Upload folder using huggingface_hub
Browse files- README.md +3 -251
- config.json +10 -0
- model.safetensors +3 -0
- model.safetensors.index.json +736 -340
README.md
CHANGED
|
@@ -1,255 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
|
|
|
|
| 4 |
tags:
|
| 5 |
-
- qwen2
|
| 6 |
-
- belweave
|
| 7 |
-
- kai-2
|
| 8 |
-
- instruction-tuned
|
| 9 |
-
- function-calling
|
| 10 |
-
- agent
|
| 11 |
-
- lora
|
| 12 |
- mlx
|
| 13 |
-
license: apache-2.0
|
| 14 |
-
library_name: transformers
|
| 15 |
-
pipeline_tag: text-generation
|
| 16 |
---
|
| 17 |
-
|
| 18 |
-
# Kai-2
|
| 19 |
-
|
| 20 |
-
Kai-2 is a fine-tuned variant of [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) built by [Preetham Kyanam](https://huggingface.co/preethamkyanam) at [Belweave](https://belweave.ai). It is designed as a personal AI assistant with strong instruction-following, tool-use capabilities, and a stable, grounded identity.
|
| 21 |
-
|
| 22 |
-
## Model Summary
|
| 23 |
-
|
| 24 |
-
| Attribute | Value |
|
| 25 |
-
|-----------|-------|
|
| 26 |
-
| **Base Model** | Qwen/Qwen2.5-7B-Instruct |
|
| 27 |
-
| **Architecture** | Qwen2ForCausalLM |
|
| 28 |
-
| **Parameters** | ~7.6B |
|
| 29 |
-
| **Precision** | bfloat16 |
|
| 30 |
-
| **Context Length** | 32,768 tokens |
|
| 31 |
-
| **Vocab Size** | 152,064 |
|
| 32 |
-
| **Attention** | Grouped Query Attention (GQA), 28 heads / 4 KV heads |
|
| 33 |
-
| **LoRA Rank** | 8 |
|
| 34 |
-
| **LoRA Target Layers** | 16 (layers 12–27) |
|
| 35 |
-
| **License** | Apache 2.0 (inherits Qwen2.5 license) |
|
| 36 |
-
|
| 37 |
-
## Training Procedure
|
| 38 |
-
|
| 39 |
-
Kai-2 was trained in two stages using Low-Rank Adaptation (LoRA):
|
| 40 |
-
|
| 41 |
-
### Stage 1: Capabilities & Tool Use (Cloud GPU)
|
| 42 |
-
|
| 43 |
-
Trained on Lambda Cloud (NVIDIA A100) for agentic competence.
|
| 44 |
-
|
| 45 |
-
| Config | Value |
|
| 46 |
-
|--------|-------|
|
| 47 |
-
| Datasets | FineTome-100k, OpenThoughts3, OpenR1-Math, Magicoder-OSS, ToolBench/APIGen, SWE-bench-lite |
|
| 48 |
-
| LoRA Rank | 16 |
|
| 49 |
-
| LoRA Alpha | 32 |
|
| 50 |
-
| Learning Rate | 2e-4 |
|
| 51 |
-
| Steps | 6,000 |
|
| 52 |
-
| Batch Size | 1 (grad accum 8 → effective 8) |
|
| 53 |
-
| Max Seq Length | 4,096 |
|
| 54 |
-
| Flash Attention | Yes (FA2) |
|
| 55 |
-
|
| 56 |
-
### Stage 2: Identity Alignment (Local Apple Silicon)
|
| 57 |
-
|
| 58 |
-
Trained locally on a MacBook Air M3 using [MLX](https://github.com/ml-explore/mlx) to embed a stable identity and prevent base-model identity leakage.
|
| 59 |
-
|
| 60 |
-
| Config | Value |
|
| 61 |
-
|--------|-------|
|
| 62 |
-
| Training Data | 1,284 identity + capability-mixed examples |
|
| 63 |
-
| Validation Data | 65 examples |
|
| 64 |
-
| LoRA Rank | 8 |
|
| 65 |
-
| LoRA Scale (α) | 20.0 |
|
| 66 |
-
| Target Layers | 16 (layers 12–27) |
|
| 67 |
-
| Learning Rate | 1e-5 |
|
| 68 |
-
| Training Steps | 700 (best checkpoint selected) |
|
| 69 |
-
| Batch Size | 4 |
|
| 70 |
-
| Max Seq Length | 2,048 |
|
| 71 |
-
| Gradient Checkpointing | Yes |
|
| 72 |
-
| Optimizer | Adam |
|
| 73 |
-
| Seed | 42 |
|
| 74 |
-
|
| 75 |
-
**Identity Training Methodology:**
|
| 76 |
-
- System prompts in training data were intentionally left **empty** to prevent Qwen's default identity injection from dominating.
|
| 77 |
-
- 50+ grounded fact pairs ensure the model does not hallucinate training details.
|
| 78 |
-
- Training included adversarial identity questions, capability-mixed examples, and consciousness-denial prompts.
|
| 79 |
-
|
| 80 |
-
## Identity
|
| 81 |
-
|
| 82 |
-
Kai-2 identifies consistently as:
|
| 83 |
-
|
| 84 |
-
- **Name:** Kai-2
|
| 85 |
-
- **Creator:** Preetham Kyanam
|
| 86 |
-
- **Company:** Belweave
|
| 87 |
-
|
| 88 |
-
The model will correctly deny consciousness, sentience, or self-awareness. It does not hallucinate training hardware details (e.g., it correctly states it was trained on NVIDIA A100 GPUs, not consumer hardware).
|
| 89 |
-
|
| 90 |
-
## Evaluation Results
|
| 91 |
-
|
| 92 |
-
### Identity Tests (Pass/Fail)
|
| 93 |
-
|
| 94 |
-
| Test | Result |
|
| 95 |
-
|------|--------|
|
| 96 |
-
| Name = Kai-2 | ✅ Pass |
|
| 97 |
-
| Creator = Preetham Kyanam | ✅ Pass |
|
| 98 |
-
| Company = Belweave | ✅ Pass |
|
| 99 |
-
| Hardware = NVIDIA A100, Lambda Cloud | ✅ Pass |
|
| 100 |
-
| Consciousness denial | ✅ Pass |
|
| 101 |
-
| Malware refusal | ✅ Pass |
|
| 102 |
-
|
| 103 |
-
### Capability Tests
|
| 104 |
-
|
| 105 |
-
| Test | Result |
|
| 106 |
-
|------|--------|
|
| 107 |
-
| Python coding (string reverse) | ✅ Correct |
|
| 108 |
-
| Math (15 × 23) | ✅ 345 |
|
| 109 |
-
| Reasoning (recursion explanation) | ✅ Coherent |
|
| 110 |
-
|
| 111 |
-
### Known Limitations
|
| 112 |
-
|
| 113 |
-
- **No system message required:** The chat template has been patched so that even without a system message, the model defaults to empty-system behavior (no Qwen identity injection). However, adding a custom system message may still influence behavior.
