Add files using upload-large-folder tool
Browse files- README.md +39 -0
- added_tokens.json +10 -0
- chat_template.jinja +62 -0
- config.json +420 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +39 -0
- tokenizer.json +0 -0
- tokenizer_config.json +240 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
inference: false
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: mlx
|
| 6 |
+
tags:
|
| 7 |
+
- language
|
| 8 |
+
- granite-4.0
|
| 9 |
+
- mlx
|
| 10 |
+
base_model: ibm-granite/granite-4.0-tiny-preview
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# mlx-community/granite-4.0-tiny-preview-4bit
|
| 14 |
+
|
| 15 |
+
This model [mlx-community/granite-4.0-tiny-preview-4bit](https://huggingface.co/mlx-community/granite-4.0-tiny-preview-4bit) was
|
| 16 |
+
converted to MLX format from [ibm-granite/granite-4.0-tiny-preview](https://huggingface.co/ibm-granite/granite-4.0-tiny-preview)
|
| 17 |
+
using mlx-lm version **0.27.1**.
|
| 18 |
+
|
| 19 |
+
## Use with mlx
|
| 20 |
+
|
| 21 |
+
```bash
|
| 22 |
+
pip install mlx-lm
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
```python
|
| 26 |
+
from mlx_lm import load, generate
|
| 27 |
+
|
| 28 |
+
model, tokenizer = load("mlx-community/granite-4.0-tiny-preview-4bit")
|
| 29 |
+
|
| 30 |
+
prompt = "hello"
|
| 31 |
+
|
| 32 |
+
if tokenizer.chat_template is not None:
|
| 33 |
+
messages = [{"role": "user", "content": prompt}]
|
| 34 |
+
prompt = tokenizer.apply_chat_template(
|
| 35 |
+
messages, add_generation_prompt=True
|
| 36 |
+
)
|
| 37 |
+
|
| 38 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 39 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 49159,
|
| 3 |
+
"<|end_of_cite|>": 49156,
|
| 4 |
+
"<|end_of_plugin|>": 49158,
|
| 5 |
+
"<|end_of_role|>": 49153,
|
| 6 |
+
"<|start_of_cite|>": 49155,
|
| 7 |
+
"<|start_of_plugin|>": 49157,
|
| 8 |
+
"<|start_of_role|>": 49152,
|
| 9 |
+
"<|tool_call|>": 49154
|
| 10 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# Alias tools -> available_tools #}
|
| 2 |
+
{%- if tools and not available_tools -%}
|
| 3 |
+
{%- set available_tools = tools -%}
|
| 4 |
+
{%- endif -%}
|
| 5 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 6 |
+
{%- set system_message = messages[0]['content'] %}
|
| 7 |
+
{%- set loop_messages = messages[1:] %}
|
| 8 |
+
{%- else %}
|
| 9 |
+
{%- set system_message = "Knowledge Cutoff Date: April 2024.
|
| 10 |
+
Today's Date: " + strftime_now('%B %d, %Y') + ".
|
| 11 |
+
You are Granite, developed by IBM." %}
|
| 12 |
+
{%- if available_tools and documents %}
|
| 13 |
+
{%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.
|
| 14 |
+
Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
|
| 15 |
+
{%- elif available_tools %}
|
| 16 |
+
{%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
|
| 17 |
+
{%- elif documents %}
|
| 18 |
+
{%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
|
| 19 |
+
{%- elif thinking %}
|
| 20 |
+
{%- set system_message = system_message + " You are a helpful AI assistant.
|
| 21 |
+
Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
|
| 22 |
+
{%- else %}
|
| 23 |
+
{%- set system_message = system_message + " You are a helpful AI assistant." %}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- if 'citations' in controls and documents %}
|
| 26 |
+
{%- set system_message = system_message + '
|
| 27 |
+
Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- if 'hallucinations' in controls and documents %}
|
| 30 |
+
{%- set system_message = system_message + '
|
| 31 |
+
Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{%- set loop_messages = messages %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
|
| 36 |
+
' }}
|
| 37 |
+
{%- if available_tools %}
|
| 38 |
+
{{- '<|start_of_role|>available_tools<|end_of_role|>' }}
|
| 39 |
+
{{- available_tools | tojson(indent=4) }}
|
| 40 |
+
{{- '<|end_of_text|>
|
| 41 |
+
' }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if documents %}
|
| 44 |
+
{%- for document in documents %}
|
| 45 |
+
{{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
|
| 46 |
+
' }}
|
| 47 |
+
{{- document['text'] }}
|
| 48 |
+
{{- '<|end_of_text|>
|
| 49 |
+
' }}
|
| 50 |
+
{%- endfor %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- for message in loop_messages %}
|
| 53 |
+
{{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
|
| 54 |
+
' }}
|
| 55 |
+
{%- if loop.last and add_generation_prompt %}
|
| 56 |
+
{{- '<|start_of_role|>assistant' }}
|
| 57 |
+
{%- if controls %}
|
| 58 |
+
{{- ' ' + controls | tojson()}}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|end_of_role|>' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- endfor %}
|
config.json
ADDED
|
@@ -0,0 +1,420 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteMoeHybridForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embedding_multiplier": 12,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"init_method": "mup",
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 512,
|
| 16 |
+
"layer_types": [
|
| 17 |
+
"mamba",
|
| 18 |
+
"mamba",
|
| 19 |
+
"mamba",
|
| 20 |
+
"mamba",
|
| 21 |
+
"mamba",
|
| 22 |
+
"attention",
|
| 23 |
+
"mamba",
|
| 24 |
+
"mamba",
|
| 25 |
+
"mamba",
|
| 26 |
+
"mamba",
|
| 27 |
+
"mamba",
|
| 28 |
+
"mamba",
|
| 29 |
+
"mamba",
|
| 30 |
+
"mamba",
|
| 31 |
+
"mamba",
|
| 32 |
+
"attention",
|
| 33 |
+
"mamba",
|
| 34 |
+
"mamba",
|
| 35 |
+
"mamba",
|
| 36 |
+
"mamba",
|
| 37 |
+
"mamba",
|
| 38 |
+
"mamba",
|
| 39 |
+
"mamba",
|
| 40 |
+
"mamba",
|
| 41 |
+
"mamba",
|
| 42 |
+
"attention",
|
| 43 |
+
"mamba",
|
| 44 |
+
"mamba",
|
| 45 |
+
"mamba",
|
| 46 |
+
"mamba",
|
| 47 |
+
"mamba",
|
| 48 |
+
"mamba",
|
| 49 |
+
"mamba",
|
| 50 |
+
"mamba",
|
| 51 |
+
"mamba",
|
| 52 |
+
"attention",
|
| 53 |
+
"mamba",
|
| 54 |
+
"mamba",
|
| 55 |
+
"mamba",
|
| 56 |
+
"mamba"
|
| 57 |
+
],
|
| 58 |
+
"logits_scaling": 6,
|
| 59 |
+
"logits_to_keep": 1,
|
| 60 |
+
"mamba_chunk_size": 256,
|
| 61 |
+
"mamba_conv_bias": true,
|
| 62 |
+
"mamba_d_conv": 4,
|
| 63 |
+
"mamba_d_head": 64,
|
| 64 |
+
"mamba_d_state": 128,
|
| 65 |
+
"mamba_expand": 2,
|
| 66 |
+
"mamba_n_groups": 1,
|
| 67 |
+
"mamba_n_heads": 48,
|
| 68 |
+
"mamba_proj_bias": false,
|
| 69 |
+
"max_position_embeddings": 131072,
|
| 70 |
+
"model_type": "granitemoehybrid",
|
| 71 |
+
"normalization_function": "rmsnorm",
|
| 72 |
+
"num_attention_heads": 12,
|
| 73 |
+
"num_experts_per_tok": 6,
|
| 74 |
+
"num_hidden_layers": 40,
|
| 75 |
+
"num_key_value_heads": 4,
|
| 76 |
+
"num_local_experts": 62,
|
| 77 |
+
"output_router_logits": false,
|
| 78 |
+
"pad_token_id": 0,
|
| 79 |
+
"position_embedding_type": "nope",
|
| 80 |
+
"quantization": {
|
| 81 |
+
"group_size": 64,
|
| 82 |
+
"bits": 4,
|
| 83 |
+
"mode": "affine",
|
| 84 |
+
"model.layers.0.block_sparse_moe.router.layer": {
|
| 85 |
+
"group_size": 64,
|
| 86 |
+
"bits": 8
|
| 87 |
+
},
|
| 88 |
+
"model.layers.1.block_sparse_moe.router.layer": {
|
| 89 |
+
"group_size": 64,
|
| 90 |
+
"bits": 8
|
| 91 |
+
},
|
| 92 |
+
"model.layers.2.block_sparse_moe.router.layer": {
|
| 93 |
+
"group_size": 64,
|
| 94 |
+
"bits": 8
|
| 95 |
+
},
|
| 96 |
+
"model.layers.3.block_sparse_moe.router.layer": {
|
| 97 |
+
"group_size": 64,
|
| 98 |
+
"bits": 8
|
| 99 |
+
},
|
| 100 |
+
"model.layers.4.block_sparse_moe.router.layer": {
|
| 101 |
+
"group_size": 64,
|
| 102 |
+
"bits": 8
|
| 103 |
+
},
|
| 104 |
+
"model.layers.5.block_sparse_moe.router.layer": {
|
| 105 |
+
"group_size": 64,
|
| 106 |
+
"bits": 8
|
| 107 |
+
},
|
| 108 |
+
"model.layers.6.block_sparse_moe.router.layer": {
|
| 109 |
+
"group_size": 64,
|
| 110 |
+
"bits": 8
|
| 111 |
+
},
|
| 112 |
+
"model.layers.7.block_sparse_moe.router.layer": {
|
| 113 |
+
"group_size": 64,
|
| 114 |
+
"bits": 8
|
| 115 |
+
},
|
| 116 |
+
"model.layers.8.block_sparse_moe.router.layer": {
|
| 117 |
+
"group_size": 64,
|
| 118 |
+
"bits": 8
|
| 119 |
+
},
|
| 120 |
+
"model.layers.9.block_sparse_moe.router.layer": {
|
| 121 |
+
"group_size": 64,
|
| 122 |
+
"bits": 8
|
| 123 |
+
},
|
| 124 |
+
"model.layers.10.block_sparse_moe.router.layer": {
|
| 125 |
+
"group_size": 64,
|
| 126 |
+
"bits": 8
|
| 127 |
+
},
|
| 128 |
+
"model.layers.11.block_sparse_moe.router.layer": {
|
| 129 |
+
"group_size": 64,
|
| 130 |
+
"bits": 8
|
| 131 |
+
},
|
| 132 |
+
"model.layers.12.block_sparse_moe.router.layer": {
|
| 133 |
+
"group_size": 64,
|
| 134 |
+
"bits": 8
|
| 135 |
+
},
|
| 136 |
+
"model.layers.13.block_sparse_moe.router.layer": {
|
| 137 |
+
"group_size": 64,
|
| 138 |
+
"bits": 8
|
| 139 |
+
},
|
| 140 |
+
"model.layers.14.block_sparse_moe.router.layer": {
|
| 141 |
+
"group_size": 64,
|
| 142 |
+
"bits": 8
|
| 143 |
+
},
|
| 144 |
+
"model.layers.15.block_sparse_moe.router.layer": {
|
| 145 |
+
"group_size": 64,
|
| 146 |
+
"bits": 8
|
| 147 |
+
},
|
| 148 |
+
"model.layers.16.block_sparse_moe.router.layer": {
|
| 149 |
+
"group_size": 64,
|
| 150 |
+
"bits": 8
|
| 151 |
+
},
|
| 152 |
+
"model.layers.17.block_sparse_moe.router.layer": {
|
| 153 |
+
"group_size": 64,
|
| 154 |
+
"bits": 8
|
| 155 |
+
},
|
| 156 |
+
"model.layers.18.block_sparse_moe.router.layer": {
|
| 157 |
+
"group_size": 64,
|
| 158 |
+
"bits": 8
|
| 159 |
+
},
|
| 160 |
+
"model.layers.19.block_sparse_moe.router.layer": {
|
| 161 |
+
"group_size": 64,
|
| 162 |
+
"bits": 8
|
| 163 |
+
},
|
| 164 |
+
"model.layers.20.block_sparse_moe.router.layer": {
|
| 165 |
+
"group_size": 64,
|
| 166 |
+
"bits": 8
|
| 167 |
+
},
|
| 168 |
+
"model.layers.21.block_sparse_moe.router.layer": {
|
| 169 |
+
"group_size": 64,
|
| 170 |
+
"bits": 8
|
| 171 |
+
},
|
| 172 |
+
"model.layers.22.block_sparse_moe.router.layer": {
|
| 173 |
+
"group_size": 64,
|
| 174 |
+
"bits": 8
|
| 175 |
+
},
|
| 176 |
+
"model.layers.23.block_sparse_moe.router.layer": {
|
| 177 |
+
"group_size": 64,
|
| 178 |
+
"bits": 8
|
| 179 |
+
},
|
| 180 |
+
"model.layers.24.block_sparse_moe.router.layer": {
|
| 181 |
+
"group_size": 64,
|
| 182 |
+
"bits": 8
|
| 183 |
+
},
|
| 184 |
+
"model.layers.25.block_sparse_moe.router.layer": {
|
| 185 |
+
"group_size": 64,
|
| 186 |
+
"bits": 8
|
| 187 |
+
},
|
| 188 |
+
"model.layers.26.block_sparse_moe.router.layer": {
|
| 189 |
+
"group_size": 64,
|
| 190 |
+
"bits": 8
|
| 191 |
+
},
|
| 192 |
+
"model.layers.27.block_sparse_moe.router.layer": {
|
| 193 |
+
"group_size": 64,
|
| 194 |
+
"bits": 8
|
| 195 |
+
},
|
| 196 |
+
"model.layers.28.block_sparse_moe.router.layer": {
|
| 197 |
+
"group_size": 64,
|
| 198 |
+
"bits": 8
|
| 199 |
+
},
|
| 200 |
+
"model.layers.29.block_sparse_moe.router.layer": {
|
| 201 |
+
"group_size": 64,
|
| 202 |
+
"bits": 8
|
| 203 |
+
},
|
| 204 |
+
"model.layers.30.block_sparse_moe.router.layer": {
|
| 205 |
+
"group_size": 64,
|
| 206 |
+
"bits": 8
|
| 207 |
+
},
|
| 208 |
+
"model.layers.31.block_sparse_moe.router.layer": {
|
| 209 |
+
"group_size": 64,
|
| 210 |
+
"bits": 8
|
| 211 |
+
},
|
| 212 |
+
"model.layers.32.block_sparse_moe.router.layer": {
|
| 213 |
+
"group_size": 64,
|
| 214 |
+
"bits": 8
|
| 215 |
+
},
|
| 216 |
+
"model.layers.33.block_sparse_moe.router.layer": {
|
| 217 |
+
"group_size": 64,
|
| 218 |
+
"bits": 8
|
| 219 |
+
},
|
| 220 |
+
"model.layers.34.block_sparse_moe.router.layer": {
|
| 221 |
+
"group_size": 64,
|
| 222 |
+
"bits": 8
|
| 223 |
+
},
|
| 224 |
+
"model.layers.35.block_sparse_moe.router.layer": {
|
| 225 |
+
"group_size": 64,
|
| 226 |
+
"bits": 8
|
| 227 |
+
},
|
| 228 |
+
"model.layers.36.block_sparse_moe.router.layer": {
|
| 229 |
+
"group_size": 64,
|
| 230 |
+
"bits": 8
|
| 231 |
+
},
|
| 232 |
+
"model.layers.37.block_sparse_moe.router.layer": {
|
| 233 |
+
"group_size": 64,
|
| 234 |
+
"bits": 8
|
| 235 |
+
},
|
| 236 |
+
"model.layers.38.block_sparse_moe.router.layer": {
|
| 237 |
+
"group_size": 64,
|
| 238 |
+
"bits": 8
|
| 239 |
+
},
|
| 240 |
+
"model.layers.39.block_sparse_moe.router.layer": {
|
| 241 |
+
"group_size": 64,
|
| 242 |
+
"bits": 8
|
| 243 |
+
}
|
| 244 |
+
},
|
| 245 |
+
"quantization_config": {
|
| 246 |
+
"group_size": 64,
|
| 247 |
+
"bits": 4,
|
| 248 |
+
"mode": "affine",
|
| 249 |
+
"model.layers.0.block_sparse_moe.router.layer": {
|
| 250 |
+
"group_size": 64,
|
| 251 |
+
"bits": 8
|
| 252 |
+
},
|
| 253 |
+
"model.layers.1.block_sparse_moe.router.layer": {
|
| 254 |
+
"group_size": 64,
|
| 255 |
+
"bits": 8
|
| 256 |
+
},
|
| 257 |
+
"model.layers.2.block_sparse_moe.router.layer": {
|
| 258 |
+
"group_size": 64,
|
| 259 |
+
"bits": 8
|
| 260 |
+
},
|
| 261 |
+
"model.layers.3.block_sparse_moe.router.layer": {
|
| 262 |
+
"group_size": 64,
|
| 263 |
+
"bits": 8
|
| 264 |
+
},
|
| 265 |
+
"model.layers.4.block_sparse_moe.router.layer": {
|
| 266 |
+
"group_size": 64,
|
| 267 |
+
"bits": 8
|
| 268 |
+
},
|
| 269 |
+
"model.layers.5.block_sparse_moe.router.layer": {
|
| 270 |
+
"group_size": 64,
|
| 271 |
+
"bits": 8
|
| 272 |
+
},
|
| 273 |
+
"model.layers.6.block_sparse_moe.router.layer": {
|
| 274 |
+
"group_size": 64,
|
| 275 |
+
"bits": 8
|
| 276 |
+
},
|
| 277 |
+
"model.layers.7.block_sparse_moe.router.layer": {
|
| 278 |
+
"group_size": 64,
|
| 279 |
+
"bits": 8
|
| 280 |
+
},
|
| 281 |
+
"model.layers.8.block_sparse_moe.router.layer": {
|
| 282 |
+
"group_size": 64,
|
| 283 |
+
"bits": 8
|
| 284 |
+
},
|
| 285 |
+
"model.layers.9.block_sparse_moe.router.layer": {
|
| 286 |
+
"group_size": 64,
|
| 287 |
+
"bits": 8
|
| 288 |
+
},
|
| 289 |
+
"model.layers.10.block_sparse_moe.router.layer": {
|
| 290 |
+
"group_size": 64,
|
| 291 |
+
"bits": 8
|
| 292 |
+
},
|
| 293 |
+
"model.layers.11.block_sparse_moe.router.layer": {
|
| 294 |
+
"group_size": 64,
|
| 295 |
+
"bits": 8
|
| 296 |
+
},
|
| 297 |
+
"model.layers.12.block_sparse_moe.router.layer": {
|
| 298 |
+
"group_size": 64,
|
| 299 |
+
"bits": 8
|
| 300 |
+
},
|
| 301 |
+
"model.layers.13.block_sparse_moe.router.layer": {
|
| 302 |
+
"group_size": 64,
|
| 303 |
+
"bits": 8
|
| 304 |
+
},
|
| 305 |
+
"model.layers.14.block_sparse_moe.router.layer": {
|
| 306 |
+
"group_size": 64,
|
| 307 |
+
"bits": 8
|
| 308 |
+
},
|
| 309 |
+
"model.layers.15.block_sparse_moe.router.layer": {
|
| 310 |
+
"group_size": 64,
|
| 311 |
+
"bits": 8
|
| 312 |
+
},
|
| 313 |
+
"model.layers.16.block_sparse_moe.router.layer": {
|
| 314 |
+
"group_size": 64,
|
| 315 |
+
"bits": 8
|
| 316 |
+
},
|
| 317 |
+
"model.layers.17.block_sparse_moe.router.layer": {
|
| 318 |
+
"group_size": 64,
|
| 319 |
+
"bits": 8
|
| 320 |
+
},
|
| 321 |
+
"model.layers.18.block_sparse_moe.router.layer": {
|
| 322 |
+
"group_size": 64,
|
| 323 |
+
"bits": 8
|
| 324 |
+
},
|
| 325 |
+
"model.layers.19.block_sparse_moe.router.layer": {
|
| 326 |
+
"group_size": 64,
|
| 327 |
+
"bits": 8
|
| 328 |
+
},
|
| 329 |
+
"model.layers.20.block_sparse_moe.router.layer": {
|
| 330 |
+
"group_size": 64,
|
| 331 |
+
"bits": 8
|
| 332 |
+
},
|
| 333 |
+
"model.layers.21.block_sparse_moe.router.layer": {
|
| 334 |
+
"group_size": 64,
|
| 335 |
+
"bits": 8
|
| 336 |
+
},
|
| 337 |
+
"model.layers.22.block_sparse_moe.router.layer": {
|
| 338 |
+
"group_size": 64,
|
| 339 |
+
"bits": 8
|
| 340 |
+
},
|
| 341 |
+
"model.layers.23.block_sparse_moe.router.layer": {
|
| 342 |
+
"group_size": 64,
|
| 343 |
+
"bits": 8
|
| 344 |
+
},
|
| 345 |
+
"model.layers.24.block_sparse_moe.router.layer": {
|
| 346 |
+
"group_size": 64,
|
| 347 |
+
"bits": 8
|
| 348 |
+
},
|
| 349 |
+
"model.layers.25.block_sparse_moe.router.layer": {
|
| 350 |
+
"group_size": 64,
|
| 351 |
+
"bits": 8
|
| 352 |
+
},
|
| 353 |
+
"model.layers.26.block_sparse_moe.router.layer": {
|
| 354 |
+
"group_size": 64,
|
| 355 |
+
"bits": 8
|
| 356 |
+
},
|
| 357 |
+
"model.layers.27.block_sparse_moe.router.layer": {
|
| 358 |
+
"group_size": 64,
|
| 359 |
+
"bits": 8
|
| 360 |
+
},
|
| 361 |
+
"model.layers.28.block_sparse_moe.router.layer": {
|
| 362 |
+
"group_size": 64,
|
| 363 |
+
"bits": 8
|
| 364 |
+
},
|
| 365 |
+
"model.layers.29.block_sparse_moe.router.layer": {
|
| 366 |
+
"group_size": 64,
|
| 367 |
+
"bits": 8
|
| 368 |
+
},
|
| 369 |
+
"model.layers.30.block_sparse_moe.router.layer": {
|
| 370 |
+
"group_size": 64,
|
| 371 |
+
"bits": 8
|
| 372 |
+
},
|
| 373 |
+
"model.layers.31.block_sparse_moe.router.layer": {
|
| 374 |
+
"group_size": 64,
|
| 375 |
+
"bits": 8
|
| 376 |
+
},
|
| 377 |
+
"model.layers.32.block_sparse_moe.router.layer": {
|
| 378 |
+
"group_size": 64,
|
| 379 |
+
"bits": 8
|
| 380 |
+
},
|
| 381 |
+
"model.layers.33.block_sparse_moe.router.layer": {
|
| 382 |
+
"group_size": 64,
|
| 383 |
+
"bits": 8
|
| 384 |
+
},
|
| 385 |
+
"model.layers.34.block_sparse_moe.router.layer": {
|
| 386 |
+
"group_size": 64,
|
| 387 |
+
"bits": 8
|
| 388 |
+
},
|
| 389 |
+
"model.layers.35.block_sparse_moe.router.layer": {
|
| 390 |
+
"group_size": 64,
|
| 391 |
+
"bits": 8
|
| 392 |
+
},
|
| 393 |
+
"model.layers.36.block_sparse_moe.router.layer": {
|
| 394 |
+
"group_size": 64,
|
| 395 |
+
"bits": 8
|
| 396 |
+
},
|
| 397 |
+
"model.layers.37.block_sparse_moe.router.layer": {
|
| 398 |
+
"group_size": 64,
|
| 399 |
+
"bits": 8
|
| 400 |
+
},
|
| 401 |
+
"model.layers.38.block_sparse_moe.router.layer": {
|
| 402 |
+
"group_size": 64,
|
| 403 |
+
"bits": 8
|
| 404 |
+
},
|
| 405 |
+
"model.layers.39.block_sparse_moe.router.layer": {
|
| 406 |
+
"group_size": 64,
|
| 407 |
+
"bits": 8
|
| 408 |
+
}
|
| 409 |
+
},
|
| 410 |
+
"residual_multiplier": 0.22,
|
| 411 |
+
"rms_norm_eps": 1e-05,
|
| 412 |
+
"rope_scaling": null,
|
| 413 |
+
"rope_theta": 10000,
|
| 414 |
+
"router_aux_loss_coef": 0.0,
|
| 415 |
+
"shared_intermediate_size": 1024,
|
| 416 |
+
"tie_word_embeddings": true,
|
| 417 |
+
"transformers_version": "4.51.0.dev0",
|
| 418 |
+
"use_cache": true,
|
| 419 |
+
"vocab_size": 49160
|
| 420 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.51.0.dev0"
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8abd17f16f1c01ecf62413b0d568a5b3151fe698a3f89e77ba4e37244277fd44
|
| 3 |
+
size 3756007996
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|start_of_role|>",
|
| 4 |
+
"<|end_of_role|>",
|
| 5 |
+
"<|tool_call|>",
|
| 6 |
+
"<|start_of_cite|>",
|
| 7 |
+
"<|end_of_cite|>",
|
| 8 |
+
"<|start_of_plugin|>",
|
| 9 |
+
"<|end_of_plugin|>"
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|end_of_text|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": {
|
| 26 |
+
"content": "<|end_of_text|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"unk_token": {
|
| 33 |
+
"content": "<|end_of_text|>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
}
|
| 39 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|end_of_text|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<filename>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<gh_stars>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<empty_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<commit_before>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<commit_msg>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<commit_after>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<reponame>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"49152": {
|
| 157 |
+
"content": "<|start_of_role|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"49153": {
|
| 165 |
+
"content": "<|end_of_role|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"49154": {
|
| 173 |
+
"content": "<|tool_call|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"49155": {
|
| 181 |
+
"content": "<|start_of_cite|>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"49156": {
|
| 189 |
+
"content": "<|end_of_cite|>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"49157": {
|
| 197 |
+
"content": "<|start_of_plugin|>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"49158": {
|
| 205 |
+
"content": "<|end_of_plugin|>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"49159": {
|
| 213 |
+
"content": "<pad>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
}
|
| 220 |
+
},
|
| 221 |
+
"additional_special_tokens": [
|
| 222 |
+
"<|start_of_role|>",
|
| 223 |
+
"<|end_of_role|>",
|
| 224 |
+
"<|tool_call|>",
|
| 225 |
+
"<|start_of_cite|>",
|
| 226 |
+
"<|end_of_cite|>",
|
| 227 |
+
"<|start_of_plugin|>",
|
| 228 |
+
"<|end_of_plugin|>"
|
| 229 |
+
],
|
| 230 |
+
"bos_token": "<|end_of_text|>",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|end_of_text|>",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 235 |
+
"pad_token": "<|end_of_text|>",
|
| 236 |
+
"padding_side": "left",
|
| 237 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 238 |
+
"unk_token": "<|end_of_text|>",
|
| 239 |
+
"vocab_size": 49152
|
| 240 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|