davidberenstein1957 commited on
Commit
08a9a26
·
verified ·
1 Parent(s): 93a1fa9

Add files using upload-large-folder tool

Browse files
Files changed (4) hide show
  1. README.md +12 -1
  2. config.json +1 -1
  3. generation_config.json +11 -0
  4. model.safetensors +2 -2
README.md CHANGED
@@ -61,7 +61,7 @@ The configuration of the model is stored in the `config.json` file.
61
  {
62
  "config": {
63
  "architectures": [
64
- "Llama4TextModel"
65
  ],
66
  "attention_bias": false,
67
  "attention_chunk_size": 8192,
@@ -124,6 +124,17 @@ The configuration of the model is stored in the `config.json` file.
124
  "use_cache": true,
125
  "use_qk_norm": true,
126
  "vocab_size": 202048
 
 
 
 
 
 
 
 
 
 
 
127
  }
128
  }
129
  ```
 
61
  {
62
  "config": {
63
  "architectures": [
64
+ "Llama4ForCausalLM"
65
  ],
66
  "attention_bias": false,
67
  "attention_chunk_size": 8192,
 
124
  "use_cache": true,
125
  "use_qk_norm": true,
126
  "vocab_size": 202048
127
+ },
128
+ "generation_config": {
129
+ "_from_model_config": true,
130
+ "bos_token_id": 200000,
131
+ "eos_token_id": [
132
+ 200001,
133
+ 200007,
134
+ 200008
135
+ ],
136
+ "pad_token_id": 200018,
137
+ "transformers_version": "4.51.3"
138
  }
139
  }
140
  ```
config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "architectures": [
3
- "Llama4TextModel"
4
  ],
5
  "attention_bias": false,
6
  "attention_chunk_size": 8192,
 
1
  {
2
  "architectures": [
3
+ "Llama4ForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_chunk_size": 8192,
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 200000,
4
+ "eos_token_id": [
5
+ 200001,
6
+ 200007,
7
+ 200008
8
+ ],
9
+ "pad_token_id": 200018,
10
+ "transformers_version": "4.51.3"
11
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dd8a64d1ebcf93bec89f3d856962742de0f7d94931d1c2e456d3c30b291bd0e
3
- size 13154832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2defd19b1af7461456472bda405a146652059192ab48bccc020ff4ebff18472
3
+ size 26086368