Model upload
Browse files- .gitattributes +1 -0
- README.md +182 -0
- anemoi.png +3 -0
- config.json +29 -0
- measurement.json +0 -0
- model.safetensors.index.json +1 -0
- output-00001-of-00003.safetensors +3 -0
- output-00002-of-00003.safetensors +3 -0
- output-00003-of-00003.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
anemoi.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
license: other
|
5 |
+
model-index:
|
6 |
+
- name: QuartetAnemoi-70B-t0.0001
|
7 |
+
results:
|
8 |
+
- task:
|
9 |
+
type: text-generation
|
10 |
+
name: Text Generation
|
11 |
+
dataset:
|
12 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
13 |
+
type: ai2_arc
|
14 |
+
config: ARC-Challenge
|
15 |
+
split: test
|
16 |
+
args:
|
17 |
+
num_few_shot: 25
|
18 |
+
metrics:
|
19 |
+
- type: acc_norm
|
20 |
+
value: 73.38
|
21 |
+
name: normalized accuracy
|
22 |
+
source:
|
23 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
|
24 |
+
name: Open LLM Leaderboard
|
25 |
+
- task:
|
26 |
+
type: text-generation
|
27 |
+
name: Text Generation
|
28 |
+
dataset:
|
29 |
+
name: HellaSwag (10-Shot)
|
30 |
+
type: hellaswag
|
31 |
+
split: validation
|
32 |
+
args:
|
33 |
+
num_few_shot: 10
|
34 |
+
metrics:
|
35 |
+
- type: acc_norm
|
36 |
+
value: 88.9
|
37 |
+
name: normalized accuracy
|
38 |
+
source:
|
39 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
|
40 |
+
name: Open LLM Leaderboard
|
41 |
+
- task:
|
42 |
+
type: text-generation
|
43 |
+
name: Text Generation
|
44 |
+
dataset:
|
45 |
+
name: MMLU (5-Shot)
|
46 |
+
type: cais/mmlu
|
47 |
+
config: all
|
48 |
+
split: test
|
49 |
+
args:
|
50 |
+
num_few_shot: 5
|
51 |
+
metrics:
|
52 |
+
- type: acc
|
53 |
+
value: 75.42
|
54 |
+
name: accuracy
|
55 |
+
source:
|
56 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
|
57 |
+
name: Open LLM Leaderboard
|
58 |
+
- task:
|
59 |
+
type: text-generation
|
60 |
+
name: Text Generation
|
61 |
+
dataset:
|
62 |
+
name: TruthfulQA (0-shot)
|
63 |
+
type: truthful_qa
|
64 |
+
config: multiple_choice
|
65 |
+
split: validation
|
66 |
+
args:
|
67 |
+
num_few_shot: 0
|
68 |
+
metrics:
|
69 |
+
- type: mc2
|
70 |
+
value: 69.53
|
71 |
+
source:
|
72 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
|
73 |
+
name: Open LLM Leaderboard
|
74 |
+
- task:
|
75 |
+
type: text-generation
|
76 |
+
name: Text Generation
|
77 |
+
dataset:
|
78 |
+
name: Winogrande (5-shot)
|
79 |
+
type: winogrande
|
80 |
+
config: winogrande_xl
|
81 |
+
split: validation
|
82 |
+
args:
|
83 |
+
num_few_shot: 5
|
84 |
+
metrics:
|
85 |
+
- type: acc
|
86 |
+
value: 85.32
|
87 |
+
name: accuracy
|
88 |
+
source:
|
89 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
|
90 |
+
name: Open LLM Leaderboard
|
91 |
+
- task:
|
92 |
+
type: text-generation
|
93 |
+
name: Text Generation
|
94 |
+
dataset:
|
95 |
+
name: GSM8k (5-shot)
|
96 |
+
type: gsm8k
|
97 |
+
config: main
|
98 |
+
split: test
|
99 |
+
args:
|
100 |
+
num_few_shot: 5
|
101 |
+
metrics:
|
102 |
+
- type: acc
|
103 |
+
value: 68.61
|
104 |
+
name: accuracy
|
105 |
+
source:
|
106 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
|
107 |
+
name: Open LLM Leaderboard
|
108 |
+
---
|
109 |
+
|
110 |
+
<img src=https://huggingface.co/alchemonaut/QuartetAnemoi-70B-t0.0001/resolve/main/anemoi.png>
|
111 |
+
|
112 |
+
# QuartetAnemoi-70B-t0.0001
|
113 |
+
|
114 |
+
A sequential merge using a custom algorithm (NearSwap) of:
|
115 |
+
- [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)
|
116 |
+
- [Sao10K/WinterGoddess-1.4x-70B-L2](https://huggingface.co/Sao10K/WinterGoddess-1.4x-70B-L2)
|
117 |
+
- [Aurora-Nights-70B-v1.0](https://huggingface.co/sophosympatheia/Aurora-Nights-70B-v1.0)
|
118 |
+
- [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1)
|
119 |
+
|
120 |
+
<br/>
|
121 |
+
|
122 |
+
In our testing, this model seems like a storyteller, as might be expected, but the changes from this merge are extremely soft. We were impressed that, unlike most models, at the end of a story it did not often use cliches such as "In the end", "And so", "beacon of hope", etc.
