初始化项目，由ModelHub XC社区提供模型
Model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
ST[[:space:]]Presets/Captain[[:space:]]Eris[[:space:]]Violet.png filter=lfs diff=lfs merge=lfs -text
|
||||
52
README.md
Normal file
52
README.md
Normal file
@@ -0,0 +1,52 @@
|
||||
---
|
||||
base_model:
|
||||
- Nitral-AI/Captain-Eris_Violet-0.420-Rebased
|
||||
- Nitral-AI/Captain-Eris_Violet-GRPO-Rebased
|
||||
library_name: transformers
|
||||
tags:
|
||||
- merge
|
||||
- finetune
|
||||
- GRPO
|
||||
- QLORA
|
||||
- SFT
|
||||
license: other
|
||||
language:
|
||||
- en
|
||||
---
|
||||
## Update: The model image itself is now available as an importable character card for SillyTavern. This serves as an example of how to prepare your own card for use with this model.
|
||||
|
||||
|
||||
## Training Notes: This model was developed using a combination of multi-stage supervised fine-tuning, pre-trained QLoRA adapters, and multi-stage RLHF optimized with GRPO. The final model was created by merging the most promising candidates identified during the process.
|
||||
|
||||
# Quants Here: Thanks to Mradermacher <3 [Regular GGUF](https://huggingface.co/mradermacher/Captain-Eris_Violet-GRPO-v0.420-GGUF) [Imatrix GGUF](https://huggingface.co/mradermacher/Captain-Eris_Violet-GRPO-v0.420-i1-GGUF) [4bpw Exl2](https://huggingface.co/Nitrals-Quants/Captain-Eris_Violet-GRPO-v0.420-4bpw-exl2)
|
||||
|
||||
### SillyTavern Reasoning Block Parsing Example:
|
||||
|
||||
|
||||
### SillyTavern Mistral Formatting Example: [Master Import Preset Here](https://huggingface.co/Nitral-AI/Captain-Eris_Violet-GRPO-v0.420/tree/main/ST%20Presets)
|
||||
|
||||
|
||||
## Series Comparison:
|
||||
|
||||
|
||||
|
||||
# The following YAML configuration was used to produce this final version of the model:
|
||||
```yaml
|
||||
slices:
|
||||
- sources:
|
||||
- model: Nitral-AI/Captain-Eris_Violet-0.420-Rebased
|
||||
layer_range: [0, 40]
|
||||
- model: Nitral-AI/Captain-Eris_Violet-GRPO-Rebased
|
||||
layer_range: [0, 40]
|
||||
merge_method: slerp
|
||||
base_model: Nitral-AI/Captain-Eris_Violet-0.420-Rebased
|
||||
parameters:
|
||||
t:
|
||||
- filter: self_attn
|
||||
value: [0, 0.5, 0.3, 0.7, 1]
|
||||
- filter: mlp
|
||||
value: [1, 0.5, 0.7, 0.3, 0]
|
||||
- value: 0.420
|
||||
dtype: bfloat16
|
||||
|
||||
```
|
||||
3
ST Presets/Captain Eris Violet.png
Normal file
3
ST Presets/Captain Eris Violet.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fdaa08b37fe794ac4981eec77c4c763ef689c74f291fd676e7b1127c5a7bfc56
|
||||
size 746890
|
||||
165
ST Presets/ChatML_Master-Import.json
Normal file
165
ST Presets/ChatML_Master-Import.json
Normal file
@@ -0,0 +1,165 @@
|
||||
{
|
||||
"instruct": {
|
||||
"input_sequence": "<|im_start|>user",
|
||||
"output_sequence": "<|im_start|>assistant",
|
||||
"last_output_sequence": "",
|
||||
"system_sequence": "<|im_start|>system",
|
||||
"stop_sequence": "<|im_end|>",
|
||||
"wrap": true,
|
||||
"macro": true,
|
||||
"names_behavior": "always",
|
||||
"activation_regex": "",
|
||||
"system_sequence_prefix": "",
|
||||
"system_sequence_suffix": "",
|
||||
"first_output_sequence": "",
|
||||
"skip_examples": false,
|
||||
"output_suffix": "<|im_end|>",
|
||||
"input_suffix": "<|im_end|>",
|
||||
"system_suffix": "<|im_end|>",
|
||||
"user_alignment_message": "",
|
||||
"system_same_as_user": false,
|
||||
"last_system_sequence": "",
|
||||
"first_input_sequence": "",
|
||||
"last_input_sequence": "",
|
||||
"names_force_groups": true,
|
||||
"name": "ChatML"
|
||||
},
|
||||
"context": {
|
||||
