cgg507 commited on
Commit
7df81f3
·
verified ·
1 Parent(s): 7f6e258

Upload folder using huggingface_hub

Browse files
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + '[/INST]' }}{% elif message['role'] == 'system' %}{{ '[SYSTEM_PROMPT] ' + message['content'] + '[/SYSTEM_PROMPT]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only user, system and assistant roles are supported!') }}{% endif %}{% endfor %}
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 12288,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 131072,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 96,
16
+ "num_hidden_layers": 88,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "config_groups": {
20
+ "group_0": {
21
+ "format": "pack-quantized",
22
+ "input_activations": null,
23
+ "output_activations": null,
24
+ "targets": [
25
+ "Linear"
26
+ ],
27
+ "weights": {
28
+ "actorder": null,
29
+ "block_structure": null,
30
+ "dynamic": false,
31
+ "group_size": 128,
32
+ "num_bits": 4,
33
+ "observer": "minmax",
34
+ "observer_kwargs": {},
35
+ "strategy": "group",
36
+ "symmetric": true,
37
+ "type": "int"
38
+ }
39
+ }
40
+ },
41
+ "format": "pack-quantized",
42
+ "global_compression_ratio": null,
43
+ "ignore": [
44
+ "lm_head"
45
+ ],
46
+ "kv_cache_scheme": null,
47
+ "quant_method": "compressed-tensors",
48
+ "quantization_status": "compressed",
49
+ "sparsity_config": {},
50
+ "transform_config": {},
51
+ "version": "0.11.0"
52
+ },
53
+ "rms_norm_eps": 1e-05,
54
+ "rope_theta": 1000000.0,
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "bfloat16",
58
+ "transformers_version": "4.55.2",
59
+ "use_cache": true,
60
+ "vocab_size": 32768
61
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.55.2"
6
+ }
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd82bd563a28ae10d217afbb4fc032c358a31bb8797685ccc9ebee1a251969cb
3
+ size 4906024600
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fd5517f57cd61d44e37b04dc2274fd017ee67051898cbb5d4a547d5c6afffa
3
+ size 4996172536
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffca4f8642c3ea9be80241d2272efb1d7d5301de73ce7c76cc308d7a2a4199f2
3
+ size 4996172632
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d0d12aa1dd62bf916145944a908de3ba36bf843da60acef16882e2ee78e1c56
3
+ size 4996172632
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649fd949aae65070c4a847a987c2bfac2a3d0fcb003c3a4694b01c806c8a08d0
3
+ size 4996172632
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47fba8a84396d8216650b9c6093dfa0be5dbfd7ecbe69ac229f82fb4c5bb422
3
+ size 4996172632
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc17e219baa395b20d1260ff4a7e0016ef5416cf13bbd8d7077b52a811bf8a05
3
+ size 4996172632
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04aad607b4841f573c7959b9083b6f5e0f17bba2482669b53da411c0ab3d0c52
3
+ size 4996172632
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafc43cf142e7c42bf0b4f12a9565b68396e2c56bf5f3de79937da781268dda9
3
+ size 4996172632
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e27030fe899fe47271a1ec4cf4bb11e7617e1fd4296c72e623f3e5cf3dbd15
3
+ size 4996172632
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e996207915e071db3f827115d04a02aec2cac7b934781d4affc6e99143fe4d58
3
+ size 4996172632
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b9923d2e5d0f2fe03fcebd4b48841feac2a035ad28abc3fde2d12f0781fee4
3
+ size 4996172632
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6c6112bf8e947550840a58ed21f39a34de8b8b3084585885ad573482f50658
3
+ size 4555741288
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ GPTQModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head]
6
+ scheme: W4A16
7
+ sequential_update: true
8
+ block_size: 128
9
+ dampening_frac: 0.01
10
+ offload_hessians: false
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_config.json ADDED
The diff for this file is too large to render. See raw diff