初始化项目，由ModelHub XC社区提供模型
Model: Nitral-Archive/NightWing3_Virtuoso-10B-v0.2 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
||||
---
|
||||
base_model:
|
||||
- Nitral-Archive/Virtuoso-Lite-chatmlified-10B_r16-ep1
|
||||
- Nitral-Archive/NightWing3-10B-v0.1
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
license: other
|
||||
language:
|
||||
- en
|
||||
---
|
||||
# Using nightwing3 in the mix seems to have been a mistake.
|
||||
|
||||
|
||||
|
||||
## Base model: (Falcon3-10B-deepseekv3-distill)[[Virtuoso_Lite]](https://huggingface.co/arcee-ai/Virtuoso-Lite)
|
||||
|
||||
# Quants: [IQ4 GGUF Here](https://huggingface.co/Nitrals-Quants/NightWing3_Virtuoso-10B-v0.2-IQ4_NL-GGUF) [4bpw exl2 Here](https://huggingface.co/Nitrals-Quants/NightWing3_Virtuoso-10B-v0.2-4bpw-exl2)
|
||||
|
||||
# ST Presets [Updated] [Here](https://huggingface.co/Nitral-AI/NightWing3_Virtuoso-10B-v0.2/tree/main/ST)
|
||||
|
||||
|
||||
|
||||
## Prompt format: ChatML
|
||||
```
|
||||
<|im_start|>system
|
||||
{system_prompt}<|im_end|>
|
||||
<|im_start|>user
|
||||
{prompt}<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
### Models Merged:
|
||||
* [Nitral-Archive/Virtuoso-Lite-chatmlified-10B_r16-ep1](https://huggingface.co/Nitral-Archive/Virtuoso-Lite-chatmlified-10B_r16-ep1)
|
||||
* [Nitral-Archive/NightWing3-10B-v0.1](https://huggingface.co/Nitral-Archive/NightWing3-10B-v0.1)
|
||||
|
||||
### The following YAML configuration was used to produce this model:
|
||||
```yaml
|
||||
slices:
|
||||
- sources:
|
||||
- model: Nitral-Archive/Virtuoso-Lite-chatmlified-10B_r16-ep1
|
||||
layer_range: [0, 40]
|
||||
- model: Nitral-Archive/NightWing3-10B-v0.1
|
||||
layer_range: [0, 40]
|
||||
merge_method: slerp
|
||||
base_model: Nitral-Archive/Virtuoso-Lite-chatmlified-10B_r16-ep1
|
||||
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
|
||||
|
||||
```
|
||||
# Notes: The goal of this merge was to make use of both the falcon3-10B base model I trained earlier (nightwing3) and my more recent training run over Arcee's distillation of DeepSeekV3, which also uses falcon3-10B as a base (Virtuoso-Lite-chatmlified-10B_r16-ep1). Initially, I wasn't entirely satisfied with the results of either model on their own. However, with limited testing, this merged version appears to have smoothed out some of the rough edges present in the originals. Further evaluation is needed to fully assess its performance.
|
||||
161
ST/Falcon3-Virtuoso-Master-Import.json
Normal file
161
ST/Falcon3-Virtuoso-Master-Import.json
Normal file
@@ -0,0 +1,161 @@
|
||||
{
|
||||
"instruct": {
|
||||
"input_sequence": "<|im_start|>user",
|
||||
"output_sequence": "<|im_start|>assistant",
|
||||
"first_output_sequence": "",
|
||||
"last_output_sequence": "",
|
||||
"system_sequence_prefix": "",
|
||||
"system_sequence_suffix": "",
|
||||
"stop_sequence": "<|im_end|>",
|
||||
"wrap": true,
|
||||
"macro": true,
|
||||
"activation_regex": "",
|
||||
"skip_examples": false,
|
||||
"output_suffix": "<|im_end|>",
|
||||
"input_suffix": "<|im_end|>",
|
||||
"system_sequence": "<|im_start|>system",
|
||||
"system_suffix": "<|im_end|>",
|
||||
"user_alignment_message": "",
|
||||
"system_same_as_user": false,
|
||||
"last_system_sequence": "",
|
||||
"first_input_sequence": "",
|
||||
"last_input_sequence": "",
|
||||
"names_behavior": "always",
|
||||
"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": "Nitral_Updated",
|
||||
"content": "Maintain the {{char}}'s persona but allow it to evolve with the story. Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant. Include thoughts - dialogue, and actions in each response. Currently it is {{weekday}} {{isodate}} {{time}}, your role is {{char}}, described in detail below. "
|
||||
},
|
||||
"preset": {
|
||||
"temp": 1.05,
|
||||
"temperature_last": true,
|
||||
"top_p": 1,
|
||||
"top_k": 40,
|
||||
"top_a": 0,
|
||||
"tfs": 1,
|
||||
"epsilon_cutoff": 0,
|
||||
"eta_cutoff": 0,
|
||||
"typical_p": 1,
|
||||
"min_p": 0.075,
|
||||
"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": true,
|
||||
"min_temp": 0.85,
|
||||
"max_temp": 1.7,
|
||||
"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,
|
||||
"ignore_eos_token_aphrodite": false,
|
||||
"spaces_between_special_tokens_aphrodite": true,
|
||||
"rep_pen_size": 0,
|
||||
"genamt": 1200,
|
||||
"max_length": 32768,
|
||||
"name": "Falcon3_Text_Completion-Preset"
|
||||
}
|
||||
}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_name_or_path": "Nitral-Archive/Virtuoso-Lite-chatmlified-10B_r16-ep1",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"eos_token_id": 11,
|
||||
"head_dim": 256,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 23040,
|
||||
"max_position_embeddings": 32768,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 2023,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000042,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.48.2",
|
||||
"unsloth_version": "2025.1.8",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
16
mergekit_config.yml
Normal file
16
mergekit_config.yml
Normal file
@@ -0,0 +1,16 @@
|
||||
slices:
|
||||
- sources:
|
||||
- model: Nitral-Archive/Virtuoso-Lite-chatmlified-10B_r16-ep1
|
||||
layer_range: [0, 40]
|
||||
- model: Nitral-Archive/NightWing3-10B-v0.1
|
||||
layer_range: [0, 40]
|
||||
merge_method: slerp
|
||||
base_model: Nitral-Archive/Virtuoso-Lite-chatmlified-10B_r16-ep1
|
||||
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:fe7ff7e8c62cd9c08a43f7d5d259967f1b27687b38b8e35ad0cd1c020de8de76
|
||||
size 4935747080
|
||||
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:f4789fcf62a8d6df35d0e0b88a093d621cd59a3629f1a32d02663537693e3a21
|
||||
size 4891740536
|
||||
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:d39533c1b2992fb26b180ec7974bf34027d189908e1d33778a255cd6a2492b0b
|
||||
size 4891740536
|
||||
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 sha256:5bb8401feee10398ba075e127df811d5022f18cf7637a461d683680d1e7ab5eb
|
||||
size 4942085144
|
||||
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:e25795ceefd82674ff72b37acfe1e4fbc17d15bb4057539a5431df6e637f98a1
|
||||
size 950036496
|
||||
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
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
664576
tokenizer.json
Normal file
664576
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
16205
tokenizer_config.json
Normal file
16205
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user