Upload VideoChatGPTLlamaForCausalLM
Browse files- config.json +18 -4
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 0,
|
| 9 |
"eos_token_id": 1,
|
| 10 |
-
"freeze_mm_mlp_adapter":
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 4096,
|
| 13 |
"initializer_range": 0.02,
|
|
@@ -16,6 +16,7 @@
|
|
| 16 |
"max_sequence_length": 2048,
|
| 17 |
"mm_hidden_size": 1024,
|
| 18 |
"mm_use_im_start_end": true,
|
|
|
|
| 19 |
"mm_vision_select_layer": -2,
|
| 20 |
"mm_vision_tower": "openai/clip-vit-large-patch14",
|
| 21 |
"model_type": "VideoChatGPT",
|
|
@@ -24,14 +25,27 @@
|
|
| 24 |
"num_key_value_heads": 32,
|
| 25 |
"pad_token_id": -1,
|
| 26 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"rms_norm_eps": 1e-06,
|
| 28 |
"rope_scaling": null,
|
| 29 |
"rope_theta": 10000.0,
|
|
|
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
-
"torch_dtype": "
|
| 32 |
"transformers_version": "4.37.2",
|
| 33 |
-
"tune_mm_mlp_adapter":
|
| 34 |
"use_cache": false,
|
| 35 |
"use_mm_proj": true,
|
| 36 |
-
"vocab_size":
|
| 37 |
}
|
|
|
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 0,
|
| 9 |
"eos_token_id": 1,
|
| 10 |
+
"freeze_mm_mlp_adapter": false,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 4096,
|
| 13 |
"initializer_range": 0.02,
|
|
|
|
| 16 |
"max_sequence_length": 2048,
|
| 17 |
"mm_hidden_size": 1024,
|
| 18 |
"mm_use_im_start_end": true,
|
| 19 |
+
"mm_use_vid_start_end": true,
|
| 20 |
"mm_vision_select_layer": -2,
|
| 21 |
"mm_vision_tower": "openai/clip-vit-large-patch14",
|
| 22 |
"model_type": "VideoChatGPT",
|
|
|
|
| 25 |
"num_key_value_heads": 32,
|
| 26 |
"pad_token_id": -1,
|
| 27 |
"pretraining_tp": 1,
|
| 28 |
+
"quantization_config": {
|
| 29 |
+
"bnb_4bit_compute_dtype": "float16",
|
| 30 |
+
"bnb_4bit_quant_type": "nf4",
|
| 31 |
+
"bnb_4bit_use_double_quant": true,
|
| 32 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 33 |
+
"llm_int8_has_fp16_weight": false,
|
| 34 |
+
"llm_int8_skip_modules": null,
|
| 35 |
+
"llm_int8_threshold": 6.0,
|
| 36 |
+
"load_in_4bit": true,
|
| 37 |
+
"load_in_8bit": false,
|
| 38 |
+
"quant_method": "bitsandbytes"
|
| 39 |
+
},
|
| 40 |
"rms_norm_eps": 1e-06,
|
| 41 |
"rope_scaling": null,
|
| 42 |
"rope_theta": 10000.0,
|
| 43 |
+
"sep_video_conv_front": false,
|
| 44 |
"tie_word_embeddings": false,
|
| 45 |
+
"torch_dtype": "float32",
|
| 46 |
"transformers_version": "4.37.2",
|
| 47 |
+
"tune_mm_mlp_adapter": true,
|
| 48 |
"use_cache": false,
|
| 49 |
"use_mm_proj": true,
|
| 50 |
+
"vocab_size": 32006
|
| 51 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4555496476
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5e9b71f2d5c62e0a74361999ca75161f3fdb4016204835caea3d8ee1236a2e9
|
| 3 |
size 4555496476
|