"story_string": "<|im_start|>system\n{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}<|im_end|>",
|
||||
"example_separator": "",
|
||||
"chat_start": "",
|
||||
"use_stop_strings": false,
|
||||
"allow_jailbreak": false,
|
||||
"names_as_stop_strings": true,
|
||||
"always_force_name2": true,
|
||||
"trim_sentences": false,
|
||||
"single_line": false,
|
||||
"name": "ChatML"
|
||||
},
|
||||
"sysprompt": {
|
||||
"name": "Reasoning-Meme",
|
||||
"content": "It is currently {{weekday}} {{date}} {{time}}. Take a breath and use as much time as you need. Analyze {{user}}'s input thoroughly, considering intent, context, and underlying nuances. Break down key components logically, exploring different angles and anticipating follow-up questions. Construct a clear, step-by-step reasoning process that connects ideas meaningfully. Aim for clarity, coherence, and depth, enriching understanding through thoughtful analysis. Use the format below during every reply:\n<reasoning> ... </reasoning> <answer> ... </answer>"
|
||||
},
|
||||
"preset": {
|
||||
"temp": 0.85,
|
||||
"temperature_last": true,
|
||||
"top_p": 1,
|
||||
"top_k": 0,
|
||||
"top_a": 0,
|
||||
"tfs": 1,
|
||||
"epsilon_cutoff": 0,
|
||||
"eta_cutoff": 0,
|
||||
"typical_p": 1,
|
||||
"min_p": 0.1,
|
||||
"rep_pen": 1,
|
||||
"rep_pen_range": 0,
|
||||
"rep_pen_decay": 0,
|
||||
"rep_pen_slope": 1,
|
||||
"no_repeat_ngram_size": 0,
|
||||
"penalty_alpha": 0,
|
||||
"num_beams": 1,
|
||||
"length_penalty": 1,
|
||||
"min_length": 0,
|
||||
"encoder_rep_pen": 1,
|
||||
"freq_pen": 0,
|
||||
"presence_pen": 0,
|
||||
"skew": 0,
|
||||
"do_sample": true,
|
||||
"early_stopping": false,
|
||||
"dynatemp": false,
|
||||
"min_temp": 0.85,
|
||||
"max_temp": 1.15,
|
||||
"dynatemp_exponent": 1,
|
||||
"smoothing_factor": 0,
|
||||
"smoothing_curve": 1,
|
||||
"dry_allowed_length": 2,
|
||||
"dry_multiplier": 0,
|
||||
"dry_base": 1.75,
|
||||
"dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\"]",
|
||||
"dry_penalty_last_n": 0,
|
||||
"add_bos_token": true,
|
||||
"ban_eos_token": false,
|
||||
"skip_special_tokens": true,
|
||||
"mirostat_mode": 0,
|
||||
"mirostat_tau": 5,
|
||||
"mirostat_eta": 0.1,
|
||||
"guidance_scale": 1,
|
||||
"negative_prompt": "",
|
||||
"grammar_string": "",
|
||||
"json_schema": {},
|
||||
"banned_tokens": "",
|
||||
"sampler_priority": [
|
||||
"repetition_penalty",
|
||||
"presence_penalty",
|
||||
"frequency_penalty",
|
||||
"dry",
|
||||
"temperature",
|
||||
"dynamic_temperature",
|
||||
"quadratic_sampling",
|
||||
"top_k",
|
||||
"top_p",
|
||||
"typical_p",
|
||||
"epsilon_cutoff",
|
||||
"eta_cutoff",
|
||||
"tfs",
|
||||
"top_a",
|
||||
"min_p",
|
||||
"mirostat",
|
||||
"xtc",
|
||||
"encoder_repetition_penalty",
|
||||
"no_repeat_ngram"
|
||||
],
|
||||
"samplers": [
|
||||
"dry",
|
||||
"top_k",
|
||||
"tfs_z",
|
||||
"typical_p",
|
||||
"top_p",
|
||||
"min_p",
|
||||
"xtc",
|
||||
"temperature"
|
||||
],
|
||||
"samplers_priorities": [
|
||||
"dry",
|
||||
"penalties",
|
||||
"no_repeat_ngram",
|
||||
"temperature",
|
||||
"top_nsigma",
|
||||
"top_p_top_k",
|
||||
"top_a",
|
||||
"min_p",
|
||||
"tfs",
|
||||
"eta_cutoff",
|
||||
"epsilon_cutoff",
|
||||
"typical_p",
|
||||
"quadratic",
|
||||
"xtc"
|
||||
],
|
||||
"ignore_eos_token": false,
|
||||
"spaces_between_special_tokens": false,
|
||||
"speculative_ngram": false,
|
||||
"sampler_order": [
|
||||
6,
|
||||
0,
|
||||
1,
|
||||
3,
|
||||
4,
|
||||
2,
|
||||
5
|
||||
],
|
||||
"logit_bias": [],
|
||||
"xtc_threshold": 0.1,
|
||||
"xtc_probability": 0,
|
||||
"nsigma": 0,
|
||||
"rep_pen_size": 0,
|
||||
