Upload folder using huggingface_hub
Browse files- README.md +142 -0
- config.json +40 -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 +43 -0
README.md
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: yi-34b
|
4 |
+
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
|
5 |
+
tags:
|
6 |
+
- merge
|
7 |
+
- roleplay
|
8 |
+
- exl2
|
9 |
+
- not-for-all-audiences
|
10 |
+
---
|
11 |
+
|
12 |
+
# Merged-RP-Stew-V2-34B - EXL2 4.0bpw
|
13 |
+
|
14 |
+
This is a 4.0bpw EXL2 quant of [ParasiticRogue/Merged-RP-Stew-V2-34B](https://huggingface.co/ParasiticRogue/Merged-RP-Stew-V2-34B)
|
15 |
+
|
16 |
+
Details about the model and the merge info can be found at the above mode page.
|
17 |
+
|
18 |
+
|
19 |
+
## EXL2 Version
|
20 |
+
|
21 |
+
These quants were made with exllamav2 version 0.0.17. Quants made on this version of EXL2 may not working on older versions of the exllamav2 library.
|
22 |
+
|
23 |
+
If you have problems loading these models, please update Text Generation WebUI to the latest version.
|
24 |
+
|
25 |
+
|
26 |
+
## Perplexity Scoring
|
27 |
+
|
28 |
+
Below are the perplexity scores for the EXL2 models. A lower score is better.
|
29 |
+
|
30 |
+
|
31 |
+
| Quant Level | Perplexity Score |
|
32 |
+
|-------------|------------------|
|
33 |
+
| 8.0 | 5.2805 |
|
34 |
+
| 7.0 | 5.2841 |
|
35 |
+
| 6.0 | 5.2789 |
|
36 |
+
| 5.0 | 5.2930 |
|
37 |
+
| 4.5 | 5.3110 |
|
38 |
+
| 4.0 | 5.3663 |
|
39 |
+
| 3.5 | 5.4860 |
|
40 |
+
|
41 |
+
|
42 |
+
## EQ Bench
|
43 |
+
|
44 |
+
Here are the EQ Bench scores for the EXL2 quants using Alpaca, ChatML and Vicuna-Chat prompt templates. A higher score is better.
|
45 |
+
|
46 |
+
|
47 |
+
| Quant Size | Instruct Template | Score |
|
48 |
+
|------------|-------------------|-------|
|
49 |
+
| 8.0 | Alpaca | 75.02 |
|
50 |
+
| 8.0 | ChatML | 73.82 |
|
51 |
+
| 8.0 | Vicuna-Chat | 73.53 |
|
52 |
+
| 7.0 | Alpaca | 74.96 |
|
53 |
+
| 7.0 | ChatML | 74.22 |
|
54 |
+
| 7.0 | Vicuna-Chat | 72.71 |
|
55 |
+
| 6.0 | Alpaca | 75.11 |
|
56 |
+
| 6.0 | ChatML | 74.29 |
|
57 |
+
| 6.0 | Vicuna-Chat | 74.16 |
|
58 |
+
| 5.0 | Alpaca | 74.11 |
|
59 |
+
| 5.0 | ChatML | 72.74 |
|
60 |
+
| 5.0 | Vicuna-Chat | 73.28 |
|
61 |
+
| 4.5 | Alpaca | 73.18 |
|
62 |
+
| 4.5 | ChatML | 73.62 |
|
63 |
+
| 4.5 | Vicuna-Chat | 73.32 |
|
64 |
+
| 4.0 | Alpaca | 71.85 |
|
65 |
+
| 4.0 | ChatML | 73.99 |
|
66 |
+
| 4.0 | Vicuna-Chat | 74.74 |
|
67 |
+
| 3.5 | Alpaca | 73.73 |
|
68 |
+
| 3.5 | ChatML | 72.07 |
|
69 |
+
| 3.5 | Vicuna-Chat | 73.56 |
|
70 |
+
|
71 |
+
### Vicuna Chat Template
|
72 |
+
|
73 |
+
This is the Vicuna-Chat template yaml that was used in EQ bench. It was tested in Text Generation Web UI and seemed to produce accurate results.
|
74 |
+
|
75 |
+
```yaml
|
76 |
+
user: "USER:"
|
77 |
+
bot: "ASSISTANT:"
|
78 |
+
turn_template: "<|user|> <|user-message|><|im_end|>\n<|bot|> <|bot-message|><|im_end|></s>\n"
|
79 |
+
context: "<|system-message|><|im_end|>\n\n"
|
80 |
+
system_message: "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."
|
81 |
+
```
|
82 |
+
|
83 |
+
### Perplexity Script
|
84 |
+
|
85 |
+
This was the script used for perplexity testing.
|
86 |
+
|
87 |
+
```bash
|
88 |
+
#!/bin/bash
|
89 |
+
|
90 |
+
# Activate the conda environment
|
91 |
+
source ~/miniconda3/etc/profile.d/conda.sh
|
92 |
+
conda activate exllamav2
|
93 |
+
|
94 |
+
# Set the model name
|
95 |
+
MODEL_NAME="Merged-RP-Stew-V2-34B"
|
96 |
+
BIT_PRECISIONS=(8.0 7.0 6.0 5.0 4.5 4.0 3.5 3.0 2.65 2.4)
|
97 |
+
|
98 |
+
for BIT_PRECISION in "${BIT_PRECISIONS[@]}"
|
99 |
+
do
|
100 |
+
MODEL_DIR="models/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
|
101 |
+
|
102 |
+
if [ -d "$MODEL_DIR" ]; then
|
103 |
+
output=$(python test_inference.py -m "$MODEL_DIR" -gs 21,24 -ed data/wikitext/wikitext-2-v1.parquet)
|
104 |
+
score=$(echo "$output" | grep -oP 'Evaluation perplexity: \K[\d.]+')
|
105 |
+
echo "BPW: $BIT_PRECISION, Score: $score"
|
106 |
+
fi
|
107 |
+
|
108 |
+
done
|
109 |
+
```
|
110 |
+
|
111 |
+
|
112 |
+
## Quant Details
|
113 |
+
|
114 |
+
This is the script used for quantization. These quants were calibrated against Bluemoon-Light's Chat Vicuna training data.
|
115 |
+
|
116 |
+
```bash
|
117 |
+
#!/bin/bash
|
118 |
+
|
119 |
+
# Activate the conda environment
|
120 |
+
source ~/miniconda3/etc/profile.d/conda.sh
|
121 |
+
conda activate exllamav2
|
122 |
+
|
123 |
+
# Set the model name and bit size
|
124 |
+
MODEL_NAME="Merged-RP-Stew-V2-34B"
|
125 |
+
BIT_PRECISION=4.0
|
126 |
+
|
127 |
+
# Define variables
|
128 |
+
MODEL_DIR="models/$MODEL_NAME"
|
129 |
+
OUTPUT_DIR="exl2_$MODEL_NAME"
|
130 |
+
MEASUREMENT_FILE="measurements/$MODEL_NAME.json"
|
131 |
+
CONVERTED_FOLDER="models/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
|
132 |
+
CALIBRATION_DATASET="data/Bluemoon-Light/chat-vicuna.parquet"
|
133 |
+
|
134 |
+
# Create directories
|
135 |
+
rm -r "$OUTPUT_DIR"
|
136 |
+
mkdir "$OUTPUT_DIR"
|
137 |
+
mkdir "$CONVERTED_FOLDER"
|
138 |
+
|
139 |
+
# Run conversion commands
|
140 |
+
python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -om $MEASUREMENT_FILE -c $CALIBRATION_DATASET
|
141 |
+
python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -m $MEASUREMENT_FILE -b $BIT_PRECISION -c $CALIBRATION_DATASET -cf $CONVERTED_FOLDER
|
142 |
+
```
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Merged-RP-Stew-V2-34B",
|
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": 7168,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 20480,
|
14 |
+
"max_position_embeddings": 200000,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 56,
|
17 |
+
"num_hidden_layers": 60,
|
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": 5000000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.39.1",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 64000,
|
29 |
+
"quantization_config": {
|
30 |
+
"quant_method": "exl2",
|
31 |
+
"version": "0.0.17",
|
32 |
+
"bits": 4.0,
|
33 |
+
"head_bits": 6,
|
34 |
+
"calibration": {
|
35 |
+
"rows": 100,
|
36 |
+
"length": 2048,
|
37 |
+
"dataset": "chat-vicuna.parquet"
|
38 |
+
}
|
39 |
+
}
|
40 |
+
}
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1", "total_size": 68777834496}, "weight_map": {"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.51.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors"}}
|
output-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6977a362473c5e67d373b55994c6fc16a8f1267830cf4d9c2f8376df291b187e
|
3 |
+
size 8541209808
|
output-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5a40963c00b2869e724ee6452ae0a1053d307c726f78c33582876f5bd5d1aa3
|
3 |
+
size 8576959120
|
output-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dea60ba0b6b41658d95c329f5492bde30a27c2f45563ade255d16815722e08bc
|
3 |
+
size 900656256
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<|startoftext|>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 200000,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"truncation_side": "right",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|