Upload folder using huggingface_hub
Browse files- README.md +40 -13
- adapter_config.json +37 -36
- adapter_model.safetensors +1 -1
- added_tokens.json +3 -3
- chat_template.jinja +47 -47
- config.json +98 -98
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- model.safetensors.index.json +0 -0
- preprocessor_config.json +29 -29
- processor_config.json +4 -4
- special_tokens_map.json +33 -33
- tokenizer_config.json +0 -0
README.md
CHANGED
|
@@ -1,21 +1,48 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
-
- text-generation-inference
|
| 5 |
-
- transformers
|
| 6 |
- unsloth
|
| 7 |
-
|
| 8 |
-
license: apache-2.0
|
| 9 |
-
language:
|
| 10 |
-
- en
|
| 11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
# Uploaded finetuned model
|
| 14 |
|
| 15 |
-
- **Developed by:** ngkhoi
|
| 16 |
-
- **License:** apache-2.0
|
| 17 |
-
- **Finetuned from model :** unsloth/gemma-3-4b-it-unsloth-bnb-4bit
|
| 18 |
|
| 19 |
-
This gemma3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 20 |
|
| 21 |
-
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
'-license': gemma
|
| 3 |
+
language:
|
| 4 |
+
- vi
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
library_name: transformers
|
| 7 |
tags:
|
|
|
|
|
|
|
| 8 |
- unsloth
|
| 9 |
+
license: gemma
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
+
# VIETRON 4B - Fine-tuned Vietnamese model
|
| 12 |
+
<img src="https://lh3.googleusercontent.com/d/1Ez_5ubsKUpDGagqNWKlgJJm-kGUIjkKS=w1000?authuser=0" />
|
| 13 |
+
|
| 14 |
+
> [!NOTE]
|
| 15 |
+
> This is my first proper fine-tuned model, but still, the model may generate false informations or mistakes.
|
| 16 |
+
|
| 17 |
+
VieTron 4B is a Large Language Model (LLM) that has been extensively fine-tuned for Vietnamese users. With a 4-billion-parameter scale, VieTron is designed to be a smart, friendly AI assistant with a deep understanding of Vietnamese culture and education.
|
| 18 |
+
|
| 19 |
+
## Details
|
| 20 |
+
|
| 21 |
+
Trained on high-quality Vietnamese datasets that cover most fields and topics.
|
| 22 |
+
|
| 23 |
+
**More thoughtful**: the model is trained with instruction to give response step by step (or CoT), the model will not only generate results but the reasoning steps behind the results.
|
| 24 |
+
|
| 25 |
+
**More natural response style**: the datasets also includes the natural Vietnamese conversation, making the model's response more "human".
|
| 26 |
+
|
| 27 |
+
## Model info
|
| 28 |
+
|
| 29 |
+
~4 billion parameters
|
| 30 |
+
|
| 31 |
+
Currently I've only uploaded the initial version, quantized Q8_0 GGUF format to test the model. I will provide more quantized GGUF formats in the future as the model is getting better.
|
| 32 |
+
|
| 33 |
+
## Usage
|
| 34 |
+
|
| 35 |
+
LM Studio **recommended**: the easiest way to run inference. Search <sup>ngkhoi/vietron-4b</sup> and download to use this model.
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
## Limitations & Ethical Considerations
|
| 39 |
+
Knowledge Cutoff: VieTron's knowledge is limited to its training data. The model may not be aware of the latest events.
|
| 40 |
+
|
| 41 |
+
Hallucination Potential: Like all LLMs, VieTron can generate incorrect information. Please verify important facts.
|
| 42 |
+
|
| 43 |
|
|
|
|
| 44 |
|
|
|
|
|
|
|
|
|
|
| 45 |
|
|
|
|
| 46 |
|
| 47 |
+
## Contributions
|
| 48 |
+
This project is developed solely by me so any contributions to this project are truly welcome!