"genamt": 2400,
|
||||
"max_length": 16384,
|
||||
"name": "Nitral-Baseline-Preset"
|
||||
},
|
||||
"reasoning": {
|
||||
"prefix": "<reasoning>",
|
||||
"suffix": "</reasoning>",
|
||||
"separator": "\n\n",
|
||||
"name": "Nitral_Reasoning-Meme"
|
||||
}
|
||||
}
|
||||
165
ST Presets/MistralV3_Master-Import.json
Normal file
165
ST Presets/MistralV3_Master-Import.json
Normal file
@@ -0,0 +1,165 @@
|
||||
{
|
||||
"instruct": {
|
||||
"input_sequence": "[INST]",
|
||||
"output_sequence": "[/INST]",
|
||||
"last_output_sequence": "",
|
||||
"system_sequence": "",
|
||||
"stop_sequence": "",
|
||||
"wrap": false,
|
||||
"macro": true,
|
||||
"names_behavior": "always",
|
||||
"activation_regex": "",
|
||||
"system_sequence_prefix": "",
|
||||
"system_sequence_suffix": "",
|
||||
"first_output_sequence": "",
|
||||
"skip_examples": false,
|
||||
"output_suffix": "</s>",
|
||||
"input_suffix": "",
|
||||
"system_suffix": "",
|
||||
"user_alignment_message": "Let's get started. Please respond based on the information and instructions provided above.",
|
||||
"system_same_as_user": true,
|
||||
"last_system_sequence": "",
|
||||
"first_input_sequence": "",
|
||||
"last_input_sequence": "",
|
||||
"names_force_groups": true,
|
||||
"name": "Mistral V3-Tekken"
|
||||
},
|
||||
"context": {
|
||||
"story_string": "[INST]{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{personality}}\n{{/if}}{{#if scenario}}{{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}[/INST]Understood.</s>",
|
||||
"example_separator": "",
|
||||
"chat_start": "",
|
||||
"use_stop_strings": false,
|
||||
"allow_jailbreak": false,
|
||||
"names_as_stop_strings": true,
|
||||
"always_force_name2": true,
|
||||
"trim_sentences": false,
|
||||
"single_line": false,
|
||||
"name": "Mistral V3-Tekken"
|
||||
},
|
||||
"sysprompt": {
|
||||
"name": "Reasoning-Meme",
|
||||
"content": "It is currently {{weekday}} {{date}} {{time}}. Take a breath and use as much time as you need. Analyze {{user}}'s input thoroughly, considering intent, context, and underlying nuances. Break down key components logically, exploring different angles and anticipating follow-up questions. Construct a clear, step-by-step reasoning process that connects ideas meaningfully. Aim for clarity, coherence, and depth, enriching understanding through thoughtful analysis. Use the format below during every reply:\n<reasoning> ... </reasoning> <answer> ... </answer>"
|
||||
},
|
||||
"preset": {
|
||||
"temp": 0.85,
|
||||
"temperature_last": true,
|
||||
"top_p": 1,
|
||||
"top_k": 0,
|
||||
"top_a": 0,
|
||||
"tfs": 1,
|
||||
"epsilon_cutoff": 0,
|
||||
"eta_cutoff": 0,
|
||||
"typical_p": 1,
|
||||
"min_p": 0.1,
|
||||
"rep_pen": 1,
|
||||
"rep_pen_range": 0,
|
||||
"rep_pen_decay": 0,
|
||||
"rep_pen_slope": 1,
|
||||
"no_repeat_ngram_size": 0,
|
||||
"penalty_alpha": 0,
|
||||
"num_beams": 1,
|
||||
"length_penalty": 1,
|
||||
"min_length": 0,
|
||||
"encoder_rep_pen": 1,
|
||||
"freq_pen": 0,
|
||||
"presence_pen": 0,
|
||||
"skew": 0,
|
||||
"do_sample": true,
|
||||
"early_stopping": false,
|
||||
"dynatemp": false,
|
||||
"min_temp": 0.85,
|
||||
"max_temp": 1.15,
|
||||
"dynatemp_exponent": 1,
|
||||
"smoothing_factor": 0,
|
||||
"smoothing_curve": 1,
|
||||
"dry_allowed_length": 2,
|
||||
"dry_multiplier": 0,
|
||||
"dry_base": 1.75,
|
||||
"dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\"]",
|
||||
"dry_penalty_last_n": 0,
|
||||
"add_bos_token": true,
|
||||
"ban_eos_token": false,
|
||||
"skip_special_tokens": true,
|
||||
"mirostat_mode": 0,
|
||||
"mirostat_tau": 5,
|
||||
"mirostat_eta": 0.1,
|
||||
"guidance_scale": 1,
|
||||
"negative_prompt": "",
|
||||
"grammar_string": "",
|
||||
"json_schema": {},
|
||||
"banned_tokens": "",
|
||||
"sampler_priority": [
|
||||
"repetition_penalty",
|
||||
"presence_penalty",
|
||||
"frequency_penalty",
|
||||
"dry",
|
||||
"temperature",
|
||||
"dynamic_temperature",
|
||||
"quadratic_sampling",
|
||||
"top_k",
|
||||
"top_p",
|
||||
"typical_p",
|
||||
"epsilon_cutoff",
|
||||
"eta_cutoff",
|
||||
"tfs",
|
||||
"top_a",
|
||||
"min_p",
|
||||
"mirostat",
|
||||
"xtc",
|
||||
"encoder_repetition_penalty",
|
||||
"no_repeat_ngram"
|
||||
],
|
||||
"samplers": [
|
||||
"dry",
|
||||
"top_k",
|
||||
"tfs_z",
|
||||
"typical_p",
|
||||
"top_p",
|
||||
"min_p",
|
||||
"xtc",
|
||||
"temperature"
|
||||
],
|
||||
"samplers_priorities": [
|
||||
"dry",
|
||||
"penalties",
|
||||
"no_repeat_ngram",
|
||||
"temperature",
|
||||
"top_nsigma",
|
||||
"top_p_top_k",
|
||||
"top_a",
|
||||
"min_p",
|
||||
"tfs",
|
||||
"eta_cutoff",
|
||||
"epsilon_cutoff",
|
||||
"typical_p",
|
||||
"quadratic",
|
||||
"xtc"
|
||||
],
|
||||
"ignore_eos_token": false,
|
||||
"spaces_between_special_tokens": false,
|
||||
"speculative_ngram": false,
|
||||
"sampler_order": [
|
||||
6,
|
||||
0,
|
||||
1,
|
||||
3,
|
||||
4,
|
||||
2,
|
||||
5
|
||||
],
|
||||
"logit_bias": [],
|
||||
"xtc_threshold": 0.1,
|
||||
"xtc_probability": 0,
|
||||
"nsigma": 0,
|
||||
"rep_pen_size": 0,
|
||||
"genamt": 2400,
|
||||
"max_length": 16384,
|
||||
"name": "Nitral-Baseline-Preset"
|
||||
},
|
||||
"reasoning": {
|
||||
"prefix": "<reasoning>",
|
||||
"suffix": "</reasoning>",
|
||||
"separator": "\n\n",
|
||||
"name": "Nitral_Reasoning-Meme"
|
||||
}
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "Nitral-AI/Captain-Eris_Violet-0.420-Rebased",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 1024000,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 10,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.48.2",
|
||||
"unsloth_version": "2025.2.5",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
16
mergekit_config.yml
Normal file
16
mergekit_config.yml
Normal file
@@ -0,0 +1,16 @@
|
||||
slices:
|
||||
- sources:
|
||||
- model: Nitral-AI/Captain-Eris_Violet-0.420-Rebased
|
||||
layer_range: [0, 40]
|
||||
- model: Nitral-AI/Captain-Eris_Violet-GRPO-Rebased
|
||||
layer_range: [0, 40]
|
||||
merge_method: slerp
|
||||
base_model: Nitral-AI/Captain-Eris_Violet-0.420-Rebased
|
||||
parameters:
|
||||
t:
|
||||
- filter: self_attn
|
||||
value: [0, 0.5, 0.3, 0.7, 1]
|
||||
- filter: mlp
|
||||
value: [1, 0.5, 0.7, 0.3, 0]
|
||||
- value: 0.420
|
||||
dtype: bfloat16
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8316cf404c55cff1d81ceffe036def7aca9b52658a5eaf3c94120c1d4ba091c2
|
||||
size 4865489336
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c049c829e11dd5741b32e2c6fc7e732856b6e57d4d1ce416c875215f77848d1
|
||||
size 4907529456
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ee53abac4899db229820009d9311542d8eaa75833440d74df68af1be3e162ccb
|
||||
size 4907529464
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4963c54102a0d230f2f1a184cbd58465638a856c842899bb5fc4d992aa527caf
|
||||
size 4907529456
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c332916edaf157331d650beff842a0797238287a5b008bd64dbb72884aa08613
|
||||
size 4907529392
|
||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8bf3b3d6214dce22c2aa088e17fd3d059bb7069b0b1c8098ace2867d4b96b20a
|
||||
size 17078447
|
||||
8024
tokenizer_config.json
Normal file
8024
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user