|
123 |
+
|
124 |
+
<br/>
|
125 |
+
|
126 |
+
Quants available at: [alchemonaut/QuartetAnemoi-70B-t0.0001-GGUF](https://huggingface.co/alchemonaut/QuartetAnemoi-70B-t0.0001-GGUF/tree/main)
|
127 |
+
|
128 |
+
<br/>
|
129 |
+
<br/>
|
130 |
+
|
131 |
+
# NearSwap Algorithm
|
132 |
+
|
133 |
+
NearSwap retains most of the weights of the base model (Miqu), but when a weight is similar between the two, it is interpolated to the secondary model value. A parameter *t* specifies the sameness threshold. When the distance between two values is below *t*, the weight from the secondary model is used.
|
134 |
+
|
135 |
+
This version of the model uses *t* = 0.0001. At this *t*, about 0.8% of weights are fully switched to the secondary model during each pass. Model quality rapidly degrades above *t* = 0.0025:
|
136 |
+
|
137 |
+
- *t* = 0.0001 (~0.8% full swap): This model
|
138 |
+
- *t* = 0.0003 (~2% full swap)
|
139 |
+
- *t* = 0.001 (~10% full swap): [BoreanGale-70B](https://huggingface.co/alchemonaut/BoreanGale-70B)
|
140 |
+
- *t* = 0.0025 (~18% full swap): Generates one paragraph okay, but then reverts to garbage
|
141 |
+
- *t* = 0.005 (~35% full swap): Garbage; semi-related word lists
|
142 |
+
- *t* = 0.01 (~55% full swap): Garbage; pseudorandom tokens output
|
143 |
+
|
144 |
+
For QuartetAnemoi-70B-t0.0001, the three secondary models were each merged sequentially with *t* = 0.0001.
|
145 |
+
|
146 |
+
NearSwap implementation:
|
147 |
+
```
|
148 |
+
t: Union[float, np.ndarray],
|
149 |
+
v0: Union[np.ndarray, torch.Tensor],
|
150 |
+
v1: Union[np.ndarray, torch.Tensor],
|
151 |
+
...
|
152 |
+
lweight = numpy.absolute(v0-v1)
|
153 |
+
lweight = t / lweight
|
154 |
+
lweight = numpy.nan_to_num(lweight, nan=1.0, posinf=1.0, neginf=1.0)
|
155 |
+
numpy.clip(lweight, a_min=0.0, a_max=1.0, out=lweight)
|
156 |
+
res = lerp(lweight,v0,v1)
|
157 |
+
```
|
158 |
+
<br/>
|
159 |
+
<br/>
|
160 |
+
|
161 |
+
|
162 |
+
# License and Use
|
163 |
+
|
164 |
+
Since the ultimate origin of Miqu is at this time unknown beyond speculation, this model is for noncommercial research use only.
|
165 |
+
|
166 |
+
<br/>
|
167 |
+
<br/>
|
168 |
+
|
169 |
+
|
170 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
171 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_alchemonaut__QuartetAnemoi-70B-t0.0001)
|
172 |
+
|
173 |
+
| Metric |Value|
|
174 |
+
|---------------------------------|----:|
|
175 |
+
|Avg. |76.86|
|
176 |
+
|AI2 Reasoning Challenge (25-Shot)|73.38|
|
177 |
+
|HellaSwag (10-Shot) |88.9|
|
178 |
+
|MMLU (5-Shot) |75.42|
|
179 |
+
|TruthfulQA (0-shot) |69.53|
|
180 |
+
|Winogrande (5-shot) |85.32|
|
181 |
+
|GSM8k (5-shot) |68.61|
|
182 |
+
|
anemoi.png
ADDED
Git LFS Details
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "QuartetAnemoi-70B-t0.0001",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 8192,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 32764,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 64,
|
17 |
+
"num_hidden_layers": 80,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 1000000,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.37.1",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
measurement.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.46.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.52.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.53.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.57.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.56.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.55.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.59.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.58.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.63.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.66.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.65.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.64.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.68.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.67.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.71.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.70.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.69.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.74.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.73.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.72.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.77.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.76.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.75.input_layernorm.weight": "model-00014-of-00015.safetensors", "lm_head.weight": "model-00014-of-00015.safetensors", "model.norm.weight": "model-00014-of-00015.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.79.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00015-of-00015.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.78.input_layernorm.weight": "model-00015-of-00015.safetensors"}}
|
output-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31ec8ecad66ce319d58126fd1891fa3a3451dfe6e647254c1119605bd1985241
|
3 |
+
size 8542686158
|
output-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7895ce508449816486cde59263ade970932caa3bcbbba9622071c6457d3fb0fc
|
3 |
+
size 8548744268
|
output-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b107bcb871c1608d005c28b25e199c28ce4eac5b3befbfdd9ef652986e864246
|
3 |
+
size 5058597548
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"spaces_between_special_tokens": false,
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": false
|
41 |
+
}
|