|
adapter_config.json
CHANGED
|
@@ -1,37 +1,38 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": {
|
| 4 |
-
"base_model_class": "Gemma3ForConditionalGeneration",
|
| 5 |
-
"parent_library": "transformers.models.gemma3.modeling_gemma3",
|
| 6 |
-
"unsloth_fixed": true
|
| 7 |
-
},
|
| 8 |
-
"base_model_name_or_path": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
|
| 9 |
-
"bias": "none",
|
| 10 |
-
"corda_config": null,
|
| 11 |
-
"eva_config": null,
|
| 12 |
-
"exclude_modules": null,
|
| 13 |
-
"fan_in_fan_out": false,
|
| 14 |
-
"inference_mode": true,
|
| 15 |
-
"init_lora_weights": true,
|
| 16 |
-
"layer_replication": null,
|
| 17 |
-
"layers_pattern": null,
|
| 18 |
-
"layers_to_transform": null,
|
| 19 |
-
"loftq_config": {},
|
| 20 |
-
"lora_alpha": 16,
|
| 21 |
-
"lora_bias": false,
|
| 22 |
-
"lora_dropout": 0.05,
|
| 23 |
-
"megatron_config": null,
|
| 24 |
-
"megatron_core": "megatron.core",
|
| 25 |
-
"modules_to_save": null,
|
| 26 |
-
"peft_type": "LORA",
|
| 27 |
-
"qalora_group_size": 16,
|
| 28 |
-
"r": 8,
|
| 29 |
-
"rank_pattern": {},
|
| 30 |
-
"revision": null,
|
| 31 |
-
"target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
|
|
|
| 37 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "Gemma3ForConditionalGeneration",
|
| 5 |
+
"parent_library": "transformers.models.gemma3.modeling_gemma3",
|
| 6 |
+
"unsloth_fixed": true
|
| 7 |
+
},
|
| 8 |
+
"base_model_name_or_path": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
|
| 9 |
+
"bias": "none",
|
| 10 |
+
"corda_config": null,
|
| 11 |
+
"eva_config": null,
|
| 12 |
+
"exclude_modules": null,
|
| 13 |
+
"fan_in_fan_out": false,
|
| 14 |
+
"inference_mode": true,
|
| 15 |
+
"init_lora_weights": true,
|
| 16 |
+
"layer_replication": null,
|
| 17 |
+
"layers_pattern": null,
|
| 18 |
+
"layers_to_transform": null,
|
| 19 |
+
"loftq_config": {},
|
| 20 |
+
"lora_alpha": 16,
|
| 21 |
+
"lora_bias": false,
|
| 22 |
+
"lora_dropout": 0.05,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 8,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
|
| 32 |
+
"target_parameters": null,
|
| 33 |
+
"task_type": "CAUSAL_LM",
|
| 34 |
+
"trainable_token_indices": null,
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_qalora": false,
|
| 37 |
+
"use_rslora": false
|
| 38 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 59675008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faeebcd3548f3e8efb67d1faefd09285a9c0098df48515e598cdc3f0881d0aaf
|
| 3 |
size 59675008
|
added_tokens.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<image_soft_token>": 262144
|
| 3 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
chat_template.jinja
CHANGED
|
@@ -1,47 +1,47 @@
|
|
| 1 |
-
{{ bos_token }}
|
| 2 |
-
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
-
{%- if messages[0]['content'] is string -%}
|
| 4 |
-
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
-
|
| 6 |
-
' -%}
|
| 7 |
-
{%- else -%}
|
| 8 |
-
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
-
|
| 10 |
-
' -%}
|
| 11 |
-
{%- endif -%}
|
| 12 |
-
{%- set loop_messages = messages[1:] -%}
|
| 13 |
-
{%- else -%}
|
| 14 |
-
{%- set first_user_prefix = "" -%}
|
| 15 |
-
{%- set loop_messages = messages -%}
|
| 16 |
-
{%- endif -%}
|
| 17 |
-
{%- for message in loop_messages -%}
|
| 18 |
-
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
-
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
-
{%- endif -%}
|
| 21 |
-
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
-
{%- set role = "model" -%}
|
| 23 |
-
{%- else -%}
|
| 24 |
-
{%- set role = message['role'] -%}
|
| 25 |
-
{%- endif -%}
|
| 26 |
-
{{ '<start_of_turn>' + role + '
|
| 27 |
-
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
-
{%- if message['content'] is string -%}
|
| 29 |
-
{{ message['content'] | trim }}
|
| 30 |
-
{%- elif message['content'] is iterable -%}
|
| 31 |
-
{%- for item in message['content'] -%}
|
| 32 |
-
{%- if item['type'] == 'image' -%}
|
| 33 |
-
{{ '<start_of_image>' }}
|
| 34 |
-
{%- elif item['type'] == 'text' -%}
|
| 35 |
-
{{ item['text'] | trim }}
|
| 36 |
-
{%- endif -%}
|
| 37 |
-
{%- endfor -%}
|
| 38 |
-
{%- else -%}
|
| 39 |
-
{{ raise_exception("Invalid content type") }}
|
| 40 |
-
{%- endif -%}
|
| 41 |
-
{{ '<end_of_turn>
|
| 42 |
-
' }}
|
| 43 |
-
{%- endfor -%}
|
| 44 |
-
{%- if add_generation_prompt -%}
|
| 45 |
-
{{ '<start_of_turn>model
|
| 46 |
-
' }}
|
| 47 |
-
{%- endif -%}
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
+
{%- if messages[0]['content'] is string -%}
|
| 4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
+
|
| 6 |
+
' -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
+
|
| 10 |
+
' -%}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- set loop_messages = messages[1:] -%}
|
| 13 |
+
{%- else -%}
|
| 14 |
+
{%- set first_user_prefix = "" -%}
|
| 15 |
+
{%- set loop_messages = messages -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- for message in loop_messages -%}
|
| 18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
+
{%- set role = "model" -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{%- set role = message['role'] -%}
|
| 25 |
+
{%- endif -%}
|
| 26 |
+
{{ '<start_of_turn>' + role + '
|
| 27 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
+
{%- if message['content'] is string -%}
|
| 29 |
+
{{ message['content'] | trim }}
|
| 30 |
+
{%- elif message['content'] is iterable -%}
|
| 31 |
+
{%- for item in message['content'] -%}
|
| 32 |
+
{%- if item['type'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{ '<start_of_turn>model
|
| 46 |
+
' }}
|
| 47 |
+
{%- endif -%}
|
config.json
CHANGED
|
@@ -1,99 +1,99 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Gemma3ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"boi_token_index": 255999,
|
| 6 |
-
"bos_token_id": 2,
|
| 7 |
-
"eoi_token_index": 256000,
|
| 8 |
-
"eos_token_id": 106,
|
| 9 |
-
"image_token_index": 262144,
|
| 10 |
-
"initializer_range": 0.02,
|
| 11 |
-
"mm_tokens_per_image": 256,
|
| 12 |
-
"model_type": "gemma3",
|
| 13 |
-
"pad_token_id": 0,
|
| 14 |
-
"text_config": {
|
| 15 |
-
"_sliding_window_pattern": 6,
|
| 16 |
-
"attention_bias": false,
|
| 17 |
-
"attention_dropout": 0.0,
|
| 18 |
-
"attn_logit_softcapping": null,
|
| 19 |
-
"cache_implementation": "hybrid",
|
| 20 |
-
"final_logit_softcapping": null,
|
| 21 |
-
"head_dim": 256,
|
| 22 |
-
"hidden_activation": "gelu_pytorch_tanh",
|
| 23 |
-
"hidden_size": 2560,
|
| 24 |
-
"initializer_range": 0.02,
|
| 25 |
-
"intermediate_size": 10240,
|
| 26 |
-
"layer_types": [
|
| 27 |
-
"sliding_attention",
|
| 28 |
-
"sliding_attention",
|
| 29 |
-
"sliding_attention",
|
| 30 |
-
"sliding_attention",
|
| 31 |
-
"sliding_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"sliding_attention",
|
| 34 |
-
"sliding_attention",
|
| 35 |
-
"sliding_attention",
|
| 36 |
-
"sliding_attention",
|
| 37 |
-
"sliding_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"sliding_attention",
|
| 40 |
-
"sliding_attention",
