Upload FlaxLlamaForCausalLM
#13
by
afmck
- opened
- config.json +5 -1
- flax_model.msgpack +3 -0
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -12,11 +12,15 @@
|
|
| 12 |
"model_type": "llama",
|
| 13 |
"num_attention_heads": 32,
|
| 14 |
"num_hidden_layers": 26,
|
|
|
|
| 15 |
"pad_token_id": 0,
|
|
|
|
| 16 |
"rms_norm_eps": 1e-06,
|
|
|
|
|
|
|
| 17 |
"tie_word_embeddings": false,
|
| 18 |
"torch_dtype": "float16",
|
| 19 |
-
"transformers_version": "4.
|
| 20 |
"use_cache": true,
|
| 21 |
"vocab_size": 32000
|
| 22 |
}
|
|
|
|
| 12 |
"model_type": "llama",
|
| 13 |
"num_attention_heads": 32,
|
| 14 |
"num_hidden_layers": 26,
|
| 15 |
+
"num_key_value_heads": 32,
|
| 16 |
"pad_token_id": 0,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
"rms_norm_eps": 1e-06,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
+
"transformers_version": "4.34.0.dev0",
|
| 24 |
"use_cache": true,
|
| 25 |
"vocab_size": 32000
|
| 26 |
}
|
flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20232d4151e2b09f3488a85022045a5d9341013c96aa55078dd0647c9484bb6f
|
| 3 |
+
size 6852958203
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.34.0.dev0"
|
| 7 |
}
|