初始化项目，由ModelHub XC社区提供模型
Model: prithivMLmods/Gliese-4B-OSS-0410 Source: Original Platform
This commit is contained in:
ModelHub XC
68
.gitattributes
vendored
Normal file
68
.gitattributes
vendored
Normal file
@@ -0,0 +1,68 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
model-00008-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00009-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00006-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00011-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00010-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00007-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00015-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00012-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00014-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00013-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||
model-00017-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00016-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
113
README.md
Normal file
113
README.md
Normal file
@@ -0,0 +1,113 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- prithivMLmods/Kepler-Qwen3-4B-Super-Thinking
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- trl
|
||||
- pytorch
|
||||
- text-generation-inference
|
||||
- thinking
|
||||
- gpt_oss
|
||||
- math
|
||||
- code
|
||||
- smoothing
|
||||
- agent
|
||||
---
|
||||
|
||||
|
||||
|
||||
# **Gliese-4B-OSS-0410**
|
||||
|
||||
> **Gliese-4B-OSS-0410** is a reasoning-focused model fine-tuned on **Qwen-4B** for enhanced **reasoning** and **polished token probability distributions**, delivering balanced **multilingual generation** across mathematics and general-purpose reasoning tasks.
|
||||
> The model is fine-tuned on curated **GPT-OSS synthetic dataset entries**, improving its ability to handle structured reasoning, probabilistic inference, and multilingual tasks with precision.
|
||||
|
||||
> [!note]
|
||||
> GGUF: [https://huggingface.co/prithivMLmods/Gliese-4B-OSS-0410-GGUF](https://huggingface.co/prithivMLmods/Gliese-4B-OSS-0410-GGUF)
|
||||
|
||||
---
|
||||
|
||||
## Key Features
|
||||
|
||||
1. **Enhanced Reasoning Precision**
|
||||
Refined token probability distributions improve reasoning quality and ensure balanced, context-aware outputs.
|
||||
|
||||
2. **Event Simulation and Logical Analysis**
|
||||
Capable of modeling random events, probability-driven reasoning, and structured decision-making with strong logical consistency.
|
||||
|
||||
3. **Multilingual Mathematical and General-Purpose Problem Solving**
|
||||
Delivers robust performance in **mathematics**, **probability**, and **structured multilingual tasks**, enabling broad applicability in research and education.
|
||||
|
||||
4. **Hybrid Symbolic–Probabilistic Thinking**
|
||||
Combines structured logic, probabilistic inference, and reasoning fluency to improve performance on uncertainty-driven tasks.
|
||||
|
||||
5. **Structured Output Generation**
|
||||
Generates well-formatted outputs in **LaTeX**, **Markdown**, **JSON**, **CSV**, and **YAML**, supporting technical workflows and data-oriented research.
|
||||
|
||||
6. **Optimized Lightweight Footprint**
|
||||
With **4B parameters**, it runs efficiently on **mid-range GPUs**, **offline clusters**, and **edge devices** without compromising reasoning performance.
|
||||
|
||||
---
|
||||
|
||||
## Quickstart with Transformers
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "prithivMLmods/Gliese-4B-OSS-0410"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="auto",
|
||||
device_map="auto"
|
||||
)
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
prompt = "Simulate the probability of rolling two dice and getting a sum greater than 9. Show the reasoning."