|
| 41 |
-
"sliding_attention",
|
| 42 |
-
"sliding_attention",
|
| 43 |
-
"sliding_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"sliding_attention",
|
| 46 |
-
"sliding_attention",
|
| 47 |
-
"sliding_attention",
|
| 48 |
-
"sliding_attention",
|
| 49 |
-
"sliding_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"sliding_attention",
|
| 52 |
-
"sliding_attention",
|
| 53 |
-
"sliding_attention",
|
| 54 |
-
"sliding_attention",
|
| 55 |
-
"sliding_attention",
|
| 56 |
-
"full_attention",
|
| 57 |
-
"sliding_attention",
|
| 58 |
-
"sliding_attention",
|
| 59 |
-
"sliding_attention",
|
| 60 |
-
"sliding_attention"
|
| 61 |
-
],
|
| 62 |
-
"max_position_embeddings": 131072,
|
| 63 |
-
"model_type": "gemma3_text",
|
| 64 |
-
"num_attention_heads": 8,
|
| 65 |
-
"num_hidden_layers": 34,
|
| 66 |
-
"num_key_value_heads": 4,
|
| 67 |
-
"query_pre_attn_scalar": 256,
|
| 68 |
-
"rms_norm_eps": 1e-06,
|
| 69 |
-
"rope_local_base_freq": 10000.0,
|
| 70 |
-
"rope_scaling": {
|
| 71 |
-
"factor": 8.0,
|
| 72 |
-
"rope_type": "linear"
|
| 73 |
-
},
|
| 74 |
-
"rope_theta": 1000000.0,
|
| 75 |
-
"sliding_window": 1024,
|
| 76 |
-
"torch_dtype": "float16",
|
| 77 |
-
"use_cache": true,
|
| 78 |
-
"vocab_size": 262208
|
| 79 |
-
},
|
| 80 |
-
"torch_dtype": "float16",
|
| 81 |
-
"transformers_version": "4.55.4",
|
| 82 |
-
"unsloth_fixed": true,
|
| 83 |
-
"unsloth_version": "2025.10.
|
| 84 |
-
"vision_config": {
|
| 85 |
-
"attention_dropout": 0.0,
|
| 86 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 87 |
-
"hidden_size": 1152,
|
| 88 |
-
"image_size": 896,
|
| 89 |
-
"intermediate_size": 4304,
|
| 90 |
-
"layer_norm_eps": 1e-06,
|
| 91 |
-
"model_type": "siglip_vision_model",
|
| 92 |
-
"num_attention_heads": 16,
|
| 93 |
-
"num_channels": 3,
|
| 94 |
-
"num_hidden_layers": 27,
|
| 95 |
-
"patch_size": 14,
|
| 96 |
-
"torch_dtype": "float16",
|
| 97 |
-
"vision_use_head": false
|
| 98 |
-
}
|
| 99 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"eoi_token_index": 256000,
|
| 8 |
+
"eos_token_id": 106,
|
| 9 |
+
"image_token_index": 262144,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"mm_tokens_per_image": 256,
|
| 12 |
+
"model_type": "gemma3",
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"text_config": {
|
| 15 |
+
"_sliding_window_pattern": 6,
|
| 16 |
+
"attention_bias": false,
|
| 17 |
+
"attention_dropout": 0.0,
|
| 18 |
+
"attn_logit_softcapping": null,
|
| 19 |
+
"cache_implementation": "hybrid",
|
| 20 |
+
"final_logit_softcapping": null,
|
| 21 |
+
"head_dim": 256,
|
| 22 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 23 |
+
"hidden_size": 2560,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 10240,
|
| 26 |
+
"layer_types": [
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention"
|
| 61 |
+
],
|
| 62 |
+
"max_position_embeddings": 131072,
|
| 63 |
+
"model_type": "gemma3_text",
|
| 64 |
+
"num_attention_heads": 8,
|
| 65 |
+
"num_hidden_layers": 34,
|
| 66 |
+
"num_key_value_heads": 4,
|
| 67 |
+
"query_pre_attn_scalar": 256,
|
| 68 |
+
"rms_norm_eps": 1e-06,
|
| 69 |
+
"rope_local_base_freq": 10000.0,
|
| 70 |
+
"rope_scaling": {
|
| 71 |
+
"factor": 8.0,
|
| 72 |
+
"rope_type": "linear"
|
| 73 |
+
},
|
| 74 |
+
"rope_theta": 1000000.0,
|
| 75 |
+
"sliding_window": 1024,
|
| 76 |
+
"torch_dtype": "float16",
|
| 77 |
+
"use_cache": true,
|
| 78 |
+
"vocab_size": 262208
|
| 79 |
+
},
|
| 80 |
+
"torch_dtype": "float16",
|
| 81 |
+
"transformers_version": "4.55.4",
|
| 82 |
+