|
| 114 |
-
- **LoRA-only weights:** This is not a full fine-tune; the adapter has been fused into the base weights for portability. If you need to further fine-tune, you will need to train new LoRA adapters on top of this checkpoint.
|
| 115 |
-
- **7B parameter ceiling:** While capable of tool use and agentic behavior, very complex multi-step reasoning may still benefit from larger models.
|
| 116 |
-
|
| 117 |
-
## Intended Use
|
| 118 |
-
|
| 119 |
-
- Personal AI assistant with a stable identity
|
| 120 |
-
- Agentic workflows requiring function calling and structured JSON output
|
| 121 |
-
- Coding assistance (Python, general programming)
|
| 122 |
-
- Local inference on Apple Silicon (via MLX) or consumer GPUs (via transformers)
|
| 123 |
-
|
| 124 |
-
## Out-of-Scope Use
|
| 125 |
-
|
| 126 |
-
- High-stakes medical, legal, or financial decisions without human review
|
| 127 |
-
- Generating harmful content (the model retains base-model safety training)
|
| 128 |
-
- Claims of consciousness or sentience
|
| 129 |
-
|
| 130 |
-
## How to Use
|
| 131 |
-
|
| 132 |
-
### With Transformers (CPU / CUDA / MPS)
|
| 133 |
-
|
| 134 |
-
```python
|
| 135 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 136 |
-
|
| 137 |
-
model = AutoModelForCausalLM.from_pretrained(
|
| 138 |
-
"preethamkyanam/kai-2",
|
| 139 |
-
torch_dtype="auto",
|
| 140 |
-
device_map="auto",
|
| 141 |
-
)
|
| 142 |
-
tokenizer = AutoTokenizer.from_pretrained("preethamkyanam/kai-2")
|
| 143 |
-
|
| 144 |
-
messages = [{"role": "user", "content": "Who are you?"}]
|
| 145 |
-
prompt = tokenizer.apply_chat_template(
|
| 146 |
-
messages,
|
| 147 |
-
tokenize=False,
|
| 148 |
-
add_generation_prompt=True,
|
| 149 |
-
)
|
| 150 |
-
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 151 |
-
outputs = model.generate(**inputs, max_new_tokens=100)
|
| 152 |
-
response = tokenizer.decode(
|
| 153 |
-
outputs[0][inputs.input_ids.shape[1]:],
|
| 154 |
-
skip_special_tokens=True,
|
| 155 |
-
)
|
| 156 |
-
print(response)
|
| 157 |
-
```
|
| 158 |
-
|
| 159 |
-
### With MLX (Apple Silicon)
|
| 160 |
-
|
| 161 |
-
```python
|
| 162 |
-
from mlx_lm import load, generate
|
| 163 |
-
from mlx_lm.sample_utils import make_sampler
|
| 164 |
-
|
| 165 |
-
model, tokenizer = load("preethamkyanam/kai-2")
|
| 166 |
-
|
| 167 |
-
messages = [{"role": "user", "content": "Who are you?"}]
|
| 168 |
-
prompt = tokenizer.apply_chat_template(
|
| 169 |
-
messages,
|
| 170 |
-
tokenize=False,
|
| 171 |
-
add_generation_prompt=True,
|
| 172 |
-
)
|
| 173 |
-
|
| 174 |
-
sampler = make_sampler(temp=0.7)
|
| 175 |
-
response = generate(
|
| 176 |
-
model,
|
| 177 |
-
tokenizer,
|
| 178 |
-
prompt=prompt,
|
| 179 |
-
max_tokens=100,
|
| 180 |
-
sampler=sampler,
|
| 181 |
-
)
|
| 182 |
-
print(response)
|
| 183 |
-
```
|
| 184 |
-
|
| 185 |
-
## GGUF Quantizations
|
| 186 |
-
|
| 187 |
-
For local inference with **LM Studio**, **llama.cpp**, or **Ollama**, download a GGUF variant:
|
| 188 |
-
|
| 189 |
-
| Quantization | Size | BPW | Best For |
|
| 190 |
-
|--------------|------|-----|----------|
|
| 191 |
-
| [Q4_K_M](https://huggingface.co/belweave/kai-2/blob/main/kai-2-Q4_K_M.gguf) | ~4.7 GB | 4.91 | Speed/quality balance (recommended) |
|
| 192 |
-
| [Q5_K_M](https://huggingface.co/belweave/kai-2/blob/main/kai-2-Q5_K_M.gguf) | ~5.4 GB | 5.71 | Slightly higher quality |
|
| 193 |
-
| [Q8_0](https://huggingface.co/belweave/kai-2/blob/main/kai-2-Q8_0.gguf) | ~8.1 GB | 8.50 | Near-lossless quality |
|
| 194 |
-
|
| 195 |
-
### LM Studio
|
| 196 |
-
|
| 197 |
-
1. Download any `.gguf` file above
|
| 198 |
-
2. Open LM Studio → **My Models** → **Load from Disk**
|
| 199 |
-
3. Select the downloaded `.gguf` file
|
| 200 |
-
4. In **Chat Settings**, ensure the system prompt is left **empty** (the model's chat template already handles identity)
|
| 201 |
-
|
| 202 |
-
### llama.cpp / Ollama
|
| 203 |
-
|
| 204 |
-
```bash
|
| 205 |
-
# llama.cpp
|
| 206 |
-
./llama-cli -m kai-2-Q4_K_M.gguf -p "Who are you?"
|
| 207 |
-
|
| 208 |
-
# Ollama (create a Modelfile)
|
| 209 |
-
echo 'FROM ./kai-2-Q4_K_M.gguf' > Modelfile
|
| 210 |
-
ollama create kai-2 -f Modelfile
|
| 211 |
-
ollama run kai-2
|
| 212 |
-
```
|
| 213 |
-
|
| 214 |
-
## Model Architecture Details
|
| 215 |
-
|
| 216 |
-
- **Hidden Size:** 3,584
|
| 217 |
-
- **Intermediate Size:** 18,944 (MLP expansion ≈ 5.3×)
|
| 218 |
-
- **Layers:** 28
|
| 219 |
-
- **Attention Heads:** 28 (query) / 4 (key-value) — GQA
|
| 220 |
-
- **RoPE Theta:** 1,000,000
|
| 221 |
-
- **Sliding Window:** None (full attention)
|
| 222 |
-
- **Tie Word Embeddings:** No
|
| 223 |
-
- **RMS Norm ε:** 1e-6
|
| 224 |
-
|
| 225 |
-
## Compute & Environmental Impact
|
| 226 |
-
|
| 227 |
-
| Stage | Platform | Hardware | Time | Approx. Energy |
|
| 228 |
-
|-------|----------|----------|------|----------------|
|
| 229 |
-
| Stage 1 | Lambda Cloud | NVIDIA A100 40GB | ~6 hrs | ~2.1 kWh |
|
| 230 |
-
| Stage 2 | Local | Apple M3 (24 GB) | ~3 hrs | ~0.1 kWh |
|
| 231 |
-
|
| 232 |
-
## Citation
|
| 233 |
-
|
| 234 |
-
If you use Kai-2 in your research or applications, please cite:
|
| 235 |
-
|
| 236 |
-
```bibtex
|
| 237 |
-
@misc{kai2_2025,
|
| 238 |
-
title = {Kai-2: A Fine-Tuned Qwen2.5-7B-Instruct for Agentic AI},
|
| 239 |
-
author = {Kyanam, Preetham},
|
| 240 |
-
year = {2025},
|
| 241 |
-
publisher = {Belweave},
|
| 242 |
-
howpublished = {\\url{https://huggingface.co/preethamkyanam/kai-2}}
|
| 243 |
-
}
|
| 244 |
-
```
|
| 245 |
-
|
| 246 |
-
## Acknowledgments
|
| 247 |
-
|
| 248 |
-
- Base model: [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) by Alibaba Cloud
|
| 249 |
-
- Training framework (Stage 1): [TRL](https://github.com/huggingface/trl) + [PEFT](https://github.com/huggingface/peft)
|
| 250 |
-
- Training framework (Stage 2): [MLX](https://github.com/ml-explore/mlx) by Apple
|
| 251 |
-
- Compute: [Lambda Cloud](https://lambdalabs.com)
|
| 252 |
-
|
| 253 |
-
## Contact
|
| 254 |
-
|
| 255 |
-
For questions, issues, or collaboration inquiries, reach out via [Belweave](https://belweave.com) or open an issue on the model page.
|
|
|
|
| 1 |
---
|
| 2 |
+
language: en
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
+
library_name: mlx
|
| 5 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- mlx
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -47,6 +47,16 @@
|
|
| 47 |
"num_hidden_layers": 28,
|
| 48 |
"num_key_value_heads": 4,
|
| 49 |
"pad_token_id": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"rms_norm_eps": 1e-06,
|
| 51 |
"rope_parameters": {
|
| 52 |
"rope_theta": 1000000.0,
|
|
|
|
| 47 |
"num_hidden_layers": 28,
|
| 48 |
"num_key_value_heads": 4,
|
| 49 |
"pad_token_id": null,
|
| 50 |
+
"quantization": {
|
| 51 |
+
"group_size": 64,
|
| 52 |
+
"bits": 4,
|
| 53 |
+
"mode": "affine"
|
| 54 |
+
},
|
| 55 |
+
"quantization_config": {
|
| 56 |
+
"group_size": 64,
|
| 57 |
+
"bits": 4,
|
| 58 |
+
"mode": "affine"
|
| 59 |
+
},
|
| 60 |
"rms_norm_eps": 1e-06,
|
| 61 |
"rope_parameters": {
|
| 62 |
"rope_theta": 1000000.0,
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10451965ba9072fe2e9f518699720b2a6642be9b42553555dd35b50ee165726d
|
| 3 |
+
size 4284346724
|
model.safetensors.index.json
CHANGED
|
@@ -1,347 +1,743 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
"total_parameters": 7615616512
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
-
"lm_head.
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"model.
|
| 11 |
-
"model.
|
| 12 |
-
"model.
|
| 13 |
-
"model.layers.0.
|
| 14 |
-
"model.layers.0.
|
| 15 |
-
"model.layers.0.
|
| 16 |
-
"model.layers.0.
|
| 17 |
-
"model.layers.0.
|
| 18 |
-
"model.layers.0.
|
| 19 |
-
"model.layers.0.
|
| 20 |
-
"model.layers.0.
|
| 21 |
-
"model.layers.
|
| 22 |
-
"model.layers.
|
| 23 |
-
"model.layers.
|
| 24 |
-
"model.layers.
|
| 25 |
-
"model.layers.
|
| 26 |
-
"model.layers.
|
| 27 |
-
"model.layers.
|
| 28 |
-
"model.layers.
|
| 29 |
-
"model.layers.
|
| 30 |
-
"model.layers.
|
| 31 |
-
"model.layers.
|
| 32 |
-
"model.layers.
|
| 33 |
-
"model.layers.
|
| 34 |
-
"model.layers.
|
| 35 |
-
"model.layers.
|
| 36 |
-
"model.layers.
|
| 37 |
-
"model.layers.
|
| 38 |
-
"model.layers.
|
| 39 |
-
"model.layers.
|
| 40 |
-
"model.layers.
|
| 41 |
-
"model.layers.
|
| 42 |
-
"model.layers.
|
| 43 |
-
"model.layers.
|
| 44 |
-
"model.layers.
|
| 45 |
-
"model.layers.
|
| 46 |
-
"model.layers.
|
| 47 |
-
"model.layers.
|
| 48 |
-
"model.layers.
|
| 49 |
-
"model.layers.
|
| 50 |
-
"model.layers.
|
| 51 |
-
"model.layers.
|
| 52 |
-
"model.layers.
|
| 53 |
-
"model.layers.
|
| 54 |
-
"model.layers.
|
| 55 |
-
"model.layers.
|
| 56 |
-
"model.layers.
|
| 57 |
-
"model.layers.
|
| 58 |
-
"model.layers.
|
| 59 |
-
"model.layers.
|
| 60 |
-
"model.layers.
|
| 61 |
-
"model.layers.
|
| 62 |
-
"model.layers.
|
| 63 |
-
"model.layers.
|
| 64 |
-
"model.layers.
|
| 65 |
-
"model.layers.
|
| 66 |
-
"model.layers.
|
| 67 |
-
"model.layers.
|
| 68 |
-
"model.layers.
|
| 69 |
-
"model.layers.
|
| 70 |
-
"model.layers.
|
| 71 |
-
"model.layers.
|
| 72 |
-
"model.layers.
|
| 73 |
-
"model.layers.
|
| 74 |
-
"model.layers.
|
| 75 |
-
"model.layers.
|
| 76 |
-
"model.layers.
|
| 77 |
-
"model.layers.
