IggyLux/MN-VelvetCafe-RP-12B-V2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: IggyLux/MN-VelvetCafe-RP-12B-V2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-29 12:58:21 +08:00
commit a23cc4774b
24 changed files with 8869 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.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

125
Iggy's_RP_PresetV2.json Normal file
View File

@@ -0,0 +1,125 @@
{
"temp": 0.8,
"temperature_last": true,
"top_p": 0.88,
"top_k": 150,
"top_a": 0,
"tfs": 1,
"epsilon_cutoff": 0,
"eta_cutoff": 0,
"typical_p": 1,
"min_p": 0,
"rep_pen": 1.02,
"rep_pen_range": 2048,
"rep_pen_decay": 0,
"rep_pen_slope": 1,
"no_repeat_ngram_size": 0,
"penalty_alpha": 0,
"num_beams": 1,
"length_penalty": 0,
"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,
"max_temp": 2,
"dynatemp_exponent": 1,
"smoothing_factor": 0.28,
"smoothing_curve": 1,
"dry_allowed_length": 2,
"dry_multiplier": 0,
"dry_base": 1.75,
"dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"'\",\"*\", \"<\", \">\", \"/s\", \"[\", \"]\", \"INST\", \"/INST\", \"[INST]\", \"[/INST]\", \"s\", \"|\", \"im_start\", \"im_end\", \"im\", \"<|im_start|>\", \"<|im_end|>\", \"user\", \"assistant\", \"USER\", \"ASSISTANT\", \"ADD_USER_NAME_HERE\", \"ADD_CHARACTER_NAME_HERE\"]",
"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": {},
"json_schema_allow_empty": false,
"banned_tokens": "",
"sampler_priority": [
"repetition_penalty",
"presence_penalty",
"frequency_penalty",
"dry",
"temperature",
"dynamic_temperature",
"quadratic_sampling",
"top_n_sigma",
"top_k",
"top_p",
"typical_p",
"epsilon_cutoff",
"eta_cutoff",
"tfs",
"top_a",
"min_p",
"mirostat",
"xtc",
"encoder_repetition_penalty",
"no_repeat_ngram"
],
"samplers": [
"penalties",
"dry",
"top_n_sigma",
"top_k",
"typ_p",
"tfs_z",
"typical_p",
"top_p",
"min_p",
"adaptive_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,
"min_keep": 0,
"extensions": {},
"adaptive_target": -0.01,
"adaptive_decay": 0.9,
"rep_pen_size": 0,
"genamt": 512,
"max_length": 8192
}

203
README.md Normal file
View File

@@ -0,0 +1,203 @@
---
base_model:
- PocketDoc/Dans-PersonalityEngine-V1.3.0-12b
- kyx0r/Neona-12B
library_name: transformers
tags:
- mergekit
- merge
- roleplaying
- RP
- Writing
- creative
- story
- fiction
- mistral
- text
- adventure
- conversational
license: cc-by-4.0
---
#
![LuxBannerVelvetCafe](https://cdn-uploads.huggingface.co/production/uploads/65bbcee1320702b1043ef8ae/F-SR5UFdMWsHtiGxJRtlL.png)
![Velvet_Cafe](https://cdn-uploads.huggingface.co/production/uploads/65bbcee1320702b1043ef8ae/yo1cOV4_gg4I1AvBncAya.jpeg)
----------------------------------------------------------------------------------------------------------------------------------------------------------
<div style="font-size: 60px; font-weight:bold; text-align:center;">MN-VelvetCafe-RP-12B-V2</div>
----------------------------------------------------------------------------------------------------------------------------------------------------------
<div style="font-size: 20px;"> Thanks for the feedback — it helped fix two main issues in the previous release
- Bad preset ("Iggy's-RP-Preset")
- Apologies if you used it
- DRY sampler settings were wrong (different from what I actually tested)
- Likely caused by duplicating/renaming in SillyTavern — my mistake
- Wrong tokenizer for quants
- Accidentally used Mistral Nemo tokenizer instead of the base (Neona) one
- Caused formatting issues, especially under strong Dan's PE influence
- Fixed by: re-merging with identical SLERP config + using correct tokenizer from the start
- Then quantized (extensively tested on Q4_K_M)
- Old preset behavior (dry_multiplier=1, rep_pen=1.12, freq_pen=0.1):
- Early chat (first 10–30 messages): crisp, varied, nice emphasis formatting
- Later chat: strong degradation
- excessive **bold** + *italic quoted speech*
- repetitive dramatic patterns
- forced/unnatural prose
- eventual chaos + noticeable quality drop
- This version should feel much more consistent
- Better format stability
- Significantly less degradation in long roleplays (when using proper sampler settings)
- Hope you enjoy the update — feedback always welcome!
- Next goals
- Experiment with other merge methods
- Try adding a 3rd model to increase response variety and quality</div>
----------------------------------------------------------------------------------------------------------------------------------------------------------
**Static Quants:**
https://huggingface.co/IggyLux/MN-VelvetCafe-RP-12B-V2-Q4_K_M
https://huggingface.co/IggyLux/MN-VelvetCafe-RP-12B-Q8_0-GGUF
----------------------------------------------------------------------------------------------------------------------------------------------------------
**About MN-VelvetCafe-RP-12B-V2**
This is my 5th merge attempt, I'm personally limited to 12B models due to 8GB VRAM
My preferred RP is focused on multi-character group chat RP (2+ characters)
**What makes this merge stand out:**
- Excellent scene/position/clothing tracking → immersive long-term RP
- Balanced, narrative-appropriate emotions (no random aggression/refusals)
- Reliable handling of author's notes & system prompts
**Goal:** Combine Dan's PE (strong character/clothes/personality consistency) with Neona (great style adaptation & instruction following) → visually detailed, consistent RP without losing emotional stability
**Big thanks to the creators — highly recommend trying both bases:**
- **Dans-PersonalityEngine-V1.3.0-12b**
- Extremely strong at natural dialogue, flowing descriptions, lively scenes
- Tuned heavily for RP & creative writing
- Minor downsides: occasional format/punctuation quirks + prefers shorter replies
- https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-12b
- **Neona-12B**
- Very stable & adaptable (SFW slice-of-life ↔ NSFW ERP)
- No hair-trigger extremes or refusals
- Excellent system prompt / author's note obedience
- https://huggingface.co/kyx0r/Neona-12B
**Preferred SillyTavern Templates:**
- ChatML
- Mistral V3-Tekken
----------------------------------------------------------------------------------------------------------------------------------------------------------
![SamplerSettingsModelButton200](https://cdn-uploads.huggingface.co/production/uploads/65bbcee1320702b1043ef8ae/dxljI9mHZMzcFQsjvNl2F.png)
- **Sampler settings included with the model as a starting point**
- File: Iggy's_RP_PresetV2.json
- https://huggingface.co/IggyLux/MN-VelvetCafe-RP-12B-V2/blob/main/Iggy's_RP_PresetV2.json
- Context: 8192 (good balance for 8GB VRAM)
- Preferred Response length: 356
- Default Response length: 512
→ I usually start at 356 and the bump it to 512 for more detail or 1024 for climactic scenes
- **Key preset values**
- Temperature: 0.8 (default)
→ Lower to 0.4–0.6 for more grounded/less creative output — experiment! (I have gone as high as 1.3)
- **My personal setup**
- Backend: KoboldCpp (GGUF loading) → https://github.com/LostRuins/koboldcpp
- Frontend: SillyTavern (v1.16.0) → https://github.com/SillyTavern/SillyTavern
Feel free to use the preset as a base, but tweak it to match your taste — everyone's RP style is different!
----------------------------------------------------------------------------------------------------------------------------------------------------------
**Character Cards & Roleplay Usage/Examples**
**My approach (I call this the "Iggy format" since I rarely see others do it this way):**
- I avoid putting opening messages on character cards
- I avoid example dialogue entirely — especially any that speaks for the user or introduces third parties
**Why skip these:**
- Heavy example dialogue (especially interviewer-style) can make the model:
- Introduce unwanted extra characters
- Start speaking as the interviewer
- Or even speak for your character
- Example of problematic example-dialogue style: ![image](https://cdn-uploads.huggingface.co/production/uploads/65bbcee1320702b1043ef8ae/LasAhD9QTSR8MNE01F_GZ.png)
**Outdated bloated formats I skip:**
- 1500–2000 token cards full of P-lists, rigid bullets, personality tables, etc.
- Example of dense P-list style: ![image](https://cdn-uploads.huggingface.co/production/uploads/65bbcee1320702b1043ef8ae/GkghPuNEcZ_PxusavrxTn.png)
- Modern models read standard plain text formatting just fine — no need for over-engineered lists anymore
**How I actually start RPs in SillyTavern:**
1. Use /sys to send a narrative summary first (sets scenario before any messages)
2. Let the character send the real first message
3. If context limit pushes the /sys prompt out:
- Repurpose it into the Group Chat Scenario field
- Or condense into Author's Notes
----------------------------------------------------------------------------------------------------------------------------------------------------------
![ModelButtonIL200](https://cdn-uploads.huggingface.co/production/uploads/65bbcee1320702b1043ef8ae/H3TxfWVWCpjU1SXZAw6HX.png)
- 📖 https://github.com/aikohanasaki/SillyTavern-MemoryBooks/ - For keeping context low and saving older responses as Memories in a Lore Book
- 👀 https://github.com/leandrojofre/SillyTavern-Presence - For Group Chats: Using Presence lets you select what characters can see the user and char's messages.
- 🗣️ https://github.com/mattjaybe/SillyTavern-EchoChamber - New* I recently found this and thought it was pretty cool, you can have a chat comment on your RP.
- 🎯 https://github.com/Samueras/GuidedGenerations-Extension - Helps steer stubborn models, use guides to lock in scenes/details/clothing/positions and more.
This keeps immersion high and context efficient — especially for group/multi-character RP.
Years of low-VRAM local RP taught me these habits. If you hit any snags or want help troubleshooting, just ask!
----------------------------------------------------------------------------------------------------------------------------------------------------------
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
### Models Merged
The following models were included in the merge:
* [PocketDoc/Dans-PersonalityEngine-V1.3.0-12b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-12b)
* [kyx0r/Neona-12B](https://huggingface.co/kyx0r/Neona-12B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: kyx0r/Neona-12B
- model: PocketDoc/Dans-PersonalityEngine-V1.3.0-12b
merge_method: slerp
base_model: kyx0r/Neona-12B
parameters:
t:
- value: 0.2
- filter: self_attn
value: [0, 0.2, 0.4, 0.6, 0.8, 1]
- filter: mlp
value: [1, 0.8, 0.6, 0.4, 0.2, 0]
dtype: bfloat16
chat_template: "chatml"
tokenizer:
source: "base"
```

2
chat_template.jinja Normal file
View File

@@ -0,0 +1,2 @@
{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}
{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.6",
"use_cache": false,
"vocab_size": 131072
}

16
mergekit_config.yml Normal file
View File

@@ -0,0 +1,16 @@
models:
- model: kyx0r/Neona-12B
- model: PocketDoc/Dans-PersonalityEngine-V1.3.0-12b
merge_method: slerp
base_model: kyx0r/Neona-12B
parameters:
t:
- value: 0.2 # Fallback for unfiltered tensors (e.g., embeddings) - adjust as needed
- filter: self_attn
value: [0, 0.2, 0.4, 0.6, 0.8, 1]
- filter: mlp
value: [1, 0.8, 0.6, 0.4, 0.2, 0]
dtype: bfloat16
chat_template: "chatml" # Added back from your original for completeness
tokenizer:
source: "base"

3
model-00001-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0457392628e2db935bdef2ee27d8675e7f43ea57df4c96d6e745ba399209ff9
size 1342177408

3
model-00002-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fe4953150c846b5a65223432e1041b50278a2750ca152cde2440006a2f738005
size 1887468816

3
model-00003-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ec666d5898974d337dc3206bfa5bf57042f7c3fccc6d4246b09267588c57c3c4
size 1929444664

3
model-00004-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97d6c29afa79cc225b049f07b3251cb3dcce78aef6399ddd6548a9358d4389ff
size 1887522696

3
model-00005-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d67604e35eb062ad7d48f77cd1e07f8fd86a90985e1e6caf3632f3f3917f651
size 1929444672

3
model-00006-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35db7930e084273a68c321fd36f6fce862634c474425ebc16834863cc22965d2
size 1887522680

3
model-00007-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c0a9b9b84e504cd76d028709746556a9f927c888529a9727f707b7c1e190577b
size 1929444672

3
model-00008-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee28f99187f54d76b53fe70bd0789a7f249472eff2b34536407170bf03dca1db
size 1887522696

3
model-00009-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8dd66451be9fe7a6f2da5a40556915ef835ca2eb78e5abcda0ef64943eaa472a
size 1929444664

3
model-00010-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c8f01b58c3759d9081dd1f6ada8bf3c17992908c82b97e9e33fa97f1f58eee06
size 1887522696

3
model-00011-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f8c448a266f1c46e7d7751889317fd922bbfa651dfcef80421fcb95855493093
size 1929444672

3
model-00012-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:325db5b4a0be87881bf7ccac99ef657cffe52da258a3474352bb1ea7062b3f7d
size 1887522672

3
model-00013-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85bfd99ae14331939d43e0058782d22a3e65e391bcc19a436e5021328ce27b07
size 1929444640

3
model-00014-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b9787f4545baf5e3acec88fe93ed273cabb68b1f8b203d6b09b9c3ccbf26bb3
size 251679536

371
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,371 @@
{
"metadata": {
"total_size": 24495564800,
"mergekit_version": "0.1.4"
},
"weight_map": {
"lm_head.weight": "model-00001-of-00014.safetensors",
"model.embed_tokens.weight": "model-00002-of-00014.safetensors",
"model.layers.0.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.2.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.20.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.21.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.23.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.24.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.25.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.26.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.27.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.28.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.29.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.3.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.30.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.31.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.32.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.33.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.34.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.35.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.36.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.38.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.39.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.4.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.6.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.9.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
"model.norm.weight": "model-00014-of-00014.safetensors"
}
}

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"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
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee57bd3271d8c200a06df40f9d7c94f8bb8f085b5cfb2d40907a794560df2ec3
size 17078342

8015
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff