ilhansertelli
commited on
Commit
•
8d7af91
1
Parent(s):
ef55533
ilhansertelli/llava-1.5-7b-hf-ft-mix
Browse files- config.json +54 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "llava-hf/llava-1.5-7b-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"ignore_index": -100,
|
7 |
+
"image_token_index": 32000,
|
8 |
+
"model_type": "llava",
|
9 |
+
"pad_token_id": 32001,
|
10 |
+
"projector_hidden_act": "gelu",
|
11 |
+
"quantization_config": {
|
12 |
+
"_load_in_4bit": true,
|
13 |
+
"_load_in_8bit": false,
|
14 |
+
"bnb_4bit_compute_dtype": "float32",
|
15 |
+
"bnb_4bit_quant_storage": "uint8",
|
16 |
+
"bnb_4bit_quant_type": "fp4",
|
17 |
+
"bnb_4bit_use_double_quant": false,
|
18 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
19 |
+
"llm_int8_has_fp16_weight": false,
|
20 |
+
"llm_int8_skip_modules": null,
|
21 |
+
"llm_int8_threshold": 6.0,
|
22 |
+
"load_in_4bit": true,
|
23 |
+
"load_in_8bit": false,
|
24 |
+
"quant_method": "bitsandbytes"
|
25 |
+
},
|
26 |
+
"text_config": {
|
27 |
+
"_name_or_path": "lmsys/vicuna-7b-v1.5",
|
28 |
+
"architectures": [
|
29 |
+
"LlamaForCausalLM"
|
30 |
+
],
|
31 |
+
"max_position_embeddings": 4096,
|
32 |
+
"model_type": "llama",
|
33 |
+
"rms_norm_eps": 1e-05,
|
34 |
+
"torch_dtype": "float16",
|
35 |
+
"vocab_size": 32064
|
36 |
+
},
|
37 |
+
"tie_word_embeddings": false,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.43.2",
|
40 |
+
"vision_config": {
|
41 |
+
"hidden_size": 1024,
|
42 |
+
"image_size": 336,
|
43 |
+
"intermediate_size": 4096,
|
44 |
+
"model_type": "clip_vision_model",
|
45 |
+
"num_attention_heads": 16,
|
46 |
+
"num_hidden_layers": 24,
|
47 |
+
"patch_size": 14,
|
48 |
+
"projection_dim": 768,
|
49 |
+
"vocab_size": 32000
|
50 |
+
},
|
51 |
+
"vision_feature_layer": -2,
|
52 |
+
"vision_feature_select_strategy": "default",
|
53 |
+
"vocab_size": 32064
|
54 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 32001,
|
6 |
+
"transformers_version": "4.43.2"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44a73963911413b5a37dfc69c07078c962b0dd2e486bfce09b3859706408c636
|
3 |
+
size 4999634089
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd5185e8e5ffb77dd2b3a5b767f9db08274c62796c4d3209ad5546c85cf5def7
|
3 |
+
size 648550945
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|