flozi00 commited on
Commit
12ad9ec
1 Parent(s): a4e51b7

Upload of AutoGPTQ quantized model

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "OpenAssistant/falcon-40b-sft-mix-1226",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "RWForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "OpenAssistant/falcon-40b-sft-mix-1226--configuration_RW.RWConfig",
11
+ "AutoModel": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWModel",
12
+ "AutoModelForCausalLM": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWForCausalLM",
13
+ "AutoModelForQuestionAnswering": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWForSequenceClassification",
15
+ "AutoModelForTokenClassification": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWForTokenClassification"
16
+ },
17
+ "bias": false,
18
+ "bos_token_id": 11,
19
+ "eos_token_id": 11,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 8192,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "model_type": "RefinedWeb",
25
+ "n_head": 128,
26
+ "n_head_kv": 8,
27
+ "n_layer": 60,
28
+ "parallel_attn": true,
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.30.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 65040
33
+ }
gptq_model-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db95563e1914cec1d13d640822e88f7cd6392f76cf49f14469135ab30d993e27
3
+ size 23336713200
quantize_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": true,
6
+ "sym": true,
7
+ "true_sequential": true,
8
+ "model_name_or_path": null,
9
+ "model_file_base_name": null
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>MIDDLE<<",
4
+ "<|prompter|>",
5
+ ">>ABSTRACT<<",
6
+ ">>DOMAIN<<",
7
+ "<|prefix_begin|>",
8
+ "<|assistant|>",
9
+ ">>SUMMARY<<",
10
+ "<|prefix_end|>",
11
+ ">>INTRODUCTION<<",
12
+ ">>TITLE<<",
13
+ ">>PREFIX<<",
14
+ ">>SUFFIX<<",
15
+ ">>ANSWER<<",
16
+ "<|system|>",
17
+ ">>QUESTION<<",
18
+ ">>COMMENT<<"
19
+ ],
20
+ "eos_token": "<|endoftext|>",
21
+ "pad_token": "<|endoftext|>",
22
+ "sep_token": "<|endoftext|>"
23
+ }
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
+ }