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "You are a reasoning tutor skilled in probability, logic, and multilingual problem-solving."},
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
|
||||
text = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True
|
||||
)
|
||||
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||
|
||||
generated_ids = model.generate(
|
||||
**model_inputs,
|
||||
max_new_tokens=512
|
||||
)
|
||||
generated_ids = [
|
||||
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
||||
]
|
||||
|
||||
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||||
print(response)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Intended Use
|
||||
|
||||
* Balanced multilingual reasoning and probability modeling
|
||||
* Event simulation, uncertainty analysis, and structured problem solving
|
||||
* Educational and research-focused reasoning tasks
|
||||
* Deployment in mid-resource environments with efficient inference
|
||||
* Structured technical content and data format generation
|
||||
|
||||
---
|
||||
|
||||
## Limitations
|
||||
|
||||
* Primarily focused on reasoning and mathematics; less suited for creative writing
|
||||
* Despite its 4B size, extremely complex multi-hop reasoning tasks may remain challenging
|
||||
* Prioritizes structured reasoning and probabilistic accuracy over conversational tone
|
||||
* May produce inconsistent results with **very long contexts** or **cross-domain multi-document inputs**
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
70
config.json
Normal file
70
config.json
Normal file
@@ -0,0 +1,70 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151654,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.56.2",
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2025.9.6",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"eos_token_id": 151645,
|
||||
"pad_token_id": 151654,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00017.safetensors
Normal file
3
model-00001-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:665457a942427a7ed01afc6dcf3bb640355f4e2a1abf5eb3bf57df25f7f7fc04
|
||||
size 777912456
|
||||
3
model-00002-of-00017.safetensors
Normal file
3
model-00002-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be490a7e705b714766c95c84b9efd688b2f1f058479d375568e4b54063c0e314
|
||||
size 456155728
|
||||
3
model-00003-of-00017.safetensors
Normal file
3
model-00003-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:80fffb2ac43232dbf65d5115c1028b92d9738dbd337ae6d9c4f09f2a8221864f
|
||||
size 453533216
|
||||
3
model-00004-of-00017.safetensors
Normal file
3
model-00004-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:366eb2215aafc74d269572fb43af27e4eafb1015590645a34f492416706e924c
|
||||
size 453533208
|
||||
3
model-00005-of-00017.safetensors
Normal file
3
model-00005-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:74030e5e3cce633e08d112eaadb9c94d436eb460e8fe5cbdd81cc2c7f3a8bdf0
|
||||
size 485001296
|
||||
3
model-00006-of-00017.safetensors
Normal file
3
model-00006-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b9c7428d475a718ab74d2b55190d2db398dfc60bd6c4c288f23ea9f70e9dfd9e
|
||||
size 474505592
|
||||
3
model-00007-of-00017.safetensors
Normal file
3
model-00007-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:715ab6f34ccaad2faff471554a3e19d5333e8dbb40ae948585dd0ed3bce4e3b2
|
||||
size 453533232
|
||||
3
model-00008-of-00017.safetensors
Normal file
3
model-00008-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f4e48663a3d21ac44f140e1da0e4afd241656e0744650555e02aa1e755b25fc
|
||||
size 485001320
|
||||
3
model-00009-of-00017.safetensors
Normal file
3
model-00009-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f208d3645b7fc6b7621f82c0f2eabd8bc71ee562762e1c1a230b4321e6540d2
|
||||
size 474505600
|
||||
3
model-00010-of-00017.safetensors
Normal file
3
model-00010-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3674519e103cce2abdb16e8628dd1a9d8e2a7d940940732b1406c9c299715baf
|
||||
size 453533232
|
||||
3
model-00011-of-00017.safetensors
Normal file
3
model-00011-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d54bade39a1b086a08ca30b6ae455ebb701df0a93b06e98499d547483c9d3823
|
||||
size 485001320
|
||||
3
model-00012-of-00017.safetensors
Normal file
3
model-00012-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff034910bbd908d6c5e7d6797faef66133004c23d996936d10ced493740ab00c
|
||||
size 474505600
|
||||
3
model-00013-of-00017.safetensors
Normal file
3
model-00013-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8bf9edddc359cb831e5c857e633b3d0158090ecb4d29a2f7d1aeae556e79d40
|
||||
size 453533232
|
||||
3
model-00014-of-00017.safetensors
Normal file
3
model-00014-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5a47cf60330d172defdcc1fbae2ccfee1725ed70956f88dc3aef63e2e5156b57
|
||||
size 485001320
|
||||
3
model-00015-of-00017.safetensors
Normal file
3
model-00015-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5696882a12ce60058750c92a4e273bc56ccd9adb023e74ffc9951994e3dc3c62
|
||||
size 474505600
|
||||
3
model-00016-of-00017.safetensors
Normal file
3
model-00016-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bff3fa00e5b81eeca23c22679839b00fd4c4780edcb2884c9d18d17332f2f245
|
||||
size 453533232
|
||||
3
model-00017-of-00017.safetensors
Normal file
3
model-00017-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:01dcc1ba6106516b656b265894f322d39e5f23d01dcdf9ef8812d64e773218c7
|
||||
size 251686032
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 4022468096,
|
||||
"total_size": 8044936192
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00017.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
|
||||
"model.norm.weight": "model-00017-of-00017.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 262144,
|
||||
"pad_token": "<|vision_pad|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user