初始化项目，由ModelHub XC社区提供模型
Model: richardyoung/OLMo-3-7B-RLZero-Math-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
41
.gitattributes
vendored
Normal file
41
.gitattributes
vendored
Normal file
@@ -0,0 +1,41 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
Olmo-3-7B-RLZero-Math-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Olmo-3-7B-RLZero-Math-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Olmo-3-7B-RLZero-Math-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Olmo-3-7B-RLZero-Math-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Olmo-3-7B-RLZero-Math-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Olmo-3-7B-RLZero-Math.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
7
MLX-4bit/README.md
Normal file
7
MLX-4bit/README.md
Normal file
@@ -0,0 +1,7 @@
|
||||
---
|
||||
language: en
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- mlx
|
||||
library_name: mlx
|
||||
---
|
||||
7
MLX-4bit/chat_template.jinja
Normal file
7
MLX-4bit/chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
Solve the following math problem step by step. The last line of your response should be the answer to the problem in form Answer: $Answer (without quotes) where $Answer is the answer to the problem.
|
||||
|
||||
{% for message in messages %}{{ '
|
||||
|
||||
' if not loop.first else '' }}{{ message['content'] + '
|
||||
' }}{% if loop.last and add_generation_prompt %}{{ '
|
||||
Remember to put your answer on its own line after "Answer:"' }}{% endif %}{% endfor %}
|
||||
78
MLX-4bit/config.json
Normal file
78
MLX-4bit/config.json
Normal file
@@ -0,0 +1,78 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Olmo3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 100257,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"layer_types": [
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 65536,
|
||||
"model_type": "olmo3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 100277,
|
||||
"quantization": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"quantization_config": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"attention_factor": 1.2079441541679836,
|
||||
"beta_fast": 32,
|
||||
"beta_slow": 1,
|
||||
"factor": 8.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "yarn"
|
||||
},
|
||||
"rope_theta": 500000,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 100278
|
||||
}
|
||||
4
MLX-4bit/generation_config.json
Normal file
4
MLX-4bit/generation_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
100001
MLX-4bit/merges.txt
Normal file
100001
MLX-4bit/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
MLX-4bit/model.safetensors
Normal file
3
MLX-4bit/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd7cc997b81bed8a9f77ee2b4e287ab60eefe07a551e7e0434635e3435785b64
|
||||
size 4105983200
|
||||
815
MLX-4bit/model.safetensors.index.json
Normal file
815
MLX-4bit/model.safetensors.index.json
Normal file
@@ -0,0 +1,815 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 4105890816,
|
||||
"total_parameters": 7298011136
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.biases": "model.safetensors",
|
||||
"lm_head.scales": "model.safetensors",
|
||||
"lm_head.weight": "model.safetensors",
|
||||
"model.embed_tokens.biases": "model.safetensors",
|
||||
"model.embed_tokens.scales": "model.safetensors",
|
||||
"model.embed_tokens.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.18.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.19.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.20.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.21.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.22.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.23.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.24.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.25.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.26.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.27.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.28.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.29.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.30.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.31.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.norm.weight": "model.safetensors"
|
||||
}
|
||||
}
|
||||
30
MLX-4bit/special_tokens_map.json
Normal file
30
MLX-4bit/special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
500524
MLX-4bit/tokenizer.json
Normal file
500524
MLX-4bit/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
189
MLX-4bit/tokenizer_config.json
Normal file
189
MLX-4bit/tokenizer_config.json
Normal file
@@ -0,0 +1,189 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"100256": {
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100257": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100258": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100259": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100260": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100261": {
|
||||
"content": "|||PHONE_NUMBER|||",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100262": {
|
||||
"content": "|||EMAIL_ADDRESS|||",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100263": {
|
||||
"content": "|||IP_ADDRESS|||",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100264": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100265": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100266": {
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100267": {
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100268": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100269": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100270": {
|
||||
"content": "<functions>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100271": {
|
||||
"content": "</functions>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100272": {
|
||||
"content": "<function_calls>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100273": {
|
||||
"content": "</function_calls>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100274": {
|
||||
"content": "<answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100275": {
|
||||
"content": "</answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100276": {
|
||||
"content": "<|endofprompt|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100277": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|pad|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
1
MLX-4bit/vocab.json
Normal file
1
MLX-4bit/vocab.json
Normal file
File diff suppressed because one or more lines are too long
3
Olmo-3-7B-RLZero-Math-IQ3_M.gguf
Normal file
3
Olmo-3-7B-RLZero-Math-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4649beef37db6302d6bc0a4ef9687d3a8866b161b246716faec66509da27314e
|
||||
size 3468316416
|
||||
3
Olmo-3-7B-RLZero-Math-IQ4_XS.gguf
Normal file
3
Olmo-3-7B-RLZero-Math-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6111fcc049d07855928f2df9690d08c032508f56116593ab386f69c55f69b871
|
||||
size 4029372096
|
||||
3
Olmo-3-7B-RLZero-Math-Q4_K_M.gguf
Normal file
3
Olmo-3-7B-RLZero-Math-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1431d5bb2f91df9cdda948299172d83d4db30e3a0e446d7a1ea90ac86c4f86fb
|
||||
size 4471599552
|
||||
3
Olmo-3-7B-RLZero-Math-Q5_K_M.gguf
Normal file
3
Olmo-3-7B-RLZero-Math-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:81d0985c540af178a88e052f64da6d4b90e490d0c63e3a937106f66a553d9f4f
|
||||
size 5208710592
|
||||
3
Olmo-3-7B-RLZero-Math-Q8_0.gguf
Normal file
3
Olmo-3-7B-RLZero-Math-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f6107e85c6c4242cfa78363ec97c60ea3fc06756f4a8fa16515e47728f22a65f
|
||||
size 7759250176
|
||||
3
Olmo-3-7B-RLZero-Math.gguf
Normal file
3
Olmo-3-7B-RLZero-Math.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c5991445e332d5557b0c93edf6c1829d2ed2eaad8c4e0686824c07f2dbe9b9a
|
||||
size 14600640256
|
||||
139
README.md
Normal file
139
README.md
Normal file
@@ -0,0 +1,139 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: allenai/OLMo-3-7B-RLZero-Math
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- gguf
|
||||
- mlx
|
||||
- ollama
|
||||
- math
|
||||
- reasoning
|
||||
- olmo
|
||||
- quantized
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# OLMo-3-7B-RLZero-Math GGUF
|
||||
|
||||
> **GGUF & MLX quantizations** of Allen Institute for AI's mathematical reasoning model, optimized for local inference with llama.cpp, Ollama, and Apple Silicon.
|
||||
|
||||
## Highlights
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| **Math Specialist** | Fine-tuned with RL-Zero for step-by-step mathematical reasoning |
|
||||
| **65K Context** | 65,536 token context window with YaRN scaling |
|
||||
| **Apple Silicon Ready** | MLX-optimized 4-bit quantization included |
|
||||
| **Runs Anywhere** | From 4GB RAM to full precision |
|
||||
|
||||
## Model Specifications
|
||||
|
||||
| Property | Value |
|
||||
|----------|-------|
|
||||
| **Parameters** | 7 billion |
|
||||
| **Architecture** | OLMo2 |
|
||||
| **Context Length** | 65,536 tokens |
|
||||
| **Training** | RL-