"offset": 33646976,
|
| 2197 |
+
"size": 1920,
|
| 2198 |
+
"shape": [
|
| 2199 |
+
480
|
| 2200 |
+
],
|
| 2201 |
+
"dtype": "F32",
|
| 2202 |
+
"role": "other",
|
| 2203 |
+
"group": "layer.7"
|
| 2204 |
+
},
|
| 2205 |
+
"model.layers.7.self_attn.k_proj.weight": {
|
| 2206 |
+
"shard": 1,
|
| 2207 |
+
"offset": 33648896,
|
| 2208 |
+
"size": 921600,
|
| 2209 |
+
"shape": [
|
| 2210 |
+
480,
|
| 2211 |
+
480
|
| 2212 |
+
],
|
| 2213 |
+
"dtype": "F32",
|
| 2214 |
+
"role": "matmul",
|
| 2215 |
+
"group": "layer.7"
|
| 2216 |
+
},
|
| 2217 |
+
"model.layers.7.self_attn.q_proj.bias": {
|
| 2218 |
+
"shard": 1,
|
| 2219 |
+
"offset": 34570496,
|
| 2220 |
+
"size": 1920,
|
| 2221 |
+
"shape": [
|
| 2222 |
+
480
|
| 2223 |
+
],
|
| 2224 |
+
"dtype": "F32",
|
| 2225 |
+
"role": "other",
|
| 2226 |
+
"group": "layer.7"
|
| 2227 |
+
},
|
| 2228 |
+
"model.layers.7.self_attn.q_proj.weight": {
|
| 2229 |
+
"shard": 1,
|
| 2230 |
+
"offset": 34572416,
|
| 2231 |
+
"size": 921600,
|
| 2232 |
+
"shape": [
|
| 2233 |
+
480,
|
| 2234 |
+
480
|
| 2235 |
+
],
|
| 2236 |
+
"dtype": "F32",
|
| 2237 |
+
"role": "matmul",
|
| 2238 |
+
"group": "layer.7"
|
| 2239 |
+
},
|
| 2240 |
+
"model.layers.7.self_attn.v_proj.bias": {
|
| 2241 |
+
"shard": 1,
|
| 2242 |
+
"offset": 35494016,
|
| 2243 |
+
"size": 1920,
|
| 2244 |
+
"shape": [
|
| 2245 |
+
480
|
| 2246 |
+
],
|
| 2247 |
+
"dtype": "F32",
|
| 2248 |
+
"role": "other",
|
| 2249 |
+
"group": "layer.7"
|
| 2250 |
+
},
|
| 2251 |
+
"model.layers.7.self_attn.v_proj.weight": {
|
| 2252 |
+
"shard": 1,
|
| 2253 |
+
"offset": 35495936,
|
| 2254 |
+
"size": 921600,
|
| 2255 |
+
"shape": [
|
| 2256 |
+
480,
|
| 2257 |
+
480
|
| 2258 |
+
],
|
| 2259 |
+
"dtype": "F32",
|
| 2260 |
+
"role": "matmul",
|
| 2261 |
+
"group": "layer.7"
|
| 2262 |
+
},
|
| 2263 |
+
"model.layers.7.mlp.up_proj.bias": {
|
| 2264 |
+
"shard": 1,
|
| 2265 |
+
"offset": 36417536,
|
| 2266 |
+
"size": 7680,
|
| 2267 |
+
"shape": [
|
| 2268 |
+
1920
|
| 2269 |
+
],
|
| 2270 |
+
"dtype": "F32",
|
| 2271 |
+
"role": "other",
|
| 2272 |
+
"group": "layer.7"
|
| 2273 |
+
},
|
| 2274 |
+
"model.layers.7.mlp.up_proj.weight": {
|
| 2275 |
+
"shard": 1,
|
| 2276 |
+
"offset": 36425216,
|
| 2277 |
+
"size": 3686400,
|
| 2278 |
+
"shape": [
|
| 2279 |
+
1920,
|
| 2280 |
+
480
|
| 2281 |
+
],
|
| 2282 |
+
"dtype": "F32",
|
| 2283 |
+
"role": "matmul",
|
| 2284 |
+
"group": "layer.7"
|
| 2285 |
+
},
|
| 2286 |
+
"model.layers.7.mlp.down_proj.bias": {
|
| 2287 |
+
"shard": 1,
|
| 2288 |
+
"offset": 40111616,
|
| 2289 |
+
"size": 1920,
|
| 2290 |
+
"shape": [
|
| 2291 |
+
480
|
| 2292 |
+
],
|
| 2293 |
+
"dtype": "F32",
|
| 2294 |
+
"role": "other",
|
| 2295 |
+
"group": "layer.7"
|
| 2296 |
+
},
|
| 2297 |
+
"model.layers.7.mlp.down_proj.weight": {
|
| 2298 |
+
"shard": 1,
|
| 2299 |
+
"offset": 40113536,
|
| 2300 |
+
"size": 3686400,
|
| 2301 |
+
"shape": [
|
| 2302 |
+
480,
|
| 2303 |
+
1920
|
| 2304 |
+
],
|
| 2305 |
+
"dtype": "F32",
|
| 2306 |
+
"role": "matmul",
|
| 2307 |
+
"group": "layer.7"
|
| 2308 |
+
},
|
| 2309 |
+
"model.layers.8.post_attention_layernorm.bias": {
|
| 2310 |
+
"shard": 1,
|
| 2311 |
+
"offset": 43799936,
|
| 2312 |
+
"size": 1920,
|
| 2313 |
+
"shape": [
|
| 2314 |
+
480
|
| 2315 |
+
],
|
| 2316 |
+
"dtype": "F32",
|
| 2317 |
+
"role": "norm",
|
| 2318 |
+
"group": "layer.8"
|
| 2319 |
+
},
|
| 2320 |
+
"model.layers.8.post_attention_layernorm.weight": {
|
| 2321 |
+
"shard": 1,
|
| 2322 |
+
"offset": 43801856,
|
| 2323 |
+
"size": 1920,
|
| 2324 |
+
"shape": [
|
| 2325 |
+
480
|
| 2326 |
+
],
|
| 2327 |
+
"dtype": "F32",
|
| 2328 |
+
"role": "norm",
|
| 2329 |
+
"group": "layer.8"
|
| 2330 |
+
},
|
| 2331 |
+
"model.layers.8.input_layernorm.bias": {
|
| 2332 |
+
"shard": 1,
|
| 2333 |
+
"offset": 43803776,
|
| 2334 |
+
"size": 1920,
|
| 2335 |
+
"shape": [
|
| 2336 |
+
480
|
| 2337 |
+
],
|
| 2338 |
+
"dtype": "F32",
|
| 2339 |
+
"role": "norm",
|
| 2340 |
+
"group": "layer.8"
|
| 2341 |
+
},
|
| 2342 |
+
"model.layers.8.input_layernorm.weight": {
|
| 2343 |
+
"shard": 1,
|
| 2344 |
+
"offset": 43805696,
|
| 2345 |
+
"size": 1920,
|
| 2346 |
+
"shape": [
|
| 2347 |
+
480
|
| 2348 |
+
],
|
| 2349 |
+
"dtype": "F32",
|
| 2350 |
+
"role": "norm",
|
| 2351 |
+
"group": "layer.8"
|
| 2352 |
+
},
|
| 2353 |
+
"model.layers.8.self_attn.o_proj.bias": {
|
| 2354 |
+
"shard": 1,
|
| 2355 |
+
"offset": 43807616,
|
| 2356 |
+
"size": 1920,
|
| 2357 |
+
"shape": [
|
| 2358 |
+
480
|
| 2359 |
+
],
|
| 2360 |
+
"dtype": "F32",
|
| 2361 |
+
"role": "other",
|
| 2362 |
+
"group": "layer.8"
|
| 2363 |
+
},
|
| 2364 |
+
"model.layers.8.self_attn.o_proj.weight": {
|
| 2365 |
+
"shard": 1,
|
| 2366 |
+
"offset": 43809536,
|
| 2367 |
+
"size": 921600,
|
| 2368 |
+
"shape": [
|
| 2369 |
+
480,
|
| 2370 |
+
480
|
| 2371 |
+
],
|
| 2372 |
+
"dtype": "F32",
|
| 2373 |
+
"role": "matmul",
|
| 2374 |
+
"group": "layer.8"
|
| 2375 |
+
},
|
| 2376 |
+
"model.layers.8.self_attn.k_proj.bias": {
|
| 2377 |
+
"shard": 1,
|
| 2378 |
+
"offset": 44731136,
|
| 2379 |
+
"size": 1920,
|
| 2380 |
+
"shape": [
|
| 2381 |
+
480
|
| 2382 |
+
],
|
| 2383 |
+
"dtype": "F32",
|
| 2384 |
+
