Upload tiny CohereForCausalLM
#1
by qgallouedec HF Staff - opened
- config.json +3 -3
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 32,
|
| 14 |
"layer_norm_eps": 1e-05,
|
| 15 |
-
"logit_scale": 0.
|
| 16 |
"max_position_embeddings": 8192,
|
| 17 |
"model_type": "cohere",
|
| 18 |
"num_attention_heads": 4,
|
|
@@ -21,8 +21,8 @@
|
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 10000.0,
|
| 24 |
-
"transformers_version": "4.
|
| 25 |
"use_cache": true,
|
| 26 |
"use_qk_norm": false,
|
| 27 |
-
"vocab_size":
|
| 28 |
}
|
|
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 32,
|
| 14 |
"layer_norm_eps": 1e-05,
|
| 15 |
+
"logit_scale": 0.125,
|
| 16 |
"max_position_embeddings": 8192,
|
| 17 |
"model_type": "cohere",
|
| 18 |
"num_attention_heads": 4,
|
|
|
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 10000.0,
|
| 24 |
+
"transformers_version": "4.56.2",
|
| 25 |
"use_cache": true,
|
| 26 |
"use_qk_norm": false,
|
| 27 |
+
"vocab_size": 256000
|
| 28 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 5,
|
| 4 |
"eos_token_id": 255001,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 5,
|
| 4 |
"eos_token_id": 255001,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.56.2"
|
| 7 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83f38216d109211a82391373a28eaa3ecb5c34062e171853f4832092fa26405a
|
| 3 |
+
size 4101744
|