Upload folder using huggingface_hub
Browse files- config.json +84 -0
- generation_config.json +10 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
config.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/mgoin/.cache/huggingface/hub/models--meta-llama--Llama-2-70b-chat-hf/snapshots/e9149a12809580e8602995856f8098ce973d1080",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"compression_config": {
|
10 |
+
"config_groups": {
|
11 |
+
"group_0": {
|
12 |
+
"input_activations": {
|
13 |
+
"block_structure": null,
|
14 |
+
"dynamic": true,
|
15 |
+
"group_size": null,
|
16 |
+
"num_bits": 8,
|
17 |
+
"observer": "memoryless",
|
18 |
+
"observer_kwargs": {},
|
19 |
+
"strategy": "token",
|
20 |
+
"symmetric": true,
|
21 |
+
"type": "int"
|
22 |
+
},
|
23 |
+
"output_activations": null,
|
24 |
+
"targets": [
|
25 |
+
"Linear"
|
26 |
+
],
|
27 |
+
"weights": {
|
28 |
+
"block_structure": null,
|
29 |
+
"dynamic": false,
|
30 |
+
"group_size": null,
|
31 |
+
"num_bits": 8,
|
32 |
+
"observer": "minmax",
|
33 |
+
"observer_kwargs": {},
|
34 |
+
"strategy": "channel",
|
35 |
+
"symmetric": true,
|
36 |
+
"type": "int"
|
37 |
+
}
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"format": "naive-quantized",
|
41 |
+
"global_compression_ratio": 1.23779333580055,
|
42 |
+
"ignore": [
|
43 |
+
"model.layers.2.mlp.down_proj",
|
44 |
+
"model.layers.8.mlp.down_proj",
|
45 |
+
"model.layers.12.mlp.down_proj",
|
46 |
+
"model.layers.72.mlp.down_proj",
|
47 |
+
"model.layers.73.mlp.down_proj",
|
48 |
+
"model.layers.75.mlp.down_proj",
|
49 |
+
"model.layers.76.mlp.down_proj",
|
50 |
+
"model.layers.77.mlp.down_proj",
|
51 |
+
"model.layers.79.mlp.down_proj",
|
52 |
+
"lm_head"
|
53 |
+
],
|
54 |
+
"kv_cache_scheme": null,
|
55 |
+
"quant_method": "compressed-tensors",
|
56 |
+
"quantization_status": "frozen",
|
57 |
+
"sparsity_config": {
|
58 |
+
"format": "dense",
|
59 |
+
"global_sparsity": 1.3004027645750875,
|
60 |
+
"registry_requires_subclass": false,
|
61 |
+
"sparsity_structure": "unstructured"
|
62 |
+
}
|
63 |
+
},
|
64 |
+
"eos_token_id": 2,
|
65 |
+
"hidden_act": "silu",
|
66 |
+
"hidden_size": 8192,
|
67 |
+
"initializer_range": 0.02,
|
68 |
+
"intermediate_size": 28672,
|
69 |
+
"max_position_embeddings": 4096,
|
70 |
+
"mlp_bias": false,
|
71 |
+
"model_type": "llama",
|
72 |
+
"num_attention_heads": 64,
|
73 |
+
"num_hidden_layers": 80,
|
74 |
+
"num_key_value_heads": 8,
|
75 |
+
"pretraining_tp": 1,
|
76 |
+
"rms_norm_eps": 1e-05,
|
77 |
+
"rope_scaling": null,
|
78 |
+
"rope_theta": 10000.0,
|
79 |
+
"tie_word_embeddings": false,
|
80 |
+
"torch_dtype": "float16",
|
81 |
+
"transformers_version": "4.41.2",
|
82 |
+
"use_cache": true,
|
83 |
+
"vocab_size": 32000
|
84 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.6,
|
8 |
+
"top_p": 0.9,
|
9 |
+
"transformers_version": "4.41.2"
|
10 |
+
}
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caa5d1fb1f5b89cb296ef21b30c826764e138452caa95a228932213550fc556d
|
3 |
+
size 4803424792
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:311c320769287223aa0291c5af33ae4865df68b2017d02dd35aebca57bb1cdd2
|
3 |
+
size 4900030456
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ae42aea0446c9d2227a3e13b6770aab67235d61eca17f9503630130e6739da4
|
3 |
+
size 4983944488
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8a3e99169819f5aa31992b84cb08f0f3eb2695758f28d931b2963f5bb86ebb5
|
3 |
+
size 4900104528
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09722dfb69d9e07be3817bf3afeb931715e56c22141ef5d6679ecdd70da6543a
|
3 |
+
size 4900104536
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71c23b03e85642aa47f93cdb2d058722779a848b259e39ca319eb5618c89783c
|
3 |
+
size 4984010400
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e924189faa0ad905f619eb5460fb1023fd0d5a487507d4f86236f1321b3c1c4
|
3 |
+
size 4900112504
|
model-00008-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:181b7199984c63c547ded76574f85da275cacecaa71dd583b6b149da9a9753f9
|
3 |
+
size 4900104528
|
model-00009-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97eda4251c52b555bf0db2f1c801934e5d2dcf73f31fd2c88aec9658630d31e3
|
3 |
+
size 4900104536
|
model-00010-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8279d613ebeb501461d64cfe83b6e5c2505478c51b9f18b828fec5dfae83c89
|
3 |
+
size 4984010400
|
model-00011-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96524f04a110ebe626625ccd7f8e46301c5096244774772226620522805f5df2
|
3 |
+
size 4900112504
|
model-00012-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f933df6c42b52b315c24cc076485f6a553554f80c11e63e2da1fd713cbae62bd
|
3 |
+
size 4900104528
|
model-00013-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dd5e9fcc9dd7d8e98984d90ed1fbb685886603f5537758cf96a89077ab0d48d
|
3 |
+
size 4983936368
|
model-00014-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b190de2a5827376489aeb6c65e2a122075f00cf653d11987f8c771559d55f721
|
3 |
+
size 4748865832
|
model-00015-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52548e5d123996c7e3adfd89b307612d95e03198f3f9abf22dc15687c28c5a61
|
3 |
+
size 2940645432
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|