"role": "other",
|
| 2385 |
+
"group": "layer.8"
|
| 2386 |
+
},
|
| 2387 |
+
"model.layers.8.self_attn.k_proj.weight": {
|
| 2388 |
+
"shard": 1,
|
| 2389 |
+
"offset": 44733056,
|
| 2390 |
+
"size": 921600,
|
| 2391 |
+
"shape": [
|
| 2392 |
+
480,
|
| 2393 |
+
480
|
| 2394 |
+
],
|
| 2395 |
+
"dtype": "F32",
|
| 2396 |
+
"role": "matmul",
|
| 2397 |
+
"group": "layer.8"
|
| 2398 |
+
},
|
| 2399 |
+
"model.layers.8.self_attn.q_proj.bias": {
|
| 2400 |
+
"shard": 1,
|
| 2401 |
+
"offset": 45654656,
|
| 2402 |
+
"size": 1920,
|
| 2403 |
+
"shape": [
|
| 2404 |
+
480
|
| 2405 |
+
],
|
| 2406 |
+
"dtype": "F32",
|
| 2407 |
+
"role": "other",
|
| 2408 |
+
"group": "layer.8"
|
| 2409 |
+
},
|
| 2410 |
+
"model.layers.8.self_attn.q_proj.weight": {
|
| 2411 |
+
"shard": 1,
|
| 2412 |
+
"offset": 45656576,
|
| 2413 |
+
"size": 921600,
|
| 2414 |
+
"shape": [
|
| 2415 |
+
480,
|
| 2416 |
+
480
|
| 2417 |
+
],
|
| 2418 |
+
"dtype": "F32",
|
| 2419 |
+
"role": "matmul",
|
| 2420 |
+
"group": "layer.8"
|
| 2421 |
+
},
|
| 2422 |
+
"model.layers.8.self_attn.v_proj.bias": {
|
| 2423 |
+
"shard": 1,
|
| 2424 |
+
"offset": 46578176,
|
| 2425 |
+
"size": 1920,
|
| 2426 |
+
"shape": [
|
| 2427 |
+
480
|
| 2428 |
+
],
|
| 2429 |
+
"dtype": "F32",
|
| 2430 |
+
"role": "other",
|
| 2431 |
+
"group": "layer.8"
|
| 2432 |
+
},
|
| 2433 |
+
"model.layers.8.self_attn.v_proj.weight": {
|
| 2434 |
+
"shard": 1,
|
| 2435 |
+
"offset": 46580096,
|
| 2436 |
+
"size": 921600,
|
| 2437 |
+
"shape": [
|
| 2438 |
+
480,
|
| 2439 |
+
480
|
| 2440 |
+
],
|
| 2441 |
+
"dtype": "F32",
|
| 2442 |
+
"role": "matmul",
|
| 2443 |
+
"group": "layer.8"
|
| 2444 |
+
},
|
| 2445 |
+
"model.layers.8.mlp.up_proj.bias": {
|
| 2446 |
+
"shard": 1,
|
| 2447 |
+
"offset": 47501696,
|
| 2448 |
+
"size": 7680,
|
| 2449 |
+
"shape": [
|
| 2450 |
+
1920
|
| 2451 |
+
],
|
| 2452 |
+
"dtype": "F32",
|
| 2453 |
+
"role": "other",
|
| 2454 |
+
"group": "layer.8"
|
| 2455 |
+
},
|
| 2456 |
+
"model.layers.8.mlp.up_proj.weight": {
|
| 2457 |
+
"shard": 1,
|
| 2458 |
+
"offset": 47509376,
|
| 2459 |
+
"size": 3686400,
|
| 2460 |
+
"shape": [
|
| 2461 |
+
1920,
|
| 2462 |
+
480
|
| 2463 |
+
],
|
| 2464 |
+
"dtype": "F32",
|
| 2465 |
+
"role": "matmul",
|
| 2466 |
+
"group": "layer.8"
|
| 2467 |
+
},
|
| 2468 |
+
"model.layers.8.mlp.down_proj.bias": {
|
| 2469 |
+
"shard": 1,
|
| 2470 |
+
"offset": 51195776,
|
| 2471 |
+
"size": 1920,
|
| 2472 |
+
"shape": [
|
| 2473 |
+
480
|
| 2474 |
+
],
|
| 2475 |
+
"dtype": "F32",
|
| 2476 |
+
"role": "other",
|
| 2477 |
+
"group": "layer.8"
|
| 2478 |
+
},
|
| 2479 |
+
"model.layers.8.mlp.down_proj.weight": {
|
| 2480 |
+
"shard": 1,
|
| 2481 |
+
"offset": 51197696,
|
| 2482 |
+
"size": 3686400,
|
| 2483 |
+
"shape": [
|
| 2484 |
+
480,
|
| 2485 |
+
1920
|
| 2486 |
+
],
|
| 2487 |
+
"dtype": "F32",
|
| 2488 |
+
"role": "matmul",
|
| 2489 |
+
"group": "layer.8"
|
| 2490 |
+
},
|
| 2491 |
+
"model.layers.9.post_attention_layernorm.bias": {
|
| 2492 |
+
"shard": 1,
|
| 2493 |
+
"offset": 54884096,
|
| 2494 |
+
"size": 1920,
|
| 2495 |
+
"shape": [
|
| 2496 |
+
480
|
| 2497 |
+
],
|
| 2498 |
+
"dtype": "F32",
|
| 2499 |
+
"role": "norm",
|
| 2500 |
+
"group": "layer.9"
|
| 2501 |
+
},
|
| 2502 |
+
"model.layers.9.post_attention_layernorm.weight": {
|
| 2503 |
+
"shard": 1,
|
| 2504 |
+
"offset": 54886016,
|
| 2505 |
+
"size": 1920,
|
| 2506 |
+
"shape": [
|
| 2507 |
+
480
|
| 2508 |
+
],
|
| 2509 |
+
"dtype": "F32",
|
| 2510 |
+
"role": "norm",
|
| 2511 |
+
"group": "layer.9"
|
| 2512 |
+
},
|
| 2513 |
+
"model.layers.9.input_layernorm.bias": {
|
| 2514 |
+
"shard": 1,
|
| 2515 |
+
"offset": 54887936,
|
| 2516 |
+
"size": 1920,
|
| 2517 |
+
"shape": [
|
| 2518 |
+
480
|
| 2519 |
+
],
|
| 2520 |
+
"dtype": "F32",
|
| 2521 |
+
"role": "norm",
|
| 2522 |
+
"group": "layer.9"
|
| 2523 |
+
},
|
| 2524 |
+
"model.layers.9.input_layernorm.weight": {
|
| 2525 |
+
"shard": 1,
|
| 2526 |
+
"offset": 54889856,
|
| 2527 |
+
"size": 1920,
|
| 2528 |
+
"shape": [
|
| 2529 |
+
480
|
| 2530 |
+
],
|
| 2531 |
+
"dtype": "F32",
|
| 2532 |
+
"role": "norm",
|
| 2533 |
+
"group": "layer.9"
|
| 2534 |
+
},
|
| 2535 |
+
"model.layers.9.self_attn.o_proj.bias": {
|
| 2536 |
+
"shard": 1,
|
| 2537 |
+
"offset": 54891776,
|
| 2538 |
+
"size": 1920,
|
| 2539 |
+
"shape": [
|
| 2540 |
+
480
|
| 2541 |
+
],
|
| 2542 |
+
"dtype": "F32",
|
| 2543 |
+
"role": "other",
|
| 2544 |
+
"group": "layer.9"
|
| 2545 |
+
},
|
| 2546 |
+
"model.layers.9.self_attn.o_proj.weight": {
|
| 2547 |
+
"shard": 1,
|
| 2548 |
+
"offset": 54893696,
|
| 2549 |
+
"size": 921600,
|
| 2550 |
+
"shape": [
|
| 2551 |
+
480,
|
| 2552 |
+
480
|
| 2553 |
+
],
|
| 2554 |
+
"dtype": "F32",
|
| 2555 |
+
"role": "matmul",
|
| 2556 |
+
"group": "layer.9"
|
| 2557 |
+
},
|
| 2558 |
+
"model.layers.9.self_attn.k_proj.bias": {
|
| 2559 |
+
"shard": 1,
|
| 2560 |
+
"offset": 55815296,
|
| 2561 |
+
"size": 1920,
|
| 2562 |
+
"shape": [
|
| 2563 |
+
480
|
| 2564 |
+
],
|
| 2565 |
+
"dtype": "F32",
|
| 2566 |
+
"role": "other",
|
| 2567 |
+
"group": "layer.9"
|
| 2568 |
+
},
|
| 2569 |
+
"model.layers.9.self_attn.k_proj.weight": {
|
| 2570 |
+
"shard": 1,
|
| 2571 |
