Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- config.json +5 -15
- generation_config.json +2 -3
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
config.json
CHANGED
@@ -1,36 +1,26 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "meta-llama/Meta-Llama-3
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
-
"eos_token_id":
|
10 |
-
128001,
|
11 |
-
128008,
|
12 |
-
128009
|
13 |
-
],
|
14 |
"hidden_act": "silu",
|
15 |
"hidden_size": 4096,
|
16 |
"initializer_range": 0.02,
|
17 |
"intermediate_size": 14336,
|
18 |
-
"max_position_embeddings":
|
19 |
"mlp_bias": false,
|
20 |
"model_type": "llama",
|
21 |
"num_attention_heads": 32,
|
22 |
"num_hidden_layers": 32,
|
23 |
"num_key_value_heads": 8,
|
24 |
-
"pad_token_id":
|
25 |
"pretraining_tp": 1,
|
26 |
"rms_norm_eps": 1e-05,
|
27 |
-
"rope_scaling":
|
28 |
-
"factor": 8.0,
|
29 |
-
"high_freq_factor": 4.0,
|
30 |
-
"low_freq_factor": 1.0,
|
31 |
-
"original_max_position_embeddings": 8192,
|
32 |
-
"rope_type": "llama3"
|
33 |
-
},
|
34 |
"rope_theta": 500000.0,
|
35 |
"tie_word_embeddings": false,
|
36 |
"torch_dtype": "float16",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128009,
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 128255,
|
21 |
"pretraining_tp": 1,
|
22 |
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"rope_theta": 500000.0,
|
25 |
"tie_word_embeddings": false,
|
26 |
"torch_dtype": "float16",
|
generation_config.json
CHANGED
@@ -3,11 +3,10 @@
|
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
128001,
|
6 |
-
128008,
|
7 |
128009
|
8 |
],
|
9 |
-
"max_length":
|
10 |
-
"pad_token_id":
|
11 |
"temperature": 0.6,
|
12 |
"top_p": 0.9,
|
13 |
"transformers_version": "4.44.0"
|
|
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
128001,
|
|
|
6 |
128009
|
7 |
],
|
8 |
+
"max_length": 8192,
|
9 |
+
"pad_token_id": 128255,
|
10 |
"temperature": 0.6,
|
11 |
"top_p": 0.9,
|
12 |
"transformers_version": "4.44.0"
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:297b9439f96039b414d24486be4f05d6a318603c33fafe6633a1e23585641530
|
3 |
size 4976698592
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802616
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc7119718278297c372cdb006e0711941d3930e1f90a20f01969c870fa55e69e
|
3 |
size 4999802616
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02568b289bdd94f0f458652d7bc5493c5ad54fcf27e79f371b28291f5af40d13
|
3 |
size 4915916080
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2218811960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf8710d994cfa510351f74f9a5e8103c2a157ab7ef3d9d4a07b2685900e3e06c
|
3 |
size 2218811960
|