Upload FalconForCausalLM
Browse files- config.json +55 -0
- generation_config.json +6 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tiiuae/falcon-40b",
|
3 |
+
"activation": "gelu",
|
4 |
+
"alibi": false,
|
5 |
+
"apply_residual_connection_post_layernorm": false,
|
6 |
+
"architectures": [
|
7 |
+
"FalconForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"auto_map": {
|
11 |
+
"AutoConfig": "tiiuae/falcon-40b--configuration_falcon.FalconConfig",
|
12 |
+
"AutoModel": "tiiuae/falcon-40b--modeling_falcon.FalconModel",
|
13 |
+
"AutoModelForCausalLM": "tiiuae/falcon-40b--modeling_falcon.FalconForCausalLM",
|
14 |
+
"AutoModelForQuestionAnswering": "tiiuae/falcon-40b--modeling_falcon.FalconForQuestionAnswering",
|
15 |
+
"AutoModelForSequenceClassification": "tiiuae/falcon-40b--modeling_falcon.FalconForSequenceClassification",
|
16 |
+
"AutoModelForTokenClassification": "tiiuae/falcon-40b--modeling_falcon.FalconForTokenClassification"
|
17 |
+
},
|
18 |
+
"bias": false,
|
19 |
+
"bos_token_id": 11,
|
20 |
+
"eos_token_id": 11,
|
21 |
+
"ffn_hidden_size": 32768,
|
22 |
+
"hidden_dropout": 0.0,
|
23 |
+
"hidden_size": 8192,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"layer_norm_epsilon": 1e-05,
|
26 |
+
"max_position_embeddings": 2048,
|
27 |
+
"model_type": "falcon",
|
28 |
+
"multi_query": true,
|
29 |
+
"new_decoder_architecture": true,
|
30 |
+
"num_attention_heads": 128,
|
31 |
+
"num_hidden_layers": 60,
|
32 |
+
"num_kv_heads": 8,
|
33 |
+
"parallel_attn": true,
|
34 |
+
"quantization_config": {
|
35 |
+
"_load_in_4bit": true,
|
36 |
+
"_load_in_8bit": false,
|
37 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
38 |
+
"bnb_4bit_quant_storage": "uint8",
|
39 |
+
"bnb_4bit_quant_type": "nf4",
|
40 |
+
"bnb_4bit_use_double_quant": true,
|
41 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
42 |
+
"llm_int8_has_fp16_weight": false,
|
43 |
+
"llm_int8_skip_modules": null,
|
44 |
+
"llm_int8_threshold": 6.0,
|
45 |
+
"load_in_4bit": true,
|
46 |
+
"load_in_8bit": false,
|
47 |
+
"quant_method": "bitsandbytes"
|
48 |
+
},
|
49 |
+
"rope_scaling": null,
|
50 |
+
"rope_theta": 10000.0,
|
51 |
+
"torch_dtype": "bfloat16",
|
52 |
+
"transformers_version": "4.40.2",
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 65024
|
55 |
+
}
|
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": "4.40.2"
|
6 |
+
}
|
model-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c398c0511b4bb573cf822fb8392db89bac23447ab548548caf04e89a85966f0e
|
3 |
+
size 4995472631
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34fbef1c4450b3b6354e418aab60caf9af45716b1695e26558be057a21f6587a
|
3 |
+
size 4908335392
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa7020657c25df2fc9de076850602a96541cd15ff3ea40a5767f36df6be9cbbd
|
3 |
+
size 4908335397
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9ac10955cf6e03eda7625a6703f0b97cda1607469cb039ca6b5db7a9f5c254d
|
3 |
+
size 4908335392
|
model-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54e0b42ec9f8ebb221530ef96ec19a1535675ebc9d2149aa05217abb74bb991d
|
3 |
+
size 2380630248
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|