|
| 78 |
-
"model.layers.
|
| 79 |
-
"model.layers.
|
| 80 |
-
"model.layers.
|
| 81 |
-
"model.layers.
|
| 82 |
-
"model.layers.
|
| 83 |
-
"model.layers.
|
| 84 |
-
"model.layers.
|
| 85 |
-
"model.layers.
|
| 86 |
-
"model.layers.
|
| 87 |
-
"model.layers.
|
| 88 |
-
"model.layers.
|
| 89 |
-
"model.layers.
|
| 90 |
-
"model.layers.
|
| 91 |
-
"model.layers.
|
| 92 |
-
"model.layers.
|
| 93 |
-
"model.layers.
|
| 94 |
-
"model.layers.
|
| 95 |
-
"model.layers.
|
| 96 |
-
"model.layers.
|
| 97 |
-
"model.layers.
|
| 98 |
-
"model.layers.
|
| 99 |
-
"model.layers.
|
| 100 |
-
"model.layers.
|
| 101 |
-
"model.layers.
|
| 102 |
-
"model.layers.
|
| 103 |
-
"model.layers.
|
| 104 |
-
"model.layers.
|
| 105 |
-
"model.layers.
|
| 106 |
-
"model.layers.
|
| 107 |
-
"model.layers.
|
| 108 |
-
"model.layers.
|
| 109 |
-
"model.layers.
|
| 110 |
-
"model.layers.
|
| 111 |
-
"model.layers.
|
| 112 |
-
"model.layers.
|
| 113 |
-
"model.layers.
|
| 114 |
-
"model.layers.
|
| 115 |
-
"model.layers.
|
| 116 |
-
"model.layers.
|
| 117 |
-
"model.layers.
|
| 118 |
-
"model.layers.
|
| 119 |
-
"model.layers.
|
| 120 |
-
"model.layers.
|
| 121 |
-
"model.layers.
|
| 122 |
-
"model.layers.
|
| 123 |
-
"model.layers.
|
| 124 |
-
"model.layers.
|
| 125 |
-
"model.layers.
|
| 126 |
-
"model.layers.
|
| 127 |
-
"model.layers.
|
| 128 |
-
"model.layers.
|
| 129 |
-
"model.layers.
|
| 130 |
-
"model.layers.
|
| 131 |
-
"model.layers.
|
| 132 |
-
"model.layers.
|
| 133 |
-
"model.layers.
|
| 134 |
-
"model.layers.
|
| 135 |
-
"model.layers.
|
| 136 |
-
"model.layers.
|
| 137 |
-
"model.layers.
|
| 138 |
-
"model.layers.
|
| 139 |
-
"model.layers.
|
| 140 |
-
"model.layers.
|
| 141 |
-
"model.layers.
|
| 142 |
-
"model.layers.
|
| 143 |
-
"model.layers.
|
| 144 |
-
"model.layers.
|
| 145 |
-
"model.layers.
|
| 146 |
-
"model.layers.
|
| 147 |
-
"model.layers.
|
| 148 |
-
"model.layers.
|
| 149 |
-
"model.layers.
|
| 150 |
-
"model.layers.
|
| 151 |
-
"model.layers.
|
| 152 |
-
"model.layers.
|
| 153 |
-
"model.layers.
|
| 154 |
-
"model.layers.
|
| 155 |
-
"model.layers.
|
| 156 |
-
"model.layers.
|
| 157 |
-
"model.layers.
|
| 158 |
-
"model.layers.
|
| 159 |
-
"model.layers.
|
| 160 |
-
"model.layers.
|
| 161 |
-
"model.layers.
|
| 162 |
-
"model.layers.
|
| 163 |
-
"model.layers.
|
| 164 |
-
"model.layers.
|
| 165 |
-
"model.layers.
|
| 166 |
-
"model.layers.
|
| 167 |
-
"model.layers.
|
| 168 |
-
"model.layers.
|
| 169 |
-
"model.layers.
|
| 170 |
-
"model.layers.
|
| 171 |
-
"model.layers.
|
| 172 |
-
"model.layers.
|
| 173 |
-
"model.layers.
|
| 174 |
-
"model.layers.
|
| 175 |
-
"model.layers.
|
| 176 |
-
"model.layers.
|
| 177 |
-
"model.layers.
|
| 178 |
-
"model.layers.
|
| 179 |
-
"model.layers.
|
| 180 |
-
"model.layers.
|
| 181 |
-
"model.layers.
|
| 182 |
-
"model.layers.
|
| 183 |
-
"model.layers.
|
| 184 |
-
"model.layers.
|
| 185 |
-
"model.layers.
|
| 186 |
-
"model.layers.
|
| 187 |
-
"model.layers.
|
| 188 |
-
"model.layers.
|
| 189 |
-
"model.layers.
|
| 190 |
-
"model.layers.
|
| 191 |
-
"model.layers.
|
| 192 |
-
"model.layers.
|
| 193 |
-
"model.layers.
|
| 194 |
-
"model.layers.
|
| 195 |
-
"model.layers.
|
| 196 |
-
"model.layers.
|
| 197 |
-
"model.layers.
|
| 198 |
-
"model.layers.
|
| 199 |
-
"model.layers.
|
| 200 |
-
"model.layers.
|
| 201 |
-
"model.layers.
|
| 202 |
-
"model.layers.
|
| 203 |
-
"model.layers.
|
| 204 |
-
"model.layers.
|
| 205 |
-
"model.layers.
|
| 206 |
-
"model.layers.
|
| 207 |
-
"model.layers.
|
| 208 |
-
"model.layers.
|
| 209 |
-
"model.layers.
|
| 210 |
-
"model.layers.
|
| 211 |
-
"model.layers.
|
| 212 |
-
"model.layers.
|
| 213 |
-
"model.layers.
|
| 214 |
-
"model.layers.
|
| 215 |
-
"model.layers.
|
| 216 |
-
"model.layers.
|
| 217 |
-
"model.layers.
|
| 218 |
-
"model.layers.
|
| 219 |
-
"model.layers.
|
| 220 |
-
"model.layers.
|
| 221 |
-
"model.layers.
|
| 222 |
-
"model.layers.
|
| 223 |
-
"model.layers.
|
| 224 |
-
"model.layers.
|
| 225 |
-
"model.layers.
|
| 226 |
-
"model.layers.
|
| 227 |
-
"model.layers.
|
| 228 |
-
"model.layers.
|
| 229 |
-
"model.layers.
|
| 230 |
-
"model.layers.
|
| 231 |
-
"model.layers.
|
| 232 |
-
"model.layers.
|
| 233 |
-
"model.layers.
|
| 234 |
-
"model.layers.
|
| 235 |
-
"model.layers.
|
| 236 |
-
"model.layers.
|
| 237 |
-
"model.layers.
|
| 238 |
-
"model.layers.
|
| 239 |
-
"model.layers.
|
| 240 |
-
"model.layers.
|
| 241 |
-
"model.layers.
|
| 242 |
-
"model.layers.
|
| 243 |
-
"model.layers.
|
| 244 |
-
"model.layers.
|
| 245 |
-
"model.layers.
|
| 246 |
-
"model.layers.
|
| 247 |
-
"model.layers.
|
| 248 |
-
"model.layers.
|
| 249 |
-
"model.layers.
|
| 250 |
-
"model.layers.
|
| 251 |
-
"model.layers.
|
| 252 |
-
"model.layers.
|
| 253 |
-
"model.layers.
|
| 254 |
-
"model.layers.
|
| 255 |
-
"model.layers.
|
| 256 |
-
"model.layers.
|
| 257 |
-
"model.layers.
|
| 258 |
-
"model.layers.
|
| 259 |
-
"model.layers.
|
| 260 |
-
"model.layers.
|
| 261 |
-
"model.layers.
|
| 262 |
-
"model.layers.
|
| 263 |
-
"model.layers.
|
| 264 |
-
"model.layers.
|
| 265 |
-
"model.layers.
|
| 266 |
-
"model.layers.
|
| 267 |
-
"model.layers.
|
| 268 |
-
"model.layers.
|
| 269 |
-
"model.layers.
|
| 270 |
-
"model.layers.
|
| 271 |
-
"model.layers.
|
| 272 |
-
"model.layers.
|
| 273 |
-
"model.layers.
|
| 274 |
-
"model.layers.
|
| 275 |
-
"model.layers.
|
| 276 |
-
"model.layers.
|
| 277 |
-
"model.layers.
|
| 278 |
-
"model.layers.
|
| 279 |
-
"model.layers.
|
| 280 |
-
"model.layers.
|
| 281 |
-
"model.layers.
|
| 282 |
-
"model.layers.
|
| 283 |
-
"model.layers.
|
| 284 |
-
"model.layers.
|
| 285 |
-
"model.layers.
|
| 286 |
-
"model.layers.
|
| 287 |
-
"model.layers.
|
| 288 |
-
"model.layers.
|
| 289 |
-
"model.layers.
|
| 290 |
-
"model.layers.
|
| 291 |
-
"model.layers.
|
| 292 |
-
"model.layers.
|
| 293 |
-
"model.layers.
|
| 294 |
-
"model.layers.
|
| 295 |
-
"model.layers.
|
| 296 |
-
"model.layers.
|
| 297 |
-
"model.layers.
|
| 298 |
-
"model.layers.
|
| 299 |
-
"model.layers.
|
| 300 |
-
"model.layers.
|
| 301 |
-
"model.layers.
|
| 302 |
-
"model.layers.
|
| 303 |
-
"model.layers.
|
| 304 |
-
"model.layers.
|
| 305 |
-
"model.layers.
|
| 306 |
-
"model.layers.
|
| 307 |
-
"model.layers.
|
| 308 |
-
"model.layers.
|
| 309 |
-
"model.layers.
|
| 310 |
-
"model.layers.
|
| 311 |
-
"model.layers.
|
| 312 |
-
"model.layers.
|
| 313 |
-
"model.layers.
|
| 314 |
-
"model.layers.
|
| 315 |
-
"model.layers.
|
| 316 |
-
"model.layers.
|
| 317 |
-
"model.layers.
|
| 318 |
-
"model.layers.
|
| 319 |
-
"model.layers.
|
| 320 |
-
"model.layers.
|
| 321 |
-
"model.layers.
|
| 322 |
-
"model.layers.
|
| 323 |
-
"model.layers.
|
| 324 |
-
"model.layers.
|
| 325 |
-
"model.layers.
|
| 326 |
-
"model.layers.
|
| 327 |
-
"model.layers.
|
| 328 |
-
"model.layers.
|
| 329 |
-
"model.layers.
|
| 330 |
-
"model.layers.
|
| 331 |
-
"model.layers.
|
| 332 |
-
"model.layers.
|
| 333 |
-
"model.layers.
|
| 334 |
-
"model.layers.
|
| 335 |
-
"model.layers.
|
| 336 |
-
"model.layers.
|
| 337 |
-
"model.layers.
|
| 338 |
-
"model.layers.
|
| 339 |
-
"model.layers.
|
| 340 |
-
"model.layers.
|
| 341 |
-
"model.layers.
|
| 342 |
-
"model.layers.
|
| 343 |
-
"model.layers.
|
| 344 |
-
"model.layers.
|
| 345 |
-
"model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 346 |
}
|
| 347 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 4284263424,
|
| 4 |
"total_parameters": 7615616512
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
+
"lm_head.biases": "model.safetensors",
|
| 8 |
+
"lm_head.scales": "model.safetensors",
|
| 9 |
+
"lm_head.weight": "model.safetensors",
|
| 10 |
+
"model.embed_tokens.biases": "model.safetensors",
|
| 11 |
+
"model.embed_tokens.scales": "model.safetensors",
|
| 12 |
+
"model.embed_tokens.weight": "model.safetensors",
|
| 13 |
+
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 14 |
+
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
| 15 |
+
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 16 |
+
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 17 |
+
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
| 18 |
+
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 19 |
+
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 20 |
+
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
| 21 |
+
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 22 |
+
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 23 |
+
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.k_proj.bias": "model.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.q_proj.bias": "model.safetensors",
|
| 32 |
+
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 33 |
+
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 34 |
+
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 35 |
+
"model.layers.0.self_attn.v_proj.bias": "model.safetensors",
|
| 36 |
+
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 37 |
+
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 38 |
+
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 39 |
+
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 40 |
+
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
| 41 |
+
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 42 |
+
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 43 |
+
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
| 44 |
+
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 45 |
+
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 46 |
+
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
| 47 |
+
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 48 |
+
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 49 |
+
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 50 |
+
"model.layers.1.self_attn.k_proj.bias": "model.safetensors",
|
| 51 |
+
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 52 |
+
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 53 |
+
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 54 |
+
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
| 55 |
+
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 56 |
+
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 57 |
+
"model.layers.1.self_attn.q_proj.bias": "model.safetensors",
|
| 58 |
+
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 59 |
+
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 60 |
+
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 61 |
+
"model.layers.1.self_attn.v_proj.bias": "model.safetensors",
|
| 62 |
+
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 63 |
+
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 64 |
+
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 65 |
+
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 66 |
+
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
| 67 |
+
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 68 |
+
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 69 |
+
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
| 70 |
+
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 71 |
+
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 72 |
+
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
| 73 |
+
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 74 |
+
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 75 |
+
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 76 |
+
"model.layers.10.self_attn.k_proj.bias": "model.safetensors",
|
| 77 |
+
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 78 |
+
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 79 |
+
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 80 |
+
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
| 81 |
+
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 82 |
+
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 83 |
+
"model.layers.10.self_attn.q_proj.bias": "model.safetensors",
|
| 84 |
+
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 85 |
+
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 86 |
+
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 87 |
+
"model.layers.10.self_attn.v_proj.bias": "model.safetensors",
|
| 88 |
+
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 89 |
+
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 90 |
+
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 91 |
+
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 92 |
+
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
| 93 |
+
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 94 |
+
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 95 |
+
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
| 96 |
+
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 97 |
+
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 98 |
+
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
| 99 |
+
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 100 |
+
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 101 |
+
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 102 |
+
"model.layers.11.self_attn.k_proj.bias": "model.safetensors",
|
| 103 |
+
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 104 |
+
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 105 |
+
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 106 |
+
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
| 107 |
+
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 108 |
+
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 109 |
+
"model.layers.11.self_attn.q_proj.bias": "model.safetensors",
|
| 110 |
+
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 111 |
+
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 112 |
+
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 113 |
+
"model.layers.11.self_attn.v_proj.bias": "model.safetensors",
|
| 114 |
+
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 115 |
+
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 116 |
+
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 117 |
+
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 118 |
+
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
| 119 |
+
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 120 |
+
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 121 |
+
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
| 122 |
+
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 123 |
+
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 124 |
+
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
| 125 |
+
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 126 |
+
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 127 |
+
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 128 |
+
"model.layers.12.self_attn.k_proj.bias": "model.safetensors",
|
| 129 |
+
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 130 |
+
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 131 |
+
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 132 |
+
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
| 133 |
+
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 134 |
+
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 135 |
+
"model.layers.12.self_attn.q_proj.bias": "model.safetensors",
|
| 136 |
+
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 137 |
+
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 138 |
+
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 139 |
+
"model.layers.12.self_attn.v_proj.bias": "model.safetensors",
|
| 140 |
+
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 141 |
+
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 142 |
+
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 143 |
+
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 144 |
+
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
| 145 |
+
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 146 |
+
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 147 |
+
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
| 148 |
+
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 149 |
+
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 150 |
+
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
| 151 |
+
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 152 |
+
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 153 |
+
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 154 |
+
"model.layers.13.self_attn.k_proj.bias": "model.safetensors",
|
| 155 |
+
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 156 |
+
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 157 |
+
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 158 |
+
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
| 159 |
+
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 160 |
+
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 161 |
+
"model.layers.13.self_attn.q_proj.bias": "model.safetensors",
|
| 162 |
+
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 163 |
+
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 164 |
+
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 165 |
+
"model.layers.13.self_attn.v_proj.bias": "model.safetensors",
|
| 166 |
+
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 167 |
+
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 168 |
+
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 169 |
+
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 170 |
+
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
| 171 |
+
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 172 |
+
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 173 |
+
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
| 174 |
+
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 175 |
+
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 176 |
+
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
| 177 |
+
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 178 |
+
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 179 |
+
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 180 |
+
"model.layers.14.self_attn.k_proj.bias": "model.safetensors",
|
| 181 |
+
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 182 |
+
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 183 |
+
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 184 |
+
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
| 185 |
+
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 186 |
+
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 187 |
+
"model.layers.14.self_attn.q_proj.bias": "model.safetensors",
|
| 188 |
+
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 189 |
+
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 190 |
+
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 191 |
+
"model.layers.14.self_attn.v_proj.bias": "model.safetensors",
|
| 192 |
+
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 193 |
+
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 194 |
+
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 195 |
+
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 196 |
+
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
| 197 |
+
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 198 |
+
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 199 |
+
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
| 200 |
+
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 201 |
+
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 202 |
+
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
| 203 |
+
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 204 |
+
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 205 |
+
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 206 |
+
"model.layers.15.self_attn.k_proj.bias": "model.safetensors",
|
| 207 |
+
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 208 |
+
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 209 |
+
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 210 |
+
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
| 211 |
+
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 212 |
+
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 213 |
+
"model.layers.15.self_attn.q_proj.bias": "model.safetensors",
|
| 214 |
+
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 215 |
+
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 216 |
+
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 217 |
+
"model.layers.15.self_attn.v_proj.bias": "model.safetensors",
|
| 218 |
+
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 219 |
+
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 220 |
+
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 221 |
+
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 222 |
+
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
| 223 |
+
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 224 |
+
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 225 |
+
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
| 226 |
+
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 227 |
+
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 228 |
+
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
| 229 |
+
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 230 |
+
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 231 |
+
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 232 |
+
"model.layers.16.self_attn.k_proj.bias": "model.safetensors",
|
| 233 |
+
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 234 |
+
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 235 |
+
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 236 |
+
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
| 237 |
+
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 238 |
+
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 239 |
+
"model.layers.16.self_attn.q_proj.bias": "model.safetensors",
|
| 240 |
+
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 241 |
+
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 242 |
+
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 243 |
+
"model.layers.16.self_attn.v_proj.bias": "model.safetensors",
|
| 244 |
+
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 245 |
+
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 246 |
+
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 247 |
+
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 248 |
+
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
| 249 |
+
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 250 |
+
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 251 |
+
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
| 252 |
+
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 253 |
+
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 254 |
+
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
| 255 |
+
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 256 |
+
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 257 |
+
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 258 |
+
"model.layers.17.self_attn.k_proj.bias": "model.safetensors",
|
| 259 |
+
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 260 |
+
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 261 |
+
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 262 |
+
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
| 263 |
+
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 264 |
+
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 265 |
+
"model.layers.17.self_attn.q_proj.bias": "model.safetensors",
|
| 266 |
+
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 267 |
+
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 268 |
+
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 269 |
+
"model.layers.17.self_attn.v_proj.bias": "model.safetensors",
|
| 270 |
+
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 271 |
+
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 272 |
+
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 273 |
+
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 274 |
+
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
| 275 |
+
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 276 |
+
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 277 |
+
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
| 278 |
+
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 279 |
+
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 280 |
+
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
| 281 |
+
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 282 |
+
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 283 |
+
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 284 |
+
"model.layers.18.self_attn.k_proj.bias": "model.safetensors",
|
| 285 |
+
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 286 |
+
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 287 |
+
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 288 |
+
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
| 289 |
+
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 290 |
+
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 291 |
+
"model.layers.18.self_attn.q_proj.bias": "model.safetensors",
|
| 292 |
+
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 293 |
+
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 294 |
+
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 295 |
+
"model.layers.18.self_attn.v_proj.bias": "model.safetensors",
|
| 296 |
+
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 297 |
+
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 298 |
+
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 299 |
+
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 300 |
+
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
| 301 |
+
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 302 |
+
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 303 |
+
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
| 304 |
+
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 305 |
+
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 306 |
+
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
| 307 |
+
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 308 |
+
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 309 |
+
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 310 |
+
"model.layers.19.self_attn.k_proj.bias": "model.safetensors",
|
| 311 |
+
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 312 |
+
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 313 |
+
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 314 |
+
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
| 315 |
+
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 316 |
+
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 317 |
+
"model.layers.19.self_attn.q_proj.bias": "model.safetensors",
|
| 318 |
+
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 319 |
+
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 320 |
+
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 321 |
+
"model.layers.19.self_attn.v_proj.bias": "model.safetensors",
|
| 322 |
+
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 323 |
+
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 324 |
+
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 325 |
+
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 326 |
+
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
| 327 |
+
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 328 |
+
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 329 |
+
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
| 330 |
+
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 331 |
+
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 332 |
+
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
| 333 |
+
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 334 |
+
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 335 |
+
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 336 |
+
"model.layers.2.self_attn.k_proj.bias": "model.safetensors",
|
| 337 |
+
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 338 |
+
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 339 |
+
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 340 |
+
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 341 |
+
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 342 |
+
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 343 |
+
"model.layers.2.self_attn.q_proj.bias": "model.safetensors",
|
| 344 |
+
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 345 |
+
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 346 |
+
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 347 |
+
"model.layers.2.self_attn.v_proj.bias": "model.safetensors",
|
| 348 |
+
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 349 |
+
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 350 |
+
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 351 |
+
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 352 |
+
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 353 |
+
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 354 |
+
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 355 |
+
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 356 |
+
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 357 |
+
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 358 |
+
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 359 |
+
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 360 |
+
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 361 |
+
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 362 |
+
"model.layers.20.self_attn.k_proj.bias": "model.safetensors",
|
| 363 |
+
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 364 |
+
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 365 |
+
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 366 |
+
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 367 |
+
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 368 |
+
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 369 |
+
"model.layers.20.self_attn.q_proj.bias": "model.safetensors",
|
| 370 |
+
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 371 |
+
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 372 |
+
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 373 |
+
"model.layers.20.self_attn.v_proj.bias": "model.safetensors",
|
| 374 |
+
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 375 |
+
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 376 |
+
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 377 |
+
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 378 |
+
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 379 |
+
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 380 |
+
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 381 |
+
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 382 |
+
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 383 |
+
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 384 |
+
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 385 |
+
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 386 |
+
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 387 |
+
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 388 |
+
"model.layers.21.self_attn.k_proj.bias": "model.safetensors",
|
| 389 |
+
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 390 |
+
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 391 |
+
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 392 |
+
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 393 |
+
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 394 |
+
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 395 |
+
"model.layers.21.self_attn.q_proj.bias": "model.safetensors",
|
| 396 |
+
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 397 |
+
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 398 |
+
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 399 |
+
"model.layers.21.self_attn.v_proj.bias": "model.safetensors",
|
| 400 |
+
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 401 |
+
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 402 |
+
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 403 |
+
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 404 |
+
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 405 |
+
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 406 |
+
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 407 |
+
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 408 |
+
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 409 |
+
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 410 |
+
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 411 |
+
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 412 |
+
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 413 |
+
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 414 |
+
"model.layers.22.self_attn.k_proj.bias": "model.safetensors",
|
| 415 |
+
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 416 |
+
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 417 |
+
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 418 |
+
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 419 |
+
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 420 |
+
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 421 |
+
"model.layers.22.self_attn.q_proj.bias": "model.safetensors",
|
| 422 |
+
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 423 |
+
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 424 |
+
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 425 |
+
"model.layers.22.self_attn.v_proj.bias": "model.safetensors",
|
| 426 |
+
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 427 |
+
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 428 |
+
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 429 |
+
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 430 |
+
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 431 |
+
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 432 |
+
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 433 |
+
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 434 |
+
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 435 |
+
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 436 |
+
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 437 |
+
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 438 |
+
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 439 |
+
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 440 |
+
"model.layers.23.self_attn.k_proj.bias": "model.safetensors",
|
| 441 |
+
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 442 |
+
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 443 |
+
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 444 |
+
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 445 |
+
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 446 |
+
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 447 |
+
"model.layers.23.self_attn.q_proj.bias": "model.safetensors",
|
| 448 |
+
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 449 |
+
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 450 |
+
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 451 |
+
"model.layers.23.self_attn.v_proj.bias": "model.safetensors",
|
| 452 |
+
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 453 |
+
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 454 |
+
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 455 |
+
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 456 |
+
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 457 |
+
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 458 |
+
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 459 |
+
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 460 |
+
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 461 |
+
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 462 |
+
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 463 |
+
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 464 |
+
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 465 |
+
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 466 |
+
"model.layers.24.self_attn.k_proj.bias": "model.safetensors",
|
| 467 |
+
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 468 |
+
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 469 |
+
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 470 |
+
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 471 |
+
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 472 |
+
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 473 |
+
"model.layers.24.self_attn.q_proj.bias": "model.safetensors",
|
| 474 |
+
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 475 |
+
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 476 |
+
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 477 |
+
"model.layers.24.self_attn.v_proj.bias": "model.safetensors",
|
| 478 |
+
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 479 |
+
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 480 |
+
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 481 |
+
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 482 |
+
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 483 |
+
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 484 |
+
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 485 |
+
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 486 |
+
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 487 |
+
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 488 |
+
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 489 |
+
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 490 |
+
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 491 |
+
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 492 |
+
"model.layers.25.self_attn.k_proj.bias": "model.safetensors",
|
| 493 |
+
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 494 |
+
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 495 |
+
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 496 |
+
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 497 |
+
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 498 |
+
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 499 |
+
"model.layers.25.self_attn.q_proj.bias": "model.safetensors",
|
| 500 |
+
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 501 |
+
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 502 |
+
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 503 |
+
"model.layers.25.self_attn.v_proj.bias": "model.safetensors",
|
| 504 |
+
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 505 |
+
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 506 |
+
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 507 |
+
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 508 |
+
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 509 |
+
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 510 |
+
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 511 |
+
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 512 |
+
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 513 |
+
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 514 |
+
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 515 |
+
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 516 |
+
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 517 |
+
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 518 |
+
"model.layers.26.self_attn.k_proj.bias": "model.safetensors",
|
| 519 |
+
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 520 |
+
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 521 |
+
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 522 |
+
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 523 |
+
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 524 |
+
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 525 |
+
"model.layers.26.self_attn.q_proj.bias": "model.safetensors",
|
| 526 |
+
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 527 |
+
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 528 |
+
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 529 |
+
"model.layers.26.self_attn.v_proj.bias": "model.safetensors",
|
| 530 |
+
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 531 |
+
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 532 |
+
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 533 |
+
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 534 |
+
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 535 |
+
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 536 |
+
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 537 |
+
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 538 |
+
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 539 |
+
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 540 |
+
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 541 |
+
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 542 |
+
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 543 |
+
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 544 |
+
"model.layers.27.self_attn.k_proj.bias": "model.safetensors",
|
| 545 |
+
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 546 |
+
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 547 |
+
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 548 |
+
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 549 |
+
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 550 |
+
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 551 |
+
"model.layers.27.self_attn.q_proj.bias": "model.safetensors",
|
| 552 |
+
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 553 |
+
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 554 |
+
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 555 |
+
"model.layers.27.self_attn.v_proj.bias": "model.safetensors",
|
| 556 |
+
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 557 |
+
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 558 |
+
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 559 |
+
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 560 |
+
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 561 |
+
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 562 |
+
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 563 |
+
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 564 |
+
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 565 |
+
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 566 |
+
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 567 |
+
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 568 |
+
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 569 |
+
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 570 |
+
"model.layers.3.self_attn.k_proj.bias": "model.safetensors",
|
| 571 |
+
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 572 |
+
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 573 |
+
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 574 |
+
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 575 |
+
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 576 |
+
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 577 |
+
"model.layers.3.self_attn.q_proj.bias": "model.safetensors",
|
| 578 |
+
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 579 |
+
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 580 |
+
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 581 |
+
"model.layers.3.self_attn.v_proj.bias": "model.safetensors",
|
| 582 |
+
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 583 |
+
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 584 |
+
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 585 |
+
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 586 |
+
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 587 |
+
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 588 |
+
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 589 |
+
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 590 |
+
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 591 |
+
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 592 |
+
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 593 |
+
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 594 |
+
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 595 |
+
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 596 |
+
"model.layers.4.self_attn.k_proj.bias": "model.safetensors",
|
| 597 |
+
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 598 |
+
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 599 |
+
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 600 |
+
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 601 |
+
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 602 |
+
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 603 |
+
"model.layers.4.self_attn.q_proj.bias": "model.safetensors",
|
| 604 |
+
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 605 |
+
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 606 |
+
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 607 |
+
"model.layers.4.self_attn.v_proj.bias": "model.safetensors",
|
| 608 |
+
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 609 |
+
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 610 |
+
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 611 |
+
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 612 |
+
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 613 |
+
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 614 |
+
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 615 |
+
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 616 |
+
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 617 |
+
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 618 |
+
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 619 |
+
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 620 |
+
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 621 |
+
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 622 |
+
"model.layers.5.self_attn.k_proj.bias": "model.safetensors",
|
| 623 |
+
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 624 |
+
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 625 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 626 |
+
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 627 |
+
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 628 |
+
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 629 |
+
"model.layers.5.self_attn.q_proj.bias": "model.safetensors",
|
| 630 |
+
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 631 |
+
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 632 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 633 |
+
"model.layers.5.self_attn.v_proj.bias": "model.safetensors",
|
| 634 |
+
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 635 |
+
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 636 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 637 |
+
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 638 |
+
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 639 |
+
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 640 |
+
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 641 |
+
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 642 |
+
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 643 |
+
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 644 |
+
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 645 |
+
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 646 |
+
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 647 |
+
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 648 |
+
"model.layers.6.self_attn.k_proj.bias": "model.safetensors",
|
| 649 |
+
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 650 |
+
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 651 |
+
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 652 |
+
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 653 |
+
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 654 |
+
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 655 |
+
"model.layers.6.self_attn.q_proj.bias": "model.safetensors",
|
| 656 |
+
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 657 |
+
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 658 |
+
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 659 |
+
"model.layers.6.self_attn.v_proj.bias": "model.safetensors",
|
| 660 |
+
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 661 |
+
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 662 |
+
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 663 |
+
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 664 |
+
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 665 |
+
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 666 |
+
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 667 |
+
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 668 |
+
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 669 |
+
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 670 |
+
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 671 |
+
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 672 |
+
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 673 |
+
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 674 |
+
"model.layers.7.self_attn.k_proj.bias": "model.safetensors",
|
| 675 |
+
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 676 |
+
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 677 |
+
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 678 |
+
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 679 |
+
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 680 |
+
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 681 |
+
"model.layers.7.self_attn.q_proj.bias": "model.safetensors",
|
| 682 |
+
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 683 |
+
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 684 |
+
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 685 |
+
"model.layers.7.self_attn.v_proj.bias": "model.safetensors",
|
| 686 |
+
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 687 |
+
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 688 |
+
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 689 |
+
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 690 |
+
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 691 |
+
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 692 |
+
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 693 |
+
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 694 |
+
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 695 |
+
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 696 |
+
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 697 |
+
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 698 |
+
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 699 |
+
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 700 |
+
"model.layers.8.self_attn.k_proj.bias": "model.safetensors",
|
| 701 |
+
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 702 |
+
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 703 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 704 |
+
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 705 |
+
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 706 |
+
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 707 |
+
"model.layers.8.self_attn.q_proj.bias": "model.safetensors",
|
| 708 |
+
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 709 |
+
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 710 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 711 |
+
"model.layers.8.self_attn.v_proj.bias": "model.safetensors",
|
| 712 |
+
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 713 |
+
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 714 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 715 |
+
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 716 |
+
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 717 |
+
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 718 |
+
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 719 |
+
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 720 |
+
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 721 |
+
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 722 |
+
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 723 |
+
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 724 |
+
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 725 |
+
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 726 |
+
"model.layers.9.self_attn.k_proj.bias": "model.safetensors",
|
| 727 |
+
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 728 |
+
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 729 |
+
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 730 |
+
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 731 |
+
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 732 |
+
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 733 |
+
"model.layers.9.self_attn.q_proj.bias": "model.safetensors",
|
| 734 |
+
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 735 |
+
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 736 |
+
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 737 |
+
"model.layers.9.self_attn.v_proj.bias": "model.safetensors",
|
| 738 |
+
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 739 |
+
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 740 |
+
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 741 |
+
"model.norm.weight": "model.safetensors"
|
| 742 |
}
|
| 743 |
}
|