+
"offset": 55817216,
|
| 2572 |
+
"size": 921600,
|
| 2573 |
+
"shape": [
|
| 2574 |
+
480,
|
| 2575 |
+
480
|
| 2576 |
+
],
|
| 2577 |
+
"dtype": "F32",
|
| 2578 |
+
"role": "matmul",
|
| 2579 |
+
"group": "layer.9"
|
| 2580 |
+
},
|
| 2581 |
+
"model.layers.9.self_attn.q_proj.bias": {
|
| 2582 |
+
"shard": 1,
|
| 2583 |
+
"offset": 56738816,
|
| 2584 |
+
"size": 1920,
|
| 2585 |
+
"shape": [
|
| 2586 |
+
480
|
| 2587 |
+
],
|
| 2588 |
+
"dtype": "F32",
|
| 2589 |
+
"role": "other",
|
| 2590 |
+
"group": "layer.9"
|
| 2591 |
+
},
|
| 2592 |
+
"model.layers.9.self_attn.q_proj.weight": {
|
| 2593 |
+
"shard": 1,
|
| 2594 |
+
"offset": 56740736,
|
| 2595 |
+
"size": 921600,
|
| 2596 |
+
"shape": [
|
| 2597 |
+
480,
|
| 2598 |
+
480
|
| 2599 |
+
],
|
| 2600 |
+
"dtype": "F32",
|
| 2601 |
+
"role": "matmul",
|
| 2602 |
+
"group": "layer.9"
|
| 2603 |
+
},
|
| 2604 |
+
"model.layers.9.self_attn.v_proj.bias": {
|
| 2605 |
+
"shard": 1,
|
| 2606 |
+
"offset": 57662336,
|
| 2607 |
+
"size": 1920,
|
| 2608 |
+
"shape": [
|
| 2609 |
+
480
|
| 2610 |
+
],
|
| 2611 |
+
"dtype": "F32",
|
| 2612 |
+
"role": "other",
|
| 2613 |
+
"group": "layer.9"
|
| 2614 |
+
},
|
| 2615 |
+
"model.layers.9.self_attn.v_proj.weight": {
|
| 2616 |
+
"shard": 1,
|
| 2617 |
+
"offset": 57664256,
|
| 2618 |
+
"size": 921600,
|
| 2619 |
+
"shape": [
|
| 2620 |
+
480,
|
| 2621 |
+
480
|
| 2622 |
+
],
|
| 2623 |
+
"dtype": "F32",
|
| 2624 |
+
"role": "matmul",
|
| 2625 |
+
"group": "layer.9"
|
| 2626 |
+
},
|
| 2627 |
+
"model.layers.9.mlp.up_proj.bias": {
|
| 2628 |
+
"shard": 1,
|
| 2629 |
+
"offset": 58585856,
|
| 2630 |
+
"size": 7680,
|
| 2631 |
+
"shape": [
|
| 2632 |
+
1920
|
| 2633 |
+
],
|
| 2634 |
+
"dtype": "F32",
|
| 2635 |
+
"role": "other",
|
| 2636 |
+
"group": "layer.9"
|
| 2637 |
+
},
|
| 2638 |
+
"model.layers.9.mlp.up_proj.weight": {
|
| 2639 |
+
"shard": 1,
|
| 2640 |
+
"offset": 58593536,
|
| 2641 |
+
"size": 3686400,
|
| 2642 |
+
"shape": [
|
| 2643 |
+
1920,
|
| 2644 |
+
480
|
| 2645 |
+
],
|
| 2646 |
+
"dtype": "F32",
|
| 2647 |
+
"role": "matmul",
|
| 2648 |
+
"group": "layer.9"
|
| 2649 |
+
},
|
| 2650 |
+
"model.layers.9.mlp.down_proj.bias": {
|
| 2651 |
+
"shard": 1,
|
| 2652 |
+
"offset": 62279936,
|
| 2653 |
+
"size": 1920,
|
| 2654 |
+
"shape": [
|
| 2655 |
+
480
|
| 2656 |
+
],
|
| 2657 |
+
"dtype": "F32",
|
| 2658 |
+
"role": "other",
|
| 2659 |
+
"group": "layer.9"
|
| 2660 |
+
},
|
| 2661 |
+
"model.layers.9.mlp.down_proj.weight": {
|
| 2662 |
+
"shard": 1,
|
| 2663 |
+
"offset": 62281856,
|
| 2664 |
+
"size": 3686400,
|
| 2665 |
+
"shape": [
|
| 2666 |
+
480,
|
| 2667 |
+
1920
|
| 2668 |
+
],
|
| 2669 |
+
"dtype": "F32",
|
| 2670 |
+
"role": "matmul",
|
| 2671 |
+
"group": "layer.9"
|
| 2672 |
+
}
|
| 2673 |
+
},
|
| 2674 |
+
"totalSize": 133077120,
|
| 2675 |
+
"hashAlgorithm": "blake3",
|
| 2676 |
+
"eos_token_id": 2,
|
| 2677 |
+
"conversion": null,
|
| 2678 |
+
"metadata": {
|
| 2679 |
+
"source": "file:///tmp/doppler-esm2-35m/source",
|
| 2680 |
+
"convertedAt": "2026-07-19T05:33:50.138Z",
|
| 2681 |
+
"hasTokenizer": true
|
| 2682 |
+
},
|
| 2683 |
+
"tokenizer": {
|
| 2684 |
+
"type": "bundled",
|
| 2685 |
+
"vocabSize": 33,
|
| 2686 |
+
"file": "tokenizer.json",
|
| 2687 |
+
"addBosToken": true,
|
| 2688 |
+
"addEosToken": true
|
| 2689 |
+
},
|
| 2690 |
+
"integrityExtensions": {
|
| 2691 |
+
"contractVersion": 1,
|
| 2692 |
+
"blockMerkle": {
|
| 2693 |
+
"blockSize": 1048576,
|
| 2694 |
+
"roots": {
|
| 2695 |
+
"model.embed_tokens.weight": "sha256:a025da812985271ff4bdd923c76c6ff36092af11ab319927c9930d581e6822a1",
|
| 2696 |
+
"model.layers.0.input_layernorm.bias": "sha256:6181d66b3b5f771271dfa7735d6491d3710ed098c719fc4c60742767e7deb222",
|
| 2697 |
+
"model.layers.0.input_layernorm.weight": "sha256:befc94e8b9bc972f4da68c70485ceffa8d2d476e0a07d7a1e6c7f8c0e0ca0153",
|
| 2698 |
+
"model.layers.0.mlp.down_proj.bias": "sha256:25ac3455ada8231960bdbb9f31b7714ff31456476228d20ae8ee348cbd528249",
|
| 2699 |
+
"model.layers.0.mlp.down_proj.weight": "sha256:63e4a364f46143d8ad1fed4391fb82e0d3c7be5040abac3f5c00d530ed0a131a",
|
| 2700 |
+
"model.layers.0.mlp.up_proj.bias": "sha256:fe4fe8950059248fbc1f7f460cd97f0f47afeeef91a50b22d4763cdca1d01a78",
|
| 2701 |
+
"model.layers.0.mlp.up_proj.weight": "sha256:50687f6645b9c44d97d23cbcb62a07d67abf52c5dda4d2ea8249c583caf6e8ed",
|
| 2702 |
+
"model.layers.0.post_attention_layernorm.bias": "sha256:8c7a2554dc56962b5690f0939b13672be12fdd7648a577b4d88dc07d3fd5f6e6",
|
| 2703 |
+
"model.layers.0.post_attention_layernorm.weight": "sha256:19cc6b83a9f3e7bca3f55ff725e8bae14eb42a5f2468a32416060b4be07a872a",
|
| 2704 |
+
"model.layers.0.self_attn.k_proj.bias": "sha256:d159868b3a62d83ad23f64f182ba5d8afcf2b3fece95c9b07bd75876cead1583",
|
| 2705 |
+
"model.layers.0.self_attn.k_proj.weight": "sha256:767a342bdd6c0a85a5c14a2aabfb07dcdf58f68fff357f03024dc6b7448daba0",
|
| 2706 |
+
"model.layers.0.self_attn.o_proj.bias": "sha256:826e090b1ead50f67f9ab7a4b43bdbcfe7fdd070ecfa020048ab594ed892b922",
|
| 2707 |
+
"model.layers.0.self_attn.o_proj.weight": "sha256:aa9ca5bbe3d593ae479aef0ed47caa7368b89c52983d7a3af8dcbce0c5b6a122",
|
| 2708 |
+
"model.layers.0.self_attn.q_proj.bias": "sha256:a891a53f3c356c773a6ea6931ae25403a1d2697a391ed512b3f8957efe7a7ec5",
|
| 2709 |
+
"model.layers.0.self_attn.q_proj.weight": "sha256:ddccdfed9b03cd5a39cedb9eff2667203b7fddfea51b6fce7f2a3990380e01ce",
|
| 2710 |
+
"model.layers.0.self_attn.v_proj.bias": "sha256:11df6b4069f0afea64c8aaf1e29781beab7c995d6c826b4142b81828708c439e",
|
| 2711 |
+
"model.layers.0.self_attn.v_proj.weight": "sha256:edd4c25be6051c51fc9afe3e5714b40791ed9ef98826b5ca41e24de86c67712f",
|
| 2712 |
+
"model.layers.1.input_layernorm.bias": "sha256:7ac81e8e9b2834059e862ca14f0c927881231b72dc4d52bb00a9da31cad5ee95",
|
| 2713 |
+
"model.layers.1.input_layernorm.weight": "sha256:d644f1b9137567c1382f0031c2bb73271956147268f82f1d5e4d633113b5531c",
|
| 2714 |
+
"model.layers.1.mlp.down_proj.bias": "sha256:e7d9776e2455c51c245173bd417508d2e9113f895dafda667eccf3fac3b21cfd",
|
| 2715 |
+
"model.layers.1.mlp.down_proj.weight": "sha256:663668b01182f18925c9286c50e8cf1f7af3ec057e5143125731843fa11fc05b",
|
| 2716 |
+
"model.layers.1.mlp.up_proj.bias": "sha256:7b70b1dd5a0b389e0d63afb871c5d182a11afc35a9ce57e72210915474069eb3",
|
| 2717 |
+
"model.layers.1.mlp.up_proj.weight": "sha256:79963ac0b625837845281c86204dcd1e400f5ac80bf8663fea53a42d5eb2a3f3",
|
| 2718 |
+
"model.layers.1.post_attention_layernorm.bias": "sha256:b8b80666c929956b6fb2319df2725c735c6235befb12624ad46a7fb6830edc60",
|
| 2719 |
+
"model.layers.1.post_attention_layernorm.weight": "sha256:71cb64a1d5c2abb23a9e58353b325df19348b156a2784ec45b35b469b3226a3a",
|
| 2720 |
+
"model.layers.1.self_attn.k_proj.bias": "sha256:3c9080b39f48100ef93bab5cad67e263f6d8d5420e8b2798a74965170e5c1572",
|
| 2721 |
+
"model.layers.1.self_attn.k_proj.weight": "sha256:9a543cfe391319a1b0cdfc42164464bb31c0336740c031a119f5d47aea9a6ec0",
|
| 2722 |
+
"model.layers.1.self_attn.o_proj.bias": "sha256:31ed740aee7a9ea248583f7e2bc940d8b503d51d866985978ed02c0bf8d3eebe",
|
| 2723 |
+
"model.layers.1.self_attn.o_proj.weight": "sha256:3ddd82bee430b13c1f3ea271a8b2ac88e0f8b80ea112783058834360c947b85a",
|
| 2724 |
+
"model.layers.1.self_attn.q_proj.bias": "sha256:ea793b47f42063f535f4cd3305ec5ef53a113d04bbb1b65436f01b1ec3842411",
|
| 2725 |
+
"model.layers.1.self_attn.q_proj.weight": "sha256:a35bcee2c1ea010b15c57e6ff14beb7de4b8a447815dae79092984bd2365edb9",
|
| 2726 |
+
"model.layers.1.self_attn.v_proj.bias": "sha256:fd2e8165bce2c36591b6cd33a1b009942a917139112631f4da924fe4ab59fb6c",
|
| 2727 |
+
"model.layers.1.self_attn.v_proj.weight": "sha256:6e6bfa7e3ab377e200cf9447f854ddf899ed77d3844d18c77f6346305ac056c4",
|
| 2728 |
+
"model.layers.10.input_layernorm.bias": "sha256:e960bff323702d18c589c7985a2763f86ad29ba68b41d4e06b0837506c458b4b",
|
| 2729 |
+
"model.layers.10.input_layernorm.weight": "sha256:abede9449c466ef93b69c86ab9d2ac297584699485f5ee2a2fa02eae7ce3b382",
|
| 2730 |
+
"model.layers.10.mlp.down_proj.bias": "sha256:a289e72de780253fdd0bd34bf582819f8767c43901d4370a449a7502fc039023",
|
| 2731 |
+
"model.layers.10.mlp.down_proj.weight": "sha256:b78f78e64765d6796a1d2788e370aea1a5f4cbeeadc5c838f35557bf41833e72",
|
| 2732 |
+
"model.layers.10.mlp.up_proj.bias": "sha256:32b3b509df3265c028d77e499a25ec36b599cd60c8e309279ae2b2e77a916254",
|
| 2733 |
+
"model.layers.10.mlp.up_proj.weight": "sha256:e9250028decbc47db3ece6f057995f8ace7f3b086a3aa86ee5c7a43f4cd1fa61",
|
| 2734 |
+
"model.layers.10.post_attention_layernorm.bias": "sha256:83fcf129ee135bc7a9c111b81054503f28e7361c71699e9d79a47c91c164ac4b",
|
| 2735 |
+
"model.layers.10.post_attention_layernorm.weight": "sha256:a343442c1d8b75cc7c82b4f39581145cd8ef8eaba81553a1aaa79ceb7fb42a9b",
|
| 2736 |
+
"model.layers.10.self_attn.k_proj.bias": "sha256:d11d2be62702f057ea4891f4cc0ea360c7154a5862e2d0d4153b4bd4a23637f6",
|
| 2737 |
+
"model.layers.10.self_attn.k_proj.weight": "sha256:c21ce73b41ca724629b2c6803ec7c3374a74ca6f09c2cd5b78389e961d78683d",
|
| 2738 |
+
"model.layers.10.self_attn.o_proj.bias": "sha256:aa205896a5b089a2f705d1312c36a45baa853779e577e4cca56e39be2d7c6924",
|
| 2739 |
+
"model.layers.10.self_attn.o_proj.weight": "sha256:d973dad4d3338dea9004be05f242281e8297016115623d43e038708e09af42e8",
|
| 2740 |
+
"model.layers.10.self_attn.q_proj.bias": "sha256:0f82c7f02d13395482a69250d9c999a68e88b46cf9bc1939db03a65d7cfd3251",
|
| 2741 |
+
"model.layers.10.self_attn.q_proj.weight": "sha256:b914a9e70f07707dd6d319ec08232f42cfcaba36cff9255ce0cebb71958f4780",
|
| 2742 |
+
"model.layers.10.self_attn.v_proj.bias": "sha256:7dff1b7836b139b2751a4d2b05e9f73768bf5b894af4fba68ae17731cc769edf",
|
| 2743 |
+
"model.layers.10.self_attn.v_proj.weight": "sha256:78f678d8b241a2ca7f6caebd5042e6c3a44f60687497cf2740d1694870c49f77",
|
| 2744 |
+
"model.layers.11.input_layernorm.bias": "sha256:1cfeb893192ae4bb569f0bf2a9d266e967bc34617101ad7f22db0f4351053d04",
|
| 2745 |
+
"model.layers.11.input_layernorm.weight": "sha256:0f43ad342aa2a54ed33132a26c3bd1dc8062db9d71b813d256450527b2aae5e7",
|
| 2746 |
+
"model.layers.11.mlp.down_proj.bias": "sha256:b8f3f9e2ba7b37a0f473d4681810fa0b7871204a02ef5ad3360ea3c50a3fa1c7",
|
| 2747 |
+
"model.layers.11.mlp.down_proj.weight": "sha256:ea99e596832ada60f87f70d3e4d4d039ceccd4d1f1d95690be3f955c89982128",
|
| 2748 |
+
"model.layers.11.mlp.up_proj.bias": "sha256:865969014bec66271c71964bc9f87cead15bca06a3dc89a7ae211fea7a56d43b",
|
| 2749 |
+
"model.layers.11.mlp.up_proj.weight": "sha256:0c0033d0bd7651b64bf2779d535090a756556fa8c7c40ea2dd7ebf768d9013a7",
|
| 2750 |
+
"model.layers.11.post_attention_layernorm.bias": "sha256:ffa660c390bbf2f2ca7516b79bc9bd6ee58ae78bcdb467097995ae064a47da4b",
|
| 2751 |
+
"model.layers.11.post_attention_layernorm.weight": "sha256:ccdf6489fef2efabbb3a2c80c5bc2397e1f025194d36e20e58e63ae10cbc0f8b",
|
| 2752 |
+
"model.layers.11.self_attn.k_proj.bias": "sha256:5467ce79aa23afa92dd125e0de38fd83764063328b575170bfe3703c0c0c0915",
|
| 2753 |
+
"model.layers.11.self_attn.k_proj.weight": "sha256:affca813e57afde89a4967aecca3a01f6db261cec7a188ddf17d408dca7e4d86",
|
| 2754 |
+
"model.layers.11.self_attn.o_proj.bias": "sha256:170bbaacf267c8f5dba184ba44b776665f2b5d7d6dc5c4b686d5830f78f20fd0",
|
| 2755 |
+
"model.layers.11.self_attn.o_proj.weight": "sha256:fdf2cf1a34eb930f6003d4c0b64a77fcf8122097cd1b0f3746c2bee32b947f45",
|
| 2756 |
+
"model.layers.11.self_attn.q_proj.bias": "sha256:bad84e34bc7ddc23e2731df5a364f5e1de169a4e8c8b70c570ca8e290498ce3e",
|
| 2757 |
+
"model.layers.11.self_attn.q_proj.weight": "sha256:a40d7497868fcad5780cae584e257c953c3428ec65560ade9b0cba57fbd24fdf",
|
| 2758 |
+
"model.layers.11.self_attn.v_proj.bias": "sha256:fd2f3cd5749a844bc72eadc8d276fe1a570bfbada89c563dd268245a98d4482f",
|
| 2759 |
+
"model.layers.11.self_attn.v_proj.weight": "sha256:6bfd9c05dce3e4d5fbe3f84ea25d50b5f21fc08b77a2621bd348e8c8166a6033",
|
| 2760 |
+
"model.layers.2.input_layernorm.bias": "sha256:7b99e3303f7b8f139f336b222480351bc2a9dc107b19a7d06402e4a01b4e34d4",
|
| 2761 |
+
"model.layers.2.input_layernorm.weight": "sha256:5faa40e697e9f92b068b3bf9550f940e6efdcac8512320e0ab1d6f44fd15b741",
|
| 2762 |
+
"model.layers.2.mlp.down_proj.bias": "sha256:4f66711a4233de644d91ba1ee63f7cf8e2f5fa6ed92e1ba2c2dadf8a543466f5",
|
| 2763 |
+
"model.layers.2.mlp.down_proj.weight": "sha256:7a74763c074f2c393b9cbbd17e4632f0251606373e7a8f48ccb8cfeb3d474f3e",
|
| 2764 |
+
"model.layers.2.mlp.up_proj.bias": "sha256:1b3386fc38a3fe94c678e9a54c9dc3f19ec95142708dd5fc16d0bd8bc8c0742a",
|
| 2765 |
+
"model.layers.2.mlp.up_proj.weight": "sha256:7e1185900d5abc4f8dcd89e59667197689d7227212ad11c8db50da23d18bd26b",
|
| 2766 |
+
"model.layers.2.post_attention_layernorm.bias": "sha256:9364d5957128171df677b9fcef1eef000af33920770b806e0ed359a8738ff775",
|
| 2767 |
+
"model.layers.2.post_attention_layernorm.weight": "sha256:e3e0ee547fb636585cbb18b21098d479d9c92240711b715779fc0d4732ee090c",
|
| 2768 |
+
"model.layers.2.self_attn.k_proj.bias": "sha256:97566cdad976712eb2c3696730971ffa8177dc62cca70b28a0deaa0ea7fbabfd",
|
| 2769 |
+
"model.layers.2.self_attn.k_proj.weight": "sha256:27bd9af9abef1feeff55ee0ea0af6b7030a56b0d94c5127cc945923b13ceaf12",
|
| 2770 |
+
"model.layers.2.self_attn.o_proj.bias": "sha256:6685c9c93945ea427fc91cfdaf9caabbd784b329002276f9223eb01dca96352a",
|
| 2771 |
+
"model.layers.2.self_attn.o_proj.weight": "sha256:a288ceeba92b6c42f26b188d57ac6b81a1fff0f43379fc3127ebf90e0414051d",
|
| 2772 |
+
"model.layers.2.self_attn.q_proj.bias": "sha256:6ace4ff727bb1667139081b8dcc9f1c05838b94193d0e04900370d4f02454276",
|
| 2773 |
+
"model.layers.2.self_attn.q_proj.weight": "sha256:6c7a63e4ef1e4767064ca2681c33d085101e70b1efa6477d583511e5734e6485",
|
| 2774 |
+
"model.layers.2.self_attn.v_proj.bias": "sha256:b6d6346ba2c377e31161b954129b1fd2f822bb29039a1cbade48d5266d7ea935",
|
| 2775 |
+
"model.layers.2.self_attn.v_proj.weight": "sha256:569070fe7cdcdcea3c68895e7c9adc9fcf5d9e90d66e877a9426d66b90591df6",
|
| 2776 |
+
"model.layers.3.input_layernorm.bias": "sha256:68cd231ce77482ae95712195aa69c5a07f67d5c9193cb389592e5364bb367c2e",
|
| 2777 |
+
"model.layers.3.input_layernorm.weight": "sha256:6782af8a3a4ffb2114c1d044943fecc26875332794d7164ffa8e89ea467d59d5",
|
| 2778 |
+
"model.layers.3.mlp.down_proj.bias": "sha256:0ca44fa1687001ee1d8d5ec6a82ade64c40f93835fc969e8f84769e7159b4468",
|
| 2779 |
+
"model.layers.3.mlp.down_proj.weight": "sha256:6edabb29f6ee088fec8ecb7bfdc249849f5dbef6316cd2daeb147230a5d8bc53",
|
| 2780 |
+
"model.layers.3.mlp.up_proj.bias": "sha256:d94d9c1155f3056b834c68432fe6805e7507cc69af49e5af809cee1fa4cc2256",
|
| 2781 |
+
"model.layers.3.mlp.up_proj.weight": "sha256:2eb23b640ee9e7187c1b5f11a2db9dc5fbad4e3fee840184582aed5d695807b7",
|
| 2782 |
+
"model.layers.3.post_attention_layernorm.bias": "sha256:9ce8cc381fb4dc3524918bb0e9e72ef420d384c8f6f38c1cc04f8a7e82e3ec2a",
|
| 2783 |
+
"model.layers.3.post_attention_layernorm.weight": "sha256:8114cd9d31f65c001574bb41a3b50e1975e9452b394436e4352d9057b6a13651",
|
| 2784 |
+
"model.layers.3.self_attn.k_proj.bias": "sha256:637852ccac8bb1105a57d387fd7c911f2f64b9e3e0daf1f1897444ab98bde49d",
|
| 2785 |
+
"model.layers.3.self_attn.k_proj.weight": "sha256:2c73470187f6dc88adfb1991ab3364bd35f6f68bd8d2a385c07f0ec42f8b3ea4",
|
| 2786 |
+
"model.layers.3.self_attn.o_proj.bias": "sha256:3b236bd733dfeff0c0a40df4e96c61ebc156574e4de0b51c886afde4301cec6b",
|
| 2787 |
+
"model.layers.3.self_attn.o_proj.weight": "sha256:c606dc8cf28657fba11e3441ae54da9df4bad2ef2f27a83229272ba6a5b8380a",
|
| 2788 |
+
"model.layers.3.self_attn.q_proj.bias": "sha256:346110c2534ba043f7284e94e468c6c345d91a368fd5f8d4a27b2e5b215d8b72",
|
| 2789 |
+
"model.layers.3.self_attn.q_proj.weight": "sha256:001e153d0674da8a82d8507d62738365a9fd6c647bf83a694461aa1b8c138638",
|
| 2790 |
+
"model.layers.3.self_attn.v_proj.bias": "sha256:9c0485e281fb3ec981af8c685b8d9bece77984106cda855cd1d96cc64aaa523e",
|
| 2791 |
+
"model.layers.3.self_attn.v_proj.weight": "sha256:9097c88d780a47d218c7b9e1b7ed9982e7cda9e52a30c7a0b38053fb9e8b8746",
|
| 2792 |
+
"model.layers.4.input_layernorm.bias": "sha256:d3a198860330f93f9a902105a5c295870c9e1556f2a155ee5e3cdb585b2deba8",
|
| 2793 |
+
"model.layers.4.input_layernorm.weight": "sha256:9b09ee866da5023a7a4ae79ff8e9988c72842d7d4c4b735db0f2ad9cd65568cd",
|
| 2794 |
+
"model.layers.4.mlp.down_proj.bias": "sha256:46e79ebb33d287bb1bbf08cff184ac79d9cbb3295ed5a0933fa2d3b6f7bc5af3",
|
| 2795 |
+
"model.layers.4.mlp.down_proj.weight": "sha256:71c589dc8d15147ae0a61ab78c19fd4873ad7b3b54b7c288d4b763fca04c65ff",
|
| 2796 |
+
"model.layers.4.mlp.up_proj.bias": "sha256:551fadfb3d671f8ca5c6f8f4ca5beced991d8037b9514f3e1da30efdb063864c",
|
| 2797 |
+
"model.layers.4.mlp.up_proj.weight": "sha256:e14a35c13a0689d527119688ec6cd01cf1d3df2179cb6596dc1e32f99e1ccbf7",
|
| 2798 |
+
"model.layers.4.post_attention_layernorm.bias": "sha256:14fcd4e48e92622985760b27d4f0e547703d995feec2706ad1ad8be6eed121bb",
|
| 2799 |
+
"model.layers.4.post_attention_layernorm.weight": "sha256:ecfe1c30c8f07c1fefe194c3a97eb516aeb8845557c1735efb9f7b686fdd9e17",
|
| 2800 |
+
"model.layers.4.self_attn.k_proj.bias": "sha256:5aa5db013273c555a955e6d47cd93ef17e60fcdc5cc4f6f0ee74490566dbb607",
|
| 2801 |
+
"model.layers.4.self_attn.k_proj.weight": "sha256:5c015f9978d584c657c10f573e46918c7b6073a33c41dea613958ac3fac95a4f",
|
| 2802 |
+
"model.layers.4.self_attn.o_proj.bias": "sha256:d9b947bc31aa2e2b9b18a935989af8bc66973b5171d1b633636fabe7fca3a9df",
|
| 2803 |
+
"model.layers.4.self_attn.o_proj.weight": "sha256:328003640073704c39da776fb1ead571032d00aa875a468c04227fcc91223b0e",
|
| 2804 |
+
"model.layers.4.self_attn.q_proj.bias": "sha256:b54901cff0756e6edc7f074c9fd20f77f4878d520e021ed250d44ba8e4fb0023",
|
| 2805 |
+
"model.layers.4.self_attn.q_proj.weight": "sha256:6eac5064dfe2ae51d859fca5aee7b0782f4b02db12bc918ba98844be8ffb3128",
|
| 2806 |
+
"model.layers.4.self_attn.v_proj.bias": "sha256:fb02216585e1ccac5c4d54cfb80e734178ed1a3ee78400d5b774ab47d7d836be",
|
| 2807 |
+
"model.layers.4.self_attn.v_proj.weight": "sha256:e0bcff73b170da6e7eb873647ad44fc3ba96dc3410f54ed029bd0b011c64dd4f",
|
| 2808 |
+
"model.layers.5.input_layernorm.bias": "sha256:5622e5084ee1b2e38a3effb7973843f1488f4d7e9e98d7b7fa027be3a4559556",
|
| 2809 |
+
"model.layers.5.input_layernorm.weight": "sha256:f835de682368754c9e3f5d48a2f79fa9014459ed74f55bb1e51e3b3a1dfb3b3e",
|
| 2810 |
+
"model.layers.5.mlp.down_proj.bias": "sha256:5f9f203791b185ebca839c553779a5a7741bba199aa552365d79f58a03052a4c",
|
| 2811 |
+
"model.layers.5.mlp.down_proj.weight": "sha256:a6dd283880afc392cc82e12a6875aa2c4b55e5dea6bb8245101ddd71eaef69a8",
|
| 2812 |
+
"model.layers.5.mlp.up_proj.bias": "sha256:373f493fc138473eccabd8a45bb8c0bf62500184aaec01c4c132e3fc81d51029",
|
| 2813 |
+
"model.layers.5.mlp.up_proj.weight": "sha256:118d2a0be91ac02c455ec414935b839d9bc3480ec2388feea81e7a860b9ba588",
|
| 2814 |
+
"model.layers.5.post_attention_layernorm.bias": "sha256:9fb4c6fb2d90d2c05a07de73da26eb5aeedf7f91baa9972862d8f5b72a72c059",
|
| 2815 |
+
"model.layers.5.post_attention_layernorm.weight": "sha256:239b794b91af18bbb39175f768518e41fa4891afe3894c90aeff25bcf06b5d99",
|
| 2816 |
+
"model.layers.5.self_attn.k_proj.bias": "sha256:f284831c3354b2f1f634ac6a2d1038852d0cba6b70f3ada72ebb7e625032a882",
|
| 2817 |
+
"model.layers.5.self_attn.k_proj.weight": "sha256:cf5c72434a8722e25e40b42994861d5fe07992dc93e85119827bb7e9e0afb4b4",
|
| 2818 |
+
"model.layers.5.self_attn.o_proj.bias": "sha256:52c4cd50a0ce23bb65f3cbb5fa3145f1525833336b2eb0629c089b7a37b4f9ca",
|
| 2819 |
+
"model.layers.5.self_attn.o_proj.weight": "sha256:2492159aa634395aa75835fdae65eb45c7ce36aeae208efd498cadb4757c0ab2",
|
| 2820 |
+
"model.layers.5.self_attn.q_proj.bias": "sha256:cffa594bb1669aca4c4bca4d906b1c721b8ae3b30c223daac7844aee99df4625",
|
| 2821 |
+
"model.layers.5.self_attn.q_proj.weight": "sha256:5bc2a7c9e518c5f56ceedc33adb14e0de99c63c74dc7320eb36e7ec9791291ce",
|
| 2822 |
+
"model.layers.5.self_attn.v_proj.bias": "sha256:b83ede3803ebedb992a6294ea416945a615a9476995cc8a323086a3e54e9f334",
|
| 2823 |
+
"model.layers.5.self_attn.v_proj.weight": "sha256:0f627f0f8709bab76b83f0d0aba6ace6ba609f38e4926de97d1e0ee9020207cc",
|
| 2824 |
+
"model.layers.6.input_layernorm.bias": "sha256:7262a8e7b81b3cdf32764538d29be9e472181369a9d2b5d2d6cb3f6411f54a1f",
|
| 2825 |
+
"model.layers.6.input_layernorm.weight": "sha256:9fdb10cb851b4a0065a61feb61e0f26b6d52f5e339a8a66389060414eb299193",
|
| 2826 |
+
"model.layers.6.mlp.down_proj.bias": "sha256:c8133aa90dddc0e014b7e06c842cbc037412bc71784652d0d1c600dbaa2fd13d",
|
| 2827 |
+
"model.layers.6.mlp.down_proj.weight": "sha256:0c7fbc04cb9ad15ef9351020d7555c93f0f6fb9fa2f3c1f1121b54d243aa6c44",
|
| 2828 |
+
"model.layers.6.mlp.up_proj.bias": "sha256:9a277e78de704865fda5b8f58dd201bda9f6dca1e046ba1b39524c6b2c73f017",
|
| 2829 |
+
"model.layers.6.mlp.up_proj.weight": "sha256:d3cc298948397729ef5e730d2dac1521163176f41db64a010e3219d93f1e3b2b",
|
| 2830 |
+
"model.layers.6.post_attention_layernorm.bias": "sha256:22d295a1ceac2f59a548952312902efa6420c5d535d29f256bb9b8f83677a05d",
|
| 2831 |
+
"model.layers.6.post_attention_layernorm.weight": "sha256:3abcbf8dc106b3261dd53d89cef3acf9878ae90a36f5a005fce9acaf867df97c",
|
| 2832 |
+
"model.layers.6.self_attn.k_proj.bias": "sha256:ac332ad99acc3c85c7580ca0ad146a96d47714c69e482cf1f2c2bc4198714333",
|
| 2833 |
+
"model.layers.6.self_attn.k_proj.weight": "sha256:6108dda66d64027a4b6866873087c73973e9cbc5a918cb2ec1afc09fd7f1201a",
|
| 2834 |
+
"model.layers.6.self_attn.o_proj.bias": "sha256:eabe7fe7a2a99ba1d21bca0b613092e954e9fa4139e23eb1ace206d8117638c8",
|
| 2835 |
+
"model.layers.6.self_attn.o_proj.weight": "sha256:a7d7ed6f099cb27e2dab54c348a6a5b1e94631dcb6ac39d2aa84a6b044140104",
|
| 2836 |
+
"model.layers.6.self_attn.q_proj.bias": "sha256:d7a140c20fd750116ab6ef1d01ce2017c0d5f00a4fd24c5357f4df35ab63723e",
|
| 2837 |
+
"model.layers.6.self_attn.q_proj.weight": "sha256:32fb3b9e8d7c79b38f53d23912518c148d28f34319f36c045d18bd3477beda71",
|
| 2838 |
+
"model.layers.6.self_attn.v_proj.bias": "sha256:09f058d69071ef0e0385eb08d256f3328f6a8bbcf60c85ac3d6d512d82be7bce",
|
| 2839 |
+
"model.layers.6.self_attn.v_proj.weight": "sha256:020788a25c0372ac8bd3e4046e08d8017d72fa73b30ff870a7ddfcf4825420df",
|
| 2840 |
+
"model.layers.7.input_layernorm.bias": "sha256:073f7f90c670098177b2d13ac7b18528a3e97b685b8574b7375f0d610599c9b5",
|
| 2841 |
+
"model.layers.7.input_layernorm.weight": "sha256:df12e8e3c51f2659cb5d982d0748891a14348e3fc42c4c817eaa4b2ec37c2fdb",
|
| 2842 |
+
"model.layers.7.mlp.down_proj.bias": "sha256:7c6cb43b9a0823e9656e08de68ad05e3b10e0373a22012bffeb7b7c85e58e6e9",
|
| 2843 |
+
"model.layers.7.mlp.down_proj.weight": "sha256:92aceb26b3f7847d9bef60f4a00c0c54ea3695e1862e26481a65d57d8c42a946",
|
| 2844 |
+
"model.layers.7.mlp.up_proj.bias": "sha256:4598df356cf56242b54e5936602301ec6721ce05f1cefcc37a0451f95edabab6",
|
| 2845 |
+
"model.layers.7.mlp.up_proj.weight": "sha256:8f30617c219fcc9f74584a5055f8eb32a69ef5183fad4f2abe13aa38436943f1",
|
| 2846 |
+
"model.layers.7.post_attention_layernorm.bias": "sha256:297f82f5e5874eaff65ca8523f0d11cbc9743eb56df12ebf3ee32d4868f333fa",
|
| 2847 |
+
"model.layers.7.post_attention_layernorm.weight": "sha256:975f929a8a366675773b09b4d6e57454aab757407abe66e8eb23f5c00086b2c8",
|
| 2848 |
+
"model.layers.7.self_attn.k_proj.bias": "sha256:e559813c30cb3b0161a0d63ad07c7318b13847f0079ca7246fb545d30756fed7",
|
| 2849 |
+
"model.layers.7.self_attn.k_proj.weight": "sha256:b2cfb5b1507a58fa871b55cdce7f9bf4a803e89e290d86f1fc3131606dcfb05c",
|
| 2850 |
+
"model.layers.7.self_attn.o_proj.bias": "sha256:4768a5340eb8a65d655e7ac27fae559346505063d8c643b4ff49f75cfaebc8fc",
|
| 2851 |
+
"model.layers.7.self_attn.o_proj.weight": "sha256:2d31d44f651718c8a1d97397d4f9f3ef73a6750685e4c9056059b5c1376c642a",
|
| 2852 |
+
"model.layers.7.self_attn.q_proj.bias": "sha256:6e920cf9463e094e1976743b25593b074d83ca253ea89161cb86dc25aa555a3e",
|
| 2853 |
+
"model.layers.7.self_attn.q_proj.weight": "sha256:17727e6e81f9785184f0322c224d87c6018edaadc60b2c0d06edb97e90691495",
|
| 2854 |
+
"model.layers.7.self_attn.v_proj.bias": "sha256:f1899e67bdedb4040f9e085357102b4080752cc2f68b9c1b25d2ffa408c95eed",
|
| 2855 |
+
"model.layers.7.self_attn.v_proj.weight": "sha256:d23c3a2993e1fe03aec75100dbf36bd45db0f72ca004e50282a3d40db695e1ed",
|
| 2856 |
+
"model.layers.8.input_layernorm.bias": "sha256:89b25c261219d906090238038e0ee192cd9a01887c93b917620a2e7be07cb988",
|
| 2857 |
+
"model.layers.8.input_layernorm.weight": "sha256:6d93deabdb8ac0612dcde01fd99af8265ffc3cdb19733b891da586e0998339a8",
|
| 2858 |
+
"model.layers.8.mlp.down_proj.bias": "sha256:4b8eaf8244e38c651556ce44fc8aad910bfc77d64bf5c61b7288d5441299cc16",
|
| 2859 |
+
"model.layers.8.mlp.down_proj.weight": "sha256:bb21e45c91a38a7adcc1980e26940d918c6a6267fdc17aa5b5d55fb5ffdd3c48",
|
| 2860 |
+
"model.layers.8.mlp.up_proj.bias": "sha256:f5819946ccee7cd629a79567d061195d5306bb0cf387acda7c3f22823d649a0a",
|
| 2861 |
+
"model.layers.8.mlp.up_proj.weight": "sha256:54115dbc8c6cd78539f2c9d45c2ea9492664af16e698c96774e109c9f1981577",
|
| 2862 |
+
"model.layers.8.post_attention_layernorm.bias": "sha256:286eeeb86cfa527a635e345a227aa5fd3cb97180bfd9f0a64acb8b0446f0762a",
|
| 2863 |
+
"model.layers.8.post_attention_layernorm.weight": "sha256:9e81b9bcd4f4a4b35227e5e7a4b595e485280de4e4377207abee9d03bcf62b0b",
|
| 2864 |
+
"model.layers.8.self_attn.k_proj.bias": "sha256:95c5e95eada8292f1c1af45f9812d7e0ef18a1ff5105017c8cf448cd5b1a7b95",
|
| 2865 |
+
"model.layers.8.self_attn.k_proj.weight": "sha256:f2e731a2c2da2ee57140ef9f16b456b5477cc2a580fc34bf1c3a4914250e4c96",
|
| 2866 |
+
"model.layers.8.self_attn.o_proj.bias": "sha256:e24182c092d6614e2cec53c3e5919dd0cd799efc2ca76b8850c3fd925df9f7b6",
|
| 2867 |
+
"model.layers.8.self_attn.o_proj.weight": "sha256:ea22ee651a715fddde3055cb167951a8cc009b1f4e1a28b83c5364beebea187f",
|
| 2868 |
+
"model.layers.8.self_attn.q_proj.bias": "sha256:23ed58f8753ca89cb696ae5378884dabbc60376e6ce65f4243b2c94f6bfa046d",
|
| 2869 |
+
"model.layers.8.self_attn.q_proj.weight": "sha256:d666a580cd47b2bf6df187ba4ed8c5238f0fad8618df661cd00b5c5d3ba371d9",
|
| 2870 |
+
"model.layers.8.self_attn.v_proj.bias": "sha256:e185aa9223e1ad38156f8c59510f9d398b2fcf810ac8bb6cdabb0a9c7626ef9b",
|
| 2871 |
+
"model.layers.8.self_attn.v_proj.weight": "sha256:23da4370a2dc5997a0f836be29b011d6e751f041ec5d07bd00b0f35269ec4194",
|
| 2872 |
+
"model.layers.9.input_layernorm.bias": "sha256:2eeac2a59131c6fe9efe67851cea82ee30ab41ba5197bde7328e80d9447efac4",
|
| 2873 |
+
"model.layers.9.input_layernorm.weight": "sha256:577b5dd4b3bfc5bed47a311decf9290b124c324d1c27e1e2d3e7c91cb585da47",
|
| 2874 |
+
"model.layers.9.mlp.down_proj.bias": "sha256:865cc0ce5036c9855083dd3a32dd92980756e1ff82ebe787e838395eea469e48",
|
| 2875 |
+
"model.layers.9.mlp.down_proj.weight": "sha256:4d14763a2267ac17f44754868242ec67da45888e56855e25ed12851a1f495cef",
|
| 2876 |
+
"model.layers.9.mlp.up_proj.bias": "sha256:17c0c623559e6c7c1e07f301884169e5227b98ecf565b92317f59cc462517b52",
|
| 2877 |
+
"model.layers.9.mlp.up_proj.weight": "sha256:c6c41bf002e207527d81a9044b0e65fd2b4475cc340612df2b43d5db505aa13a",
|
| 2878 |
+
"model.layers.9.post_attention_layernorm.bias": "sha256:a4efdc7d2b8f91577b065fe53c0adde52de64cd3356fe0519ae4c36ed3540da8",
|
| 2879 |
+
"model.layers.9.post_attention_layernorm.weight": "sha256:2635ea9e264019ab4c0d71c5c77c6314e114ac2bb5949d9b0a8aa106e659a49a",
|
| 2880 |
+
"model.layers.9.self_attn.k_proj.bias": "sha256:5eb5bd8806978f5471ae63d3bf50052830a5627b12fd0a775ec531d71ca96f05",
|
| 2881 |
+
"model.layers.9.self_attn.k_proj.weight": "sha256:65951dda8992ec4ede098eb2c2401bb2a2754ca1fe99296ea4f671d63ea70f75",
|
| 2882 |
+
"model.layers.9.self_attn.o_proj.bias": "sha256:439b0ba8d4d53ec24865754568cf54dc00fd9080ede474220839dac3971a34af",
|
| 2883 |
+
"model.layers.9.self_attn.o_proj.weight": "sha256:764069b8846133a0a5ec90c09e9400fc01a0cf9100ee30e33b366b9db4af7852",
|
| 2884 |
+
"model.layers.9.self_attn.q_proj.bias": "sha256:7b8dd3b4563ce8645da219f235fbfe59953ef526ab74abab1fe98cbaed682048",
|
| 2885 |
+
"model.layers.9.self_attn.q_proj.weight": "sha256:be31facd549416f551ca10cb2ade4737787fbf9a22af3d9b9a7de48535c0d74a",
|
| 2886 |
+
"model.layers.9.self_attn.v_proj.bias": "sha256:53cacc2649e15652813642b5edd1f6dafac01d085f33ad9bf53446c5a181e043",
|
| 2887 |
+
"model.layers.9.self_attn.v_proj.weight": "sha256:1fafe761659ab3a5d1577413e3bf1495a101be2a6c7689b3127b6ab9094b9725",
|
| 2888 |
+
"model.norm.bias": "sha256:9703198cbbb0d9bc49b726061c08d245198d32b0e843bef6d1e73eb9acc39324",
|
| 2889 |
+
"model.norm.weight": "sha256:a0b40ce2d22b82a94ce8af5485401b874d603b81d3323bf177be27cbf54c642b"
|
| 2890 |
+
}
|
| 2891 |
+
}
|
| 2892 |
+
}
|
| 2893 |
+
}
|
models/esm2-t12-35m-ur50d-f32-af32/origin.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"sourceModel": "facebook/esm2_t12_35M_UR50D",
|
| 3 |
+
"sourceRepo": "facebook/esm2_t12_35M_UR50D",
|
| 4 |
+
"sourceFormat": "safetensors",
|
| 5 |
+
"sourceRevision": "6fbf070e65b0b7291e7bbcd451118c216cff79d8",
|
| 6 |
+
"sourceLicense": "MIT",
|
| 7 |
+
"sourceLicenseUrl": "https://huggingface.co/facebook/esm2_t12_35M_UR50D",
|
| 8 |
+
"variant": "f32-af32",
|
| 9 |
+
"convertedAt": "2026-07-19T01:33:50-04:00"
|
| 10 |
+
}
|
models/esm2-t12-35m-ur50d-f32-af32/shard_00000.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d0c833bb71bc72c43e52dfecaf48e788f399b5460b33a67d1f0ab403ac64f12
|
| 3 |
+
size 67108864
|
models/esm2-t12-35m-ur50d-f32-af32/shard_00001.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42cfb7b67978da82d478c4b351a69d863ae53e6f0f39cc5afa147e9a98470645
|
| 3 |
+
size 65968256
|
models/esm2-t12-35m-ur50d-f32-af32/tokenizer.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"version":"1.0","truncation":null,"padding":null,"added_tokens":[{"id":1,"content":"<pad>","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":true},{"id":0,"content":"<cls>","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":true},{"id":2,"content":"<eos>","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":true},{"id":3,"content":"<unk>","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":true},{"id":32,"content":"<mask>","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":true}],"normalizer":null,"pre_tokenizer":{"type":"Split","pattern":{"String":""},"behavior":"Removed","invert":false},"post_processor":null,"decoder":{"type":"WordPiece","prefix":"##","cleanup":false},"model":{"type":"WordPiece","dropout":null,"unk_token":"<unk>","continuing_subword_prefix":"##","max_input_chars_per_word":100,"vocab":{"<cls>":0,"<pad>":1,"<eos>":2,"<unk>":3,"L":4,"A":5,"G":6,"V":7,"S":8,"E":9,"R":10,"T":11,"I":12,"D":13,"P":14,"K":15,"Q":16,"N":17,"F":18,"Y":19,"M":20,"H":21,"W":22,"C":23,"X":24,"B":25,"U":26,"Z":27,"O":28,".":29,"-":30,"<null_1>":31,"<mask>":32}},"special_tokens_map":{"pad_token":"<pad>","bos_token":"<cls>","eos_token":"<eos>","unk_token":"<unk>","mask_token":"<mask>"},"add_bos_token":true,"add_eos_token":true,"source_vocab_size":33}
|