VoidStare commited on
Commit
cc26167
·
verified ·
1 Parent(s): 0d3139c

Upload folder using huggingface_hub

Browse files
.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
+ eval.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
4
+ # Reka Flash 3
5
+
6
+ Reka Flash 3 is a 21B general-purpose reasoning model that was trained from scratch. It was trained in synthetic and public datasets for supervised finetuning, followed by RLOO with model-based and rule-based rewards. It performs competitively with proprietary models such as OpenAI o1-mini, making it a good foundation to build applications that require low latency or on-device deployment. It is currently the best open model in its size category.
7
+
8
+ Try it out at [Reka Space](https://space.reka.ai).
9
+
10
+ Reka Flash 3 powers Nexus, our new platform for organizations to create and manage AI workers. Nexus workers have native deep research capabilities and can browse the web, execute code, and analyse internal files including documents, images, videos and audio. Learn more about Nexus at [getnexus.reka.ai](https://getnexus.reka.ai).
11
+
12
+ ![Performance](./eval.png)
13
+
14
+ ## Quickstart
15
+
16
+ For ease of deployment, the model is released in a Llama-compatible format. You may use any library compatible with Llama to run the model.
17
+
18
+ ### Via Hugging Face
19
+
20
+ ```python
21
+ import transformers
22
+
23
+ tokenizer = transformers.AutoTokenizer.from_pretrained("RekaAI/reka-flash-3")
24
+ model = transformers.AutoModelForCausalLM.from_pretrained("RekaAI/reka-flash-3", torch_dtype='auto', device_map='auto')
25
+
26
+ prompt = {"role": "human", "content": "Write a poem about large language model."}
27
+ text = tokenizer.apply_chat_template([prompt], tokenize=False, add_generation_prompt=True)
28
+ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
29
+ outputs = model.generate(**model_inputs, max_new_tokens=512)
30
+ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
31
+ ```
32
+
33
+ ### Via vLLM
34
+
35
+ ```bash
36
+ docker run --rm -it --network=host --gpus '"device=0"' -v --shm-size=10.24gb vllm/vllm-openai:latest serve RekaAI/reka-flash-3 --dtype auto -tp 1
37
+ ```
38
+
39
+ ## Model Details
40
+
41
+ ### Prompt Format
42
+
43
+ Reka Flash 3 uses cl100k_base tokenizer and adds no additional special tokens. Its prompt format is as follows:
44
+
45
+ ```
46
+ human: this is round 1 prompt <sep> assistant: this is round 1 response <sep> ...
47
+ ```
48
+
49
+ Generation should stop on seeing the string `<sep>` or seeing the special token `<|endoftext|>`.
50
+
51
+ System prompt can be added by prepending to the first user round.
52
+
53
+ ```
54
+ human: You are a friendly assistant blah ... this is round 1 user prompt <sep> assistant: this is round 1 response <sep> ...
55
+ ```
56
+
57
+ For multi-round conversations, it is recommended to drop the reasoning traces in the previous assistant round to save tokens for the model to think.
58
+
59
+ If you are using HF or vLLM, the built-in chat_template shall handle prompt formatting automatically.
60
+
61
+ ### Budget Forcing
62
+
63
+ Reka Flash thinks before it produces an output. We use <reasoning> </reasoning> tags to indicate the beginning and the end of its thinking process. For some problems, the model might think for a long time. You can make the model to stop its thinking process by forcing it to output </reasoning> after a certain number of steps. We observe such a budget forcing mechanism will still produce a reasonable output. We show performance on AIME-2024 (cons@16) for various budgets below.
64
+
65
+ ![AIME'24](./aime.png)
66
+
67
+
68
+ ### Language Support
69
+
70
+ This model is primarily built for the English language, and you should consider this an English only model. However, the model is able to converse and understand other languages to some degree.
71
+
72
+
73
+ ### Relase Notes
74
+
75
+ - As a smaller model, it is not the best model for knowledge-intensive tasks. We recommend coupling Reka Flash 3 with web search for knowledge-related tasks.
76
+ - The model often thinks in English when prompted questions in non-English languages. We observe that this sometimes affects the output quality in non-English languages.
77
+ - The model has not undergone extensive alignment or persona training.
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|endofprompt|>": 100276
3
+ }
aime.png ADDED
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "eos_token_id": 100257,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 6144,
11
+ "initializer_range": 0.006,
12
+ "intermediate_size": 19648,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 44,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 8000000,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "use_cache": true,
25
+ "vocab_size": 100352,
26
+ "quantization_config": {
27
+ "quant_method": "exl2",
28
+ "version": "0.2.8",
29
+ "bits": 8.0,
30
+ "head_bits": 8,
31
+ "calibration": {
32
+ "rows": 115,
33
+ "length": 2048,
34
+ "dataset": "(default)"
35
+ }
36
+ }
37
+ }
eval.png ADDED

Git LFS Details

  • SHA256: 0f4c4347af3b177fba02cf21d70dbe7c208d49044c75636ec79a4ed06a3434b1
  • Pointer size: 131 Bytes
  • Size of remote file: 205 kB
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 100257,
3
+ "do_sample": true,
4
+ "eos_token_id": 100257,
5
+ "pad_token_id": 100257,
6
+ "temperature": 0.6,
7
+ "top_k": 1024,
8
+ "top_p": 0.95
9
+ }
10
+
measurement.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 41810964480
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
7
+ "lm_head.weight": "model-00001-of-00005.safetensors",
8
+ "model.norm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
27
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
28
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
29
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
30
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
31
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
32
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
33
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
34
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
35
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
36
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
37
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
38
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
39
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
40
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
41
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
42
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
43
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
44
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
45
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
46
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
47
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
48
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
49
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
50
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
51
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
52
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
53
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
54
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
55
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
56
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
57
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
58
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
59
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
60
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
61
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
62
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
63
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
64
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
65
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
66
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
67
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
68
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
69
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
70
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
71
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
72
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
73
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
74
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
75
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
76
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
77
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
78
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
79
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
80
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
81
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
82
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
83
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
84
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
85
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
86
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
87
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
88
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
89
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
90
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
91
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
92
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
93
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
94
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
95
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
96
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
97
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
98
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
99
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
100
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
101
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
102
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
103
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
104
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
105
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
106
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
107
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
108
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
109
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
110
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
111
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
112
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
113
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
114
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
115
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
116
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
117
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
118
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
119
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
120
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
121
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
122
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
123
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
124
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
125
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
126
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
127
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
128
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
129
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
130
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
131
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
132
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
133
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
134
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
135
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
136
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
137
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
138
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
139
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
140
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
141
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
142
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
143
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
144
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
145
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
146
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
147
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
148
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
149
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
150
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
151
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
152
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
153
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
154
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
155
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
156
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
157
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
158
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
159
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
160
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
161
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
162
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
163
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
164
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
165
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
166
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
167
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
168
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
169
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
170
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
171
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
172
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
173
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
174
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
175
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
176
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
177
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
178
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
179
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
180
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
181
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
182
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
183
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
184
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
185
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
186
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
187
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
188
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
189
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
190
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
191
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
192
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
193
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
194
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
195
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
196
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
197
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
198
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
199
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
200
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
201
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
202
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
203
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
204
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
205
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
206
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
207
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
208
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
209
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
210
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
211
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
212
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
213
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
214
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
215
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
216
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
217
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
218
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
219
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
220
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
221
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
222
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
223
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
224
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
225
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
226
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
227
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
228
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
229
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
230
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
231
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
232
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
233
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
235
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
237
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
238
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
239
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
240
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
241
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
242
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
243
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
244
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
245
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
246
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
247
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
248
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
249
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
250
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
251
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
252
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
253
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
254
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
256
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
257
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
258
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
259
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
260
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
261
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
262
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
263
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
264
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
265
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
266
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
267
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
268
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
269
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
270
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
271
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
272
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
273
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
274
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
275
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
276
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
277
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
278
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
279
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
280
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
281
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
282
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
283
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
284
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
285
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
286
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
287
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
288
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
290
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
292
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
293
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
294
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
295
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
296
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
297
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
298
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
299
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
300
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
301
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
302
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
303
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
304
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
305
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
306
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
307
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
308
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
309
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
310
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
311
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
312
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
313
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
314
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
315
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
316
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
317
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
318
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
319
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
321
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
322
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
323
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
324
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
325
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
326
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
327
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
329
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
332
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
333
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
334
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
335
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
336
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
337
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
338
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
339
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
340
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
341
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
342
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
343
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
344
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
345
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
346
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
347
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
348
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
349
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
350
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
351
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
352
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
353
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
354
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
355
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
356
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
357
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
358
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
359
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
360
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
361
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
362
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
363
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
364
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
365
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
366
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
367
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
368
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
369
+ "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
370
+ "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
371
+ "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
372
+ "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
373
+ "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
374
+ "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
375
+ "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
376
+ "model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
377
+ "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
378
+ "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
379
+ "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
380
+ "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
381
+ "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
382
+ "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
383
+ "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
384
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
385
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
386
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
387
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
388
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
389
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
390
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
391
+ "model.layers.42.input_layernorm.weight": "model-00005-of-00005.safetensors",
392
+ "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
393
+ "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
394
+ "model.layers.42.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
395
+ "model.layers.42.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
396
+ "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
397
+ "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
398
+ "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
399
+ "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
400
+ "model.layers.43.input_layernorm.weight": "model-00005-of-00005.safetensors",
401
+ "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
402
+ "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
403
+ "model.layers.43.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
404
+ "model.layers.43.mlp.down_proj.weight": "model-00005-of-00005.safetensors"
405
+ }
406
+ }
output-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96497c44c68d8033928b8491acdfd712cdaaaafd2b4f91671688c338c58a8980
3
+ size 8475321348
output-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63751f70fb8f5a28633a18c65c8063532421d5929a15a3c6b30449d82f24bb6
3
+ size 8475583196
output-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d261afdaafbb864a2f75207d91cf3eb04cf7cd2c8732341f24a08aca7eda4ca3
3
+ size 4573897480
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|fim_prefix|>",
5
+ "<|fim_middle|>",
6
+ "<|fim_suffix|>",
7
+ "<|endofprompt|>",
8
+ "<|_unuse_missing_100256|>",
9
+ "<|_unuse_missing_100261|>",
10
+ "<|_unuse_missing_100262|>",
11
+ "<|_unuse_missing_100263|>",
12
+ "<|_unuse_missing_100264|>",
13
+ "<|_unuse_missing_100265|>",
14
+ "<|_unuse_missing_100266|>",
15
+ "<|_unuse_missing_100267|>",
16
+ "<|_unuse_missing_100268|>",
17
+ "<|_unuse_missing_100269|>",
18
+ "<|_unuse_missing_100270|>",
19
+ "<|_unuse_missing_100271|>",
20
+ "<|_unuse_missing_100272|>",
21
+ "<|_unuse_missing_100273|>",
22
+ "<|_unuse_missing_100274|>",
23
+ "<|_unuse_missing_100275|>"
24
+ ],
25
+ "bos_token": "<|endoftext|>",
26
+ "eos_token": "<|endoftext|>",
27
+ "unk_token": "<|endoftext|>"
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|_unuse_missing_100256|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "<|_unuse_missing_100261|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100262": {
53
+ "content": "<|_unuse_missing_100262|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100263": {
61
+ "content": "<|_unuse_missing_100263|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100264": {
69
+ "content": "<|_unuse_missing_100264|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|_unuse_missing_100265|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|_unuse_missing_100266|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100267": {
93
+ "content": "<|_unuse_missing_100267|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100268": {
101
+ "content": "<|_unuse_missing_100268|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100269": {
109
+ "content": "<|_unuse_missing_100269|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100270": {
117
+ "content": "<|_unuse_missing_100270|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100271": {
125
+ "content": "<|_unuse_missing_100271|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100272": {
133
+ "content": "<|_unuse_missing_100272|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100273": {
141
+ "content": "<|_unuse_missing_100273|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100274": {
149
+ "content": "<|_unuse_missing_100274|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100275": {
157
+ "content": "<|_unuse_missing_100275|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ }
172
+ },
173
+ "additional_special_tokens": [
174
+ "<|endoftext|>",
175
+ "<|fim_prefix|>",
176
+ "<|fim_middle|>",
177
+ "<|fim_suffix|>",
178
+ "<|endofprompt|>",
179
+ "<|_unuse_missing_100256|>",
180
+ "<|_unuse_missing_100261|>",
181
+ "<|_unuse_missing_100262|>",
182
+ "<|_unuse_missing_100263|>",
183
+ "<|_unuse_missing_100264|>",
184
+ "<|_unuse_missing_100265|>",
185
+ "<|_unuse_missing_100266|>",
186
+ "<|_unuse_missing_100267|>",
187
+ "<|_unuse_missing_100268|>",
188
+ "<|_unuse_missing_100269|>",
189
+ "<|_unuse_missing_100270|>",
190
+ "<|_unuse_missing_100271|>",
191
+ "<|_unuse_missing_100272|>",
192
+ "<|_unuse_missing_100273|>",
193
+ "<|_unuse_missing_100274|>",
194
+ "<|_unuse_missing_100275|>"
195
+ ],
196
+ "bos_token": "<|endoftext|>",
197
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set merged_content = messages[0]['content'] + ' ' + messages[1]['content'] %}{% set merged_messages = [{'role': messages[1]['role'], 'content': merged_content}] + messages[2:] %}{% else %}{% set merged_messages = messages %}{% endif %}{% for message in merged_messages %}{{message['role'] + ': ' + (message['content'].split('<reasoning>')[0] + message['content'].split('</reasoning>')[1] if message['role'] == 'assistant' and '</reasoning>' in message['content'] else message['content'])}}{% if (loop.last and add_generation_prompt and merged_messages[-1]['role'] != 'assistant') or not loop.last %}{{ ' <sep> ' }}{% endif %}{% endfor %}{% if add_generation_prompt and merged_messages[-1]['role'] != 'assistant' %}{{ 'assistant:' }}{% endif %}",
198
+ "clean_up_tokenization_spaces": true,
199
+ "eos_token": "<|endoftext|>",
200
+ "model_max_length": 32768,
201
+ "tokenizer_class": "GPT2Tokenizer",
202
+ "unk_token": "<|endoftext|>"
203
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff