Hugging Face's logo

jxm
/
gpt-oss-20b-base

Text Generation
Transformers
Safetensors
English
gpt_oss
trl
sft
conversational
Model card Files
xet
Community
4
jxm commited on
Commit
f32bcda
·
verified ·
1 Parent(s): e4b0abe

Upload GptOssForCausalLM

Browse files
Files changed (10) hide show
  1. model-00001-of-00009.safetensors +1 -1
  2. model-00002-of-00009.safetensors +1 -1
  3. model-00003-of-00009.safetensors +1 -1
  4. model-00004-of-00009.safetensors +1 -1
  5. model-00005-of-00009.safetensors +1 -1
  6. model-00006-of-00009.safetensors +1 -1
  7. model-00007-of-00009.safetensors +1 -1
  8. model-00008-of-00009.safetensors +2 -2
  9. model-00009-of-00009.safetensors +2 -2
  10. model.safetensors.index.json +2 -2
model-00001-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cccebcfb676b6f63386694b84968f875d2f6f3172dfc0d799a22a4e221cd91a7
3
  size 4504304664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc729189133161b61e287dd7bdec06afc2b7f77ed1820ca53eda0553fa742230
3
  size 4504304664
model-00002-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:178b66bed3a8cfb55953ef54da7fa7bfac85edc63fc72e8404181e93c83014e7
3
  size 4939127656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4708b3da84cd7d559f5cd2eb9d0d13466ae1ccd90fdee8295d9ec3d8748582c
3
  size 4939127656
model-00003-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db1366ddde93b8f5919f8fc0d254446e702a649943ecbd14a612844d1264cde8
3
  size 4939127656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96031fa4efe1e880b2f17ac4352c3a2d251129d8140d122b9e8649a2d45c51d2
3
  size 4939127656
model-00004-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2894e10edaecc88de487b4ab87174ae656b3b0df8732906504e47cbe0451191
3
  size 4939127680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46e221c089ddcbacd6f4495a2dfccea2206cb8b21795ea868415125e9fb8139e
3
  size 4939127680
model-00005-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98abefd9ffe321e67ba132110a32a10f2be02364c57803f561a9cbf00e2f296d
3
  size 4939127704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f223ae981c1c8f4925334b8e0954ce78a613b0602d3eba28ea73f0146c9d73f3
3
  size 4939127704
model-00006-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0deb5c86dc10fde76cca242d60770b4f630299a03209598bf04674aa7784c2e
3
  size 4939127704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0e3a0ccf931369e3ebe77f1f6d0a1781d739d6cb1dfed7c54fedda3f94fe18
3
  size 4939127704
model-00007-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65d588c7488f77d2be8c644251d067972bfeeccacd4c84c2295fd6547a28e6dc
3
  size 4939127704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a3ad356e1a0d63de63f78975caf1a129d7d29bc00a7614de652aff7a4c57b0
3
  size 4939127704
model-00008-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:906e6060b5f13c74d708a3c0f2135a30ec4ae2672a44f79f3356d9c46730bf6c
3
- size 4939680904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a2d79388f1f6f1bebac3d03216b6ac47c2bf498640ab54ac8c15beb629847f
3
+ size 4939127704
model-00009-of-00009.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d4711720aa73cbb1cec952feea2cdffc746fe708f212d74714a04e9da241745
3
- size 2750809656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1951ff65d233bcb7f50485d294cced6497b8e0d9707f57087912fc2352492e
3
+ size 2751362856
model.safetensors.index.json CHANGED
@@ -280,9 +280,9 @@
280
  "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
281
  "model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
282
  "model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
283
- "model.layers.23.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
284
  "model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
285
- "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
286
  "model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
287
  "model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
288
  "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
 
280
  "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
281
  "model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
282
  "model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
283
+ "model.layers.23.mlp.experts.down_proj_bias": "model-00009-of-00009.safetensors",
284
  "model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
285
+ "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00009-of-00009.safetensors",
286
  "model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
287
  "model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
288
  "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",