Upload MistralForCausalLM
Browse files- config.json +7 -8
- generation_config.json +3 -2
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +1 -1
config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"MistralForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
-
"eos_token_id":
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 4096,
|
| 11 |
"initializer_range": 0.02,
|
|
@@ -15,14 +15,13 @@
|
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
-
"pad_token_id": 0,
|
| 19 |
"rms_norm_eps": 1e-05,
|
| 20 |
-
"rope_theta":
|
| 21 |
-
"sliding_window":
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"torch_dtype": "float16",
|
| 24 |
-
"transformers_version": "4.
|
| 25 |
"unsloth_version": "2024.3",
|
| 26 |
-
"use_cache":
|
| 27 |
-
"vocab_size":
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/Users/anima/Downloads/Nexus-IKM-Mistral-Instruct-v0.2-7B",
|
| 3 |
"architectures": [
|
| 4 |
"MistralForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 32000,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 4096,
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
|
|
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 10000.0,
|
| 20 |
+
"sliding_window": 4096,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
+
"transformers_version": "4.39.1",
|
| 24 |
"unsloth_version": "2024.3",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 32032
|
| 27 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
-
"
|
| 5 |
-
"
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 32000,
|
| 6 |
+
"transformers_version": "4.39.1"
|
| 7 |
}
|
model-00001-of-00003.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 sha256:151ca6654e050a3cb12d215360205e791f507a74a47f166f7f3bf82cfaca2876
|
| 3 |
+
size 4943424384
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999819232
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1cf3a1e207e3156735b54466b8acbb5a3ff22f1bfa53bc00fd29b5a93163fa2
|
| 3 |
size 4999819232
|
model-00003-of-00003.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:dffbab6aa7b87c0d81450bc148e4f95add1d0011d6d4ffe77ff597d0fed05a99
|
| 3 |
+
size 4540778400
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 14483988480
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|