at676 commited on
Commit
b194a39
·
verified ·
1 Parent(s): 15473fd

Upload folder using huggingface_hub (#4)

Browse files

- 9caece07fb669021407613908b6d446e2256577093eae42ab22077c1e7cc83f9 (b5fb9e78a35c71128f468c35c393ee336046f0da)
- 996dc59ff5f72438e0e2eb6cf8718a5a84689871a55b111d71a0217e89dd0ea3 (ec5d98d9eb1979b9b1c014ef8a15990ab5a184d4)
- d615c835ada5f31aec3bd4531531f06dc0a94ab59491cdc0cd307beb15e58e51 (70503c841059b4356b469339db3968436977e9e7)
- 198bdcd211d1ffcc79469f3184053185cc7964167a008a27f46549bb6909cf79 (da93a52c2ca6006a8a62ab05074b61088a2d615b)
- 3266ecd9655d1adbed198bf1bc7f49fcc5d92d48cfd344c57e1e96394ce2176e (b5de5f0130fbb1c51bafb9ce8fbef6eaee8cff10)

config.json CHANGED
@@ -4,6 +4,7 @@
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
 
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
  "hidden_act": "silu",
@@ -26,14 +27,15 @@
26
  "model_version": 1,
27
  "outlier_channel_split": false,
28
  "packsz": 4,
29
- "rescale_WH": false
 
30
  },
31
  "rms_norm_eps": 1e-05,
32
  "rope_scaling": null,
33
  "rope_theta": 10000.0,
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "float16",
36
- "transformers_version": "4.34.0",
37
  "use_cache": true,
38
  "vocab_size": 32000
39
  }
 
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
 
27
  "model_version": 1,
28
  "outlier_channel_split": false,
29
  "packsz": 4,
30
+ "rescale_WH": false,
31
+ "resid_scale_override": -1
32
  },
33
  "rms_norm_eps": 1e-05,
34
  "rope_scaling": null,
35
  "rope_theta": 10000.0,
36
  "tie_word_embeddings": false,
37
  "torch_dtype": "float16",
38
+ "transformers_version": "4.36.2",
39
  "use_cache": true,
40
  "vocab_size": 32000
41
  }
generation_config.json CHANGED
@@ -6,5 +6,5 @@
6
  "pad_token_id": 0,
7
  "temperature": 0.6,
8
  "top_p": 0.9,
9
- "transformers_version": "4.34.0"
10
  }
 
6
  "pad_token_id": 0,
7
  "temperature": 0.6,
8
  "top_p": 0.9,
9
+ "transformers_version": "4.36.2"
10
  }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6b7f34bf0f64297a78f7f29cdf65fa8555be48a2f533306d3a506efe293a04
3
+ size 4964068056
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcee277070f9bbfee6ee1a29017626160e35ed667b7a9da64ff009775365dadd
3
+ size 4985874080
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb5821eca0bb1c08df6c87f0a9737f5c7c4f4abebfa946980bf1be360a6c568
3
+ size 4964866176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4216bcdd81a2169f8b7545f800ba194870371294fcabc0de2909f9fb9b5d1974
3
+ size 3271337328
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff