初始化项目，由ModelHub XC社区提供模型
Model: mistral-experimental/pixtral-12b Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
137
README.md
Normal file
137
README.md
Normal file
@@ -0,0 +1,137 @@
|
||||
---
|
||||
library_name: transformers
|
||||
pipeline_tag: image-text-to-text
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
Transformers compatible pixtral checkpoints. Make sure to install from source or wait for v4.45!
|
||||
|
||||
|
||||
### Usage example
|
||||
|
||||
```python
|
||||
from PIL import Image
|
||||
from transformers import AutoProcessor, LlavaForConditionalGeneration
|
||||
model_id = "mistral-community/pixtral-12b"
|
||||
model = LlavaForConditionalGeneration.from_pretrained(model_id)
|
||||
processor = AutoProcessor.from_pretrained(model_id)
|
||||
|
||||
IMG_URLS = [
|
||||
"https://picsum.photos/id/237/400/300",
|
||||
"https://picsum.photos/id/231/200/300",
|
||||
"https://picsum.photos/id/27/500/500",
|
||||
"https://picsum.photos/id/17/150/600",
|
||||
]
|
||||
PROMPT = "<s>[INST]Describe the images.\n[IMG][IMG][IMG][IMG][/INST]"
|
||||
|
||||
inputs = processor(text=PROMPT, images=IMG_URLS, return_tensors="pt").to("cuda")
|
||||
generate_ids = model.generate(**inputs, max_new_tokens=500)
|
||||
output = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
||||
```
|
||||
|
||||
You should get an output similar to the below:
|
||||
```
|
||||
|
||||
"""
|
||||
Describe the images.
|
||||
Sure, let's break down each image description:
|
||||
|
||||
1. **Image 1:**
|
||||
- **Description:** A black dog with a glossy coat is sitting on a wooden floor. The dog has a focused expression and is looking directly at the camera.
|
||||
- **Details:** The wooden floor has a rustic appearance with visible wood grain patterns. The dog's eyes are a striking color, possibly brown or amber, which contrasts with its black fur.
|
||||
|
||||
2. **Image 2:**
|
||||
- **Description:** A scenic view of a mountainous landscape with a winding road cutting through it. The road is surrounded by lush green vegetation and leads to a distant valley.
|
||||
- **Details:** The mountains are rugged with steep slopes, and the sky is clear, indicating good weather. The winding road adds a sense of depth and perspective to the image.
|
||||
|
||||
3. **Image 3:**
|
||||
- **Description:** A beach scene with waves crashing against the shore. There are several people in the water and on the beach, enjoying the waves and the sunset.
|
||||
- **Details:** The waves are powerful, creating a dynamic and lively atmosphere. The sky is painted with hues of orange and pink from the setting sun, adding a warm glow to the scene.
|
||||
|
||||
4. **Image 4:**
|
||||
- **Description:** A garden path leading to a large tree with a bench underneath it. The path is bordered by well-maintained grass and flowers.
|
||||
- **Details:** The path is made of small stones or gravel, and the tree provides a shaded area with the bench invitingly placed beneath it. The surrounding area is lush and green, suggesting a well-kept garden.
|
||||
|
||||
Each image captures a different scene, from a close-up of a dog to expansive natural landscapes, showcasing various elements of nature and human interaction with it.
|
||||
"""
|
||||
```
|
||||
|
||||
### Usage with chat template
|
||||
|
||||
You can also use a chat template to format your chat history for Pixtral. Make sure that the `images` argument to the `processor` contains the images in the order
|
||||
that they appear in the chat, so that the model understands where each image is supposed to go.
|
||||
|
||||
Here's an example with text and multiple images interleaved in the same message:
|
||||
|
||||
```python
|
||||
from PIL import Image
|
||||
from transformers import AutoProcessor, LlavaForConditionalGeneration
|
||||
model_id = "mistral-community/pixtral-12b"
|
||||
model = LlavaForConditionalGeneration.from_pretrained(model_id)
|
||||
processor = AutoProcessor.from_pretrained(model_id)
|
||||
|
||||
url_dog = "https://picsum.photos/id/237/200/300"
|
||||
url_mountain = "https://picsum.photos/seed/picsum/200/300"
|
||||
|
||||
chat = [
|
||||
{
|
||||
"role": "user", "content": [
|
||||
{"type": "text", "content": "Can this animal"},
|
||||
{"type": "image"},
|
||||
{"type": "text", "content": "live here?"},
|
||||
{"type": "image"}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
prompt = processor.apply_chat_template(chat)
|
||||
inputs = processor(text=prompt, images=[url_dog, url_mountain], return_tensors="pt").to(model.device)
|
||||
generate_ids = model.generate(**inputs, max_new_tokens=500)
|
||||
output = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
||||
```
|
||||
|
||||
-----------
|
||||
From transformers>=v4.48, you can also pass image url or local path to the conversation history, and let the chat template handle the rest.
|
||||
Chat template will load the image for you and return inputs in `torch.Tensor` which you can pass directly to `model.generate()`.
|
||||
|
||||
```python
|
||||
chat = [
|
||||
{
|
||||
"role": "user", "content": [
|
||||
{"type": "text", "content": "Can this animal"},
|
||||
{"type": "image", "url": url_dog},
|
||||
{"type": "text", "content": "live here?"},
|
||||
{"type": "image", "url" : url_mountain}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
inputs = processor.apply_chat_template(chat, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors"pt").to(model.device)
|
||||
generate_ids = model.generate(**inputs, max_new_tokens=500)
|
||||
output = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
||||
```
|
||||
|
||||
You should get something like this:
|
||||
|
||||
```
|
||||
Can this animallive here?Certainly! Here are some details about the images you provided:
|
||||
|
||||
### First Image
|
||||
- **Description**: The image shows a black dog lying on a wooden surface. The dog has a curious expression with its head tilted slightly to one side.
|
||||
- **Details**: The dog appears to be a young puppy with soft, shiny fur. Its eyes are wide and alert, and it has a playful demeanor.
|
||||
- **Context**: This image could be used to illustrate a pet-friendly environment or to showcase the dog's personality.
|
||||
|
||||
### Second Image
|
||||
- **Description**: The image depicts a serene landscape with a snow-covered hill in the foreground. The sky is painted with soft hues of pink, orange, and purple, indicating a sunrise or sunset.
|
||||
- **Details**: The hill is covered in a blanket of pristine white snow, and the horizon meets the sky in a gentle curve. The scene is calm and peaceful.
|
||||
- **Context**: This image could be used to represent tranquility, natural beauty, or a winter wonderland.
|
||||
|
||||
### Combined Context
|
||||
If you're asking whether the dog can "live here," referring to the snowy landscape, it would depend on the breed and its tolerance to cold weather. Some breeds, like Huskies or Saint Bernards, are well-adapted to cold environments, while others might struggle. The dog in the first image appears to be a breed that might prefer warmer climates.
|
||||
|
||||
Would you like more information on any specific aspect?
|
||||
```
|
||||
|
||||
While it may appear that spacing in the input is disrupted, this is caused by us skipping special tokens for display, and actually "Can this animal" and "live here" are
|
||||
correctly separated by image tokens. Try decoding with special tokens included to see exactly what the model sees!
