TheBloke commited on
Commit
5d07bb2
1 Parent(s): f234993

AWQ model commit, 4-bit/128g

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/process/tiiuae_falcon-180b-chat/source",
3
+ "alibi": false,
4
+ "architectures": [
5
+ "FalconForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bias": false,
9
+ "bos_token_id": 11,
10
+ "eos_token_id": 11,
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 14848,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_position_embeddings": 2048,
16
+ "model_type": "falcon",
17
+ "multi_query": true,
18
+ "new_decoder_architecture": true,
19
+ "num_attention_heads": 232,
20
+ "num_hidden_layers": 80,
21
+ "num_kv_heads": 8,
22
+ "parallel_attn": true,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.33.2",
27
+ "use_cache": true,
28
+ "vocab_size": 65024
29
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
5
+ "transformers_version": "4.33.2"
6
+ }
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af919d47df8c08931c8eea43a8d9680b5143425b91bdee6d6217b4acf2b9b30
3
+ size 11922601224
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91bf98754536d8c8cc89f590c485eaf746438d53d25ac53be62b31471377110
3
+ size 9937249592
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d633bda4047079d7be687ec57c9f9410f28e28ffedb0ada9c58ff2f82be5a3c7
3
+ size 9923351696
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68890919acf9ea9a8847a1166f1e0877de5e299be5e7c28034c797be990c8463
3
+ size 9686376544
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02f12e89dfb003dded62cf4cdf06c6eb217a64176908a1a48bbcb393b2accfe
3
+ size 9923351696
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dbb63dcaa43e7d1530bee61740e9a49f99a854e032d86ff986ad10cf73c5b79
3
+ size 9686376544
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b37208b93df49bdf2fb94139c83c66101a672b15e870a3135865b509b2804bc
3
+ size 9923351696
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9008e6ef562239ccba258a073e7fdc8707046b1f13dbd2cc61a80a9ff2d3372f
3
+ size 9686376544
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335cfdeb8469e014358e2ce5495a290d087e035c4ef97c358908c09cb8dfd1b3
3
+ size 9923351696
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018143223a8f09475ddd7cf8ff6c563aa9525a601c7c0fb3c44cc13a4462b26f
3
+ size 5530651880
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quant_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "zero_point": true,
3
+ "q_group_size": 128,
4
+ "w_bit": 4,
5
+ "version": "GEMM"
6
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>"
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }