LoneStriker commited on
Commit
7644b12
1 Parent(s): 0b6de1d

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
+ Snow_Lotus_Logo.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - Roleplay
5
+ - Solar
6
+ - Mistral
7
+ - Text Generation
8
+ ---
9
+ ![SnowLotus Logo](https://cdn-uploads.huggingface.co/production/uploads/64bb1109aaccfd28b023bcec/gTQtPK46laLIFg0RTAv73.png)
10
+
11
+ ### Premise
12
+
13
+ So this is a basic slerp merge between a smart model and a good prose model. Prose and smarts. What we all want in an uncensored RP model right? I feel like Solar has untapped potential, in any case.
14
+
15
+ Sao10K's Frostwind finetune is a key component of the mixture, its smarts are impressive. NyxKrage's Frostmaid experiment, which merges Frostwind with a frankenmerge of Noromaid and a mystery medical model, delivers quite impressive prose. His model creatively incorporates long-range context and instructions too, despite being slightly incoherent due to the fraken merging.
16
+
17
+ So those are the main ingredients. Thanks to Nyx for sorting out the pytorch files btw.
18
+
19
+ ### Recipe
20
+
21
+ So, the recipe. I basically just gradient SLERP'd Frostwind into Frostmaid with these params:
22
+
23
+ - filter: self_attn
24
+ value: [0.9, 0.6, 0.3, 0, 0]
25
+ - filter: mlp
26
+ value: [0.3, 0.6]
27
+ - value: 0.5 # fallback for rest of tensors
28
+
29
+
30
+ ### Tentative Dozen or So Test Conclusion
31
+
32
+ This made a model that was actually pretty much everything I was looking for - NEARLY as smart as Frostwind but with MOST of Frostmaids punchy prose. I tried doing TIES merges and DARE ties merges, but they actually came out worse, because both models have major weaknesses - one is very dry and gpt-ish, the other is a little loose with what's going on. The ties merges tended to bring out those qualities, dare even worse. So I stuck with this. It's not AS smart as Frostwind, so you maybe have to regen a little, but it's pretty smart, and quite creative. A sweet spot hopefully. Maybe someone merge wiser than I can do more with this recipe, but I'm very pleased with it, it did what I was hoping for - a smaller model I can mobile dgpu and produces pretty outsized quality responses (it's fairly zealous tho, be warned). I've only played with it a TINY bit, so there may be qualities or flaws I've missed.
33
+
34
+ Cheers to all the finetuners, mergers and developers without which open source models wouldn't be half of what they are.
35
+
36
+ Resources used:
37
+
38
+ https://huggingface.co/NyxKrage/FrostMaid-10.7B-TESTING-pt
39
+
40
+ https://huggingface.co/Sao10K/Frostwind-10.7B-v1
41
+
42
+ https://github.com/cg123/mergekit/tree/main
Snow_Lotus_Logo.png ADDED

Git LFS Details

  • SHA256: 704f462da62d612645fc2e7c5b284826f49608dc8880bcfe3d7a649a9551e54f
  • Pointer size: 132 Bytes
  • Size of remote file: 5.33 MB
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./FrostNymph",
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": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": false,
27
+ "vocab_size": 32000
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: ./FrostNymph
3
+ merge_method: passthrough
4
+ parameters:
5
+ normalize: true
6
+ int8_mask: true
7
+ dtype: float16
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}
output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5499ff9ff87aad6de0fc4fb2351f31e1c5bfc539d2cb6d0e70e18aa226d915
3
+ size 8588625672
output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a004859f367a5b299f2da713614fe3b316c24dca6935f1786c3641c0aee11ffd
3
+ size 2279974904
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "trust_remote_code": false,
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true,
43
+ "use_fast": true
44
+ }