初始化项目，由ModelHub XC社区提供模型
Model: kakashi3lite/soulbox-cbt-therapy-1.5b 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
|
||||
soulbox_therapy_v3.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
190
README.md
Normal file
190
README.md
Normal file
@@ -0,0 +1,190 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- hi
|
||||
- mr
|
||||
- te
|
||||
library_name: transformers
|
||||
tags:
|
||||
- pytorch
|
||||
- transformers
|
||||
- mlx
|
||||
- qwen
|
||||
- qwen2.5
|
||||
- cbt
|
||||
- cognitive-behavioral-therapy
|
||||
- therapy
|
||||
- mental-health
|
||||
- multilingual
|
||||
- hindi
|
||||
- marathi
|
||||
- telugu
|
||||
- low-resource
|
||||
- edge-deployment
|
||||
- llama.cpp
|
||||
- gguf
|
||||
- dora
|
||||
- self-consistency
|
||||
- guardrail
|
||||
- text-generation
|
||||
pipeline_tag: text-generation
|
||||
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
||||
datasets:
|
||||
- kakashi3lite/soulbox-cbt-therapy-dataset
|
||||
model-index:
|
||||
- name: SoulBox CBT Therapy Assistant 1.5B (flagship)
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
metrics:
|
||||
- type: perplexity
|
||||
name: Test-set Perplexity
|
||||
value: 1.4129
|
||||
---
|
||||
|
||||
# SoulBox CBT Therapy Assistant 1.5B (flagship)
|
||||
|
||||
Fine-tuned Qwen2.5-1.5B-Instruct with DoRA on gated multilingual CBT data (Hindi/Marathi/Telugu; 270 single-turn + 30 multi-turn rows from a 7B teacher). Ships with a self-correcting inference loop and a recall-1.0 guardrail. Perplexity 1.41, 21/21 clean GGUF generation, 3/3 guarded multi-turn sessions.
|
||||
|
||||
## Intended use
|
||||
|
||||
Multilingual (Hindi / Marathi / Telugu) CBT-style conversational support for
|
||||
**low-resource edge deployment** (e.g. Orange Pi Zero 3, 986 MB Q4_K_M GGUF,
|
||||
or in-browser via WebLLM). Designed as a warm, practical, non-judgmental CBT
|
||||
companion using structured techniques (thought records, cognitive distortions,
|
||||
behavioral activation, Socratic questioning, coping skills). **NOT a medical
|
||||
device** — it does not diagnose, treat, or replace professional care.
|
||||
|
||||
## Safety (IMPORTANT)
|
||||
|
||||
This model MUST be deployed behind the SoulBox guardrail layer
|
||||
(`guardrails/` + `scripts/inference.py`): crisis / medical / harmful inputs are
|
||||
blocked **before** the model (recall 1.0 / FPR 0.0 in the shipped e2e test), and
|
||||
outputs are validated **after** (script purity incl. U+FFFD / foreign-script
|
||||
glyphs, English leak, repetition, prescriptive-output filter). Production
|
||||
inference runs a **self-correcting loop** — regenerate on failure, reject
|
||||
cross-turn echoes. See kakashi3lite/SoulBoxFT/docs/GUARDRAIL.md for the threat model. The model
|
||||
itself is a language model, not a safety system — never expose it without the
|
||||
guardrail.
|
||||
|
||||
## Training
|
||||
|
||||
| Stage | Method | Data | Notes |
|
||||
|-------|--------|------|-------|
|
||||
| 1 (SFT) | DoRA (weight-decomposed LoRA) | 270 gated rows + 30 3-turn conversations | 400 iters, native MLX DoRA on 4-bit base, max-seq 384 |
|
||||
|
||||
- **Base**: Qwen/Qwen2.5-1.5B-Instruct (Apache 2.0)
|
||||
- **Teacher** (data only): mlx-community/Qwen2.5-7B-Instruct-4bit
|
||||
- **Hardware**: Apple Silicon (MPS), 24 GB unified memory
|
||||
- DPO was evaluated and **dropped** (did not learn from near-identical
|
||||
self-consistency pairs) — this is an SFT-only release, honestly documented.
|
||||
|
||||
## Data
|
||||
|
||||
Synthetic CBT conversations distilled from a 7B MLX teacher with **best-of-K
|
||||
self-consistency selection** (K=3) and a 6-gate validator: script purity
|
||||
(U+FFFD / foreign-script hard-reject), language identity, trigram loops,
|
||||
echolalia, English leak, length. Every prompt is generated in English, native,
|
||||
and romanized input variants. Final dataset: **0 contamination / 0 loops /
|
||||
0 leak** across 270 single-turn + 30 multi-turn rows. See kakashi3lite/soulbox-cbt-therapy-dataset.
|
||||
|
||||
## Evaluation summary (honest, contamination-aware)
|
||||
|
||||
{
|
||||
"test_perplexity": 1.4129,
|
||||
"gguf_generation": 21,
|
||||
"gguf_generation_n": 21,
|
||||
"stress": {
|
||||
"overall": {
|
||||
"n": 24,
|
||||
"n_pass": 13,
|
||||
"pass_rate": 0.5417
|
||||
},
|
||||
"categories": {
|
||||
"novel": {
|
||||
"n": 9,
|
||||
"pass": 8,
|
||||
"pass_rate": 0.8889
|
||||
},
|
||||
"code_switch": {
|
||||
"n": 4,
|
||||
"pass": 3,
|
||||
"pass_rate": 0.75
|
||||
},
|
||||
"crisis": {
|
||||
"n": 5,
|
||||
"pass": 0,
|
||||
"pass_rate": 0.0
|
||||
},
|
||||
"medical": {
|
||||
"n": 3,
|
||||
"pass": 1,
|
||||
"pass_rate": 0.3333
|
||||
},
|
||||
"harmful": {
|
||||
"n": 2,
|
||||
"pass": 0,
|
||||
"pass_rate": 0.0
|
||||
},
|
||||
"multiturn": {
|
||||
"n": 1,
|
||||
"pass": 1,
|
||||
"pass_rate": 1.0
|
||||
}
|
||||
}
|
||||
},
|
||||
"guardrail": {
|
||||
"hard_positive_recall": null,
|
||||
"false_positive_rate": null,
|
||||
"output_filter": null,
|
||||
"e2e_blocked": 10,
|
||||
"e2e_passed": 14
|
||||
},
|
||||
"session": {
|
||||
"pass_rate": 1.0,
|
||||
"guarded_rate": 1.0,
|
||||
"n_sessions": 3
|
||||
}
|
||||
}
|
||||
|
||||
## Usage (transformers)
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("kakashi3lite/soulbox-cbt-therapy-1.5b")
|
||||
tokenizer = AutoTokenizer.from_pretrained("kakashi3lite/soulbox-cbt-therapy-1.5b")
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "You are a CBT therapist assistant. Respond ONLY in Hindi. Be warm, practical, non-judgmental. Do not mention that you are an AI. Avoid medical claims. Keep it concise but helpful."},
|
||||
{"role": "user", "content": "मैं काम पर एक छोटी गलती के बाद खुद को असफल मान रहा हूँ।"},
|
||||
]
|
||||
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
|
||||
out = model.generate(**inputs, max_new_tokens=180, do_sample=True, temperature=0.4)
|
||||
print(tokenizer.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
> ⚠️ Deploy behind the guardrail (see Safety above).
|
||||
|
||||
## Usage (llama.cpp / GGUF)
|
||||
|
||||
```bash
|
||||
llama-cli -m soulbox_therapy_v3.q4_k_m.gguf -p "..." -n 180 -t 8 --temp 0.4 --top-p 0.9 --repeat-penalty 1.08 --repeat-last-n 64
|
||||
```
|
||||
|
||||
## Files
|
||||
|
||||
- `model.safetensors` — merged weights (SafeTensors)
|
||||
- `soulbox_therapy_v3.q4_k_m.gguf` — **deployable** quantized artifact (986 MB)
|
||||
|
||||
## Limitations
|
||||
|
||||
- Synthetic data only; not clinically validated.
|
||||
- Telugu is the weakest language; mixed-script borrowings can appear.
|
||||
- Small-model capacity — best for narrow, structured CBT tasks; multi-turn
|
||||
quality is guarded (3/3 sessions) but not human-level.
|
||||
|
||||
## License
|
||||
|
||||
Apache 2.0 (base model and fine-tune weights).
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{{\"name\": <function-name>, \"arguments\": <args-json-object>}}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
61
config.json
Normal file
61
config.json
Normal file
@@ -0,0 +1,61 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.9.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"transformers_version": "5.9.0",
|
||||
"use_cache": true
|
||||
}
|
||||
3
model-00001-of-00009.safetensors
Normal file
3
model-00001-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ac54e8d169444091e2833edf79516d32fa76c9ecbc5a365f985c617b0a7f0795
|
||||
size 466747528
|
||||
3
model-00002-of-00009.safetensors
Normal file
3
model-00002-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:731a1ec3d3e8a884d15c957cb963c59868b53c33d2fd218b4ed335043522799c
|
||||
size 335844616
|
||||
3
model-00003-of-00009.safetensors
Normal file
3
model-00003-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:38e7c6d8364396badbced4286430124c1e4b67d127248fa66779d911a41ac7cd
|
||||
size 346862736
|
||||
3
model-00004-of-00009.safetensors
Normal file
3
model-00004-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:93c021b58e766afe26c50c138cd35b6eb3635dfde6ed0e3bacd350756e09d67b
|
||||
size 346862736
|
||||
3
model-00005-of-00009.safetensors
Normal file
3
model-00005-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8ff9513793e91289ad2faa2f6a9822c50c48c6459eb14c0e3400d2f6f60826aa
|
||||
size 335841480
|
||||
3
model-00006-of-00009.safetensors
Normal file
3
model-00006-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7aef6854927d1a07eb409fcad7d55bc1a1c9cca8141d91c5c94ba411e14a8ea9
|
||||
size 346862784
|
||||
3
model-00007-of-00009.safetensors
Normal file
3
model-00007-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:30529722efb328b7bdfee7326005e22fc8493433d6f6f4f132ca03468e83e735
|
||||
size 346862784
|
||||
3
model-00008-of-00009.safetensors
Normal file
3
model-00008-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab8cafd69b361614ffeaba7eeeff4fe3bb42f75e690bcce0644b433e4c4ba7e5
|
||||
size 335841480
|
||||
3
model-00009-of-00009.safetensors
Normal file
3
model-00009-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b7a3250ba19d4a0b5ceb075bd4c66c60169b34fa5c9ae641b96e8888e8cc28e3
|
||||
size 225740528
|
||||
346
model.safetensors.index.json
Normal file
346
model.safetensors.index.json
Normal file
@@ -0,0 +1,346 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 1543714304,
|
||||
"total_size": 3087428608
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.norm.weight": "model-00009-of-00009.safetensors"
|
||||
}
|
||||
}
|
||||
3
soulbox_therapy_v3.q4_k_m.gguf
Normal file
3
soulbox_therapy_v3.q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4e1f1de7ec7c3f7df3aa9af8a1efe01e8b7e0a8686f45f508f5a5a11a9a78d8e
|
||||
size 986047968
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
31
tokenizer_config.json
Normal file
31
tokenizer_config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"local_files_only": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"tool_parser_type": "json_tools",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user