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"chat_template": "{%- if messages[0][\"role\"] == \"system\" %}{%- set system_message = messages[0][\"content\"] %}{%- set loop_messages = messages[1:] %}\n{%- else %}{%- set loop_messages = messages %}{%- endif %}{{- bos_token }}{%- for message in loop_messages %}{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif %}{%- if message[\"role\"] == \"user\" %}{%- if loop.last and system_message is defined %}{{- \"[INST]\" + system_message + \"\n\n\" }}{%- else %}{{ \"[INST]\" }}{%- endif %}{%- endif %}{%- if message[\"content\"] is not string %}{%- for chunk in message[\"content\"] %}{%- if chunk[\"type\"] == \"text\" %}{%- if \"content\" in chunk %}{{- chunk[\"content\"] }}{%- elif \"text\" in chunk %}{{- chunk[\"text\"] }}{%- endif %}{%- elif chunk[\"type\"] == \"image\" %}{{- \"[IMG]\" }}{%- else %}{{- raise_exception(\"Unrecognized content type!\") }}{%- endif %}{%- endfor %}{%- else %}{{- message[\"content\"] }}{%- endif %}{%- if message[\"role\"] == \"user\" %}{{- \"[/INST]\" }}{%- elif message[\"role\"] == \"assistant\" %}{{- eos_token}}{%- else %}{{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}{%- endif %}{%- endfor %}"
|
||||
}
|
||||
40
config.json
Normal file
40
config.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"_commit_hash": null,
|
||||
"_name_or_path": "../pixtral",
|
||||
"architectures": [
|
||||
"LlavaForConditionalGeneration"
|
||||
],
|
||||
"ignore_index": -100,
|
||||
"image_seq_length": 1,
|
||||
"image_token_index": 10,
|
||||
"model_type": "llava",
|
||||
"projector_hidden_act": "gelu",
|
||||
"text_config": {
|
||||
"hidden_size": 5120,
|
||||
"head_dim": 128,
|
||||
"intermediate_size": 14336,
|
||||
"is_composition": true,
|
||||
"max_position_embeddings": 1024000,
|
||||
"model_type": "mistral",
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000000.0,
|
||||
"sliding_window": null,
|
||||
"vocab_size": 131072
|
||||
},
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": null,
|
||||
"vision_config": {
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"image_size": 1024,
|
||||
"is_composition": true,
|
||||
"model_type": "pixtral",
|
||||
"patch_size": 16,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false
|
||||
},
|
||||
"vision_feature_layer": -1,
|
||||
"vision_feature_select_strategy": "full"
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.45.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ea4644275d194e959b3fa47742b4719c80ebce63051a737f261c493cfb076a92
|
||||
size 4990957080
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a040f77850fad5867332f08567e2331fd6ae9eb68f24d0d6584e6b2fba20cd7d
|
||||
size 4959959696
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:57e9ebe6f3c168415abe19c954fd4a23a93fbc0fedf1d16a38187bc5fa208299
|
||||
size 4907530672
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f98940380e57c4f9d567dfebe33de6d81076c91cdfbbf4955b80fd48e5969ba
|
||||
size 4907530672
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e2a77995872e79c5d9d8d60395d50cee180ed5461a413de5acc37992a3533150
|
||||
size 4257401696
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b8c9d03cd084f621896d137613209fcee96e2f528cbdb80723e1eea3c68cb176
|
||||
size 1342177424
|
||||
592
model.safetensors.index.json
Normal file
592
model.safetensors.index.json
Normal file
@@ -0,0 +1,592 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 25365479424
|
||||
},
|
||||
"weight_map": {
|
||||
"language_model.lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"language_model.model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"language_model.model.norm.weight": "model-00005-of-00006.safetensors",
|
||||
"multi_modal_projector.linear_1.bias": "model-00001-of-00006.safetensors",
|
||||
"multi_modal_projector.linear_1.weight": "model-00001-of-00006.safetensors",
|
||||
"multi_modal_projector.linear_2.bias": "model-00001-of-00006.safetensors",
|
||||
"multi_modal_projector.linear_2.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.ln_pre.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.patch_conv.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.0.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.1.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.10.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.11.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.12.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.13.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.14.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.15.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.16.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.17.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.18.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.19.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.2.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.20.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.21.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.22.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.23.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.3.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.4.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.5.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.6.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.7.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.8.ffn_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.attention_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"vision_tower.transformer.layers.9.ffn_norm.weight": "model-00001-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
27
preprocessor_config.json
Normal file
27
preprocessor_config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "PixtralImageProcessor",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"patch_size": {
|
||||
"height": 16,
|
||||
"width": 16
|
||||
},
|
||||
"processor_class": "PixtralProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"longest_edge": 1024
|
||||
}
|
||||
}
|
||||
7
processor_config.json
Normal file
7
processor_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"image_break_token": "[IMG_BREAK]",
|
||||
"image_end_token": "[IMG_END]",
|
||||
"image_token": "[IMG]",
|
||||
"patch_size": 16,
|
||||
"processor_class": "PixtralProcessor"
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
409568
tokenizer.json
Normal file
409568
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
8015
tokenizer_config.json
Normal file
8015
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user