"unsloth_fixed": true,
|
| 83 |
+
"unsloth_version": "2025.10.3",
|
| 84 |
+
"vision_config": {
|
| 85 |
+
"attention_dropout": 0.0,
|
| 86 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 87 |
+
"hidden_size": 1152,
|
| 88 |
+
"image_size": 896,
|
| 89 |
+
"intermediate_size": 4304,
|
| 90 |
+
"layer_norm_eps": 1e-06,
|
| 91 |
+
"model_type": "siglip_vision_model",
|
| 92 |
+
"num_attention_heads": 16,
|
| 93 |
+
"num_channels": 3,
|
| 94 |
+
"num_hidden_layers": 27,
|
| 95 |
+
"patch_size": 14,
|
| 96 |
+
"torch_dtype": "float16",
|
| 97 |
+
"vision_use_head": false
|
| 98 |
+
}
|
| 99 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4961251752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:064b41ff8c8cfe92f154216b8746914072ee0276c7a15bf6de867cfb727275e2
|
| 3 |
size 4961251752
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3639026128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e63281f405a8cecd7b31e412ce948e2636c3b69e35292ee293b71cf3ed7dc20
|
| 3 |
size 3639026128
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
CHANGED
|
@@ -1,29 +1,29 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_convert_rgb": null,
|
| 3 |
-
"do_normalize": true,
|
| 4 |
-
"do_pan_and_scan": null,
|
| 5 |
-
"do_rescale": true,
|
| 6 |
-
"do_resize": true,
|
| 7 |
-
"image_mean": [
|
| 8 |
-
0.5,
|
| 9 |
-
0.5,
|
| 10 |
-
0.5
|
| 11 |
-
],
|
| 12 |
-
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
-
"image_seq_length": 256,
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"pan_and_scan_max_num_crops": null,
|
| 20 |
-
"pan_and_scan_min_crop_size": null,
|
| 21 |
-
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
-
"processor_class": "Gemma3Processor",
|
| 23 |
-
"resample": 2,
|
| 24 |
-
"rescale_factor": 0.00392156862745098,
|
| 25 |
-
"size": {
|
| 26 |
-
"height": 896,
|
| 27 |
-
"width": 896
|
| 28 |
-
}
|
| 29 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pan_and_scan": null,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
+
"image_seq_length": 256,
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"pan_and_scan_max_num_crops": null,
|
| 20 |
+
"pan_and_scan_min_crop_size": null,
|
| 21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
+
"processor_class": "Gemma3Processor",
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 896,
|
| 27 |
+
"width": 896
|
| 28 |
+
}
|
| 29 |
+
}
|
processor_config.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
{
|
| 2 |
-
"image_seq_length": 256,
|
| 3 |
-
"processor_class": "Gemma3Processor"
|
| 4 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "Gemma3Processor"
|
| 4 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,33 +1,33 @@
|
|
| 1 |
-
{
|
| 2 |
-
"boi_token": "<start_of_image>",
|
| 3 |
-
"bos_token": {
|
| 4 |
-
"content": "<bos>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
"eoi_token": "<end_of_image>",
|
| 11 |
-
"eos_token": {
|
| 12 |
-
"content": "<end_of_turn>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false
|
| 17 |
-
},
|
| 18 |
-
"image_token": "<image_soft_token>",
|
| 19 |
-
"pad_token": {
|
| 20 |
-
"content": "<pad>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false
|
| 25 |
-
},
|
| 26 |
-
"unk_token": {
|
| 27 |
-
"content": "<unk>",
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"normalized": false,
|
| 30 |
-
"rstrip": false,
|
| 31 |
-
"single_word": false
|
| 32 |
-
}
|
| 33 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<end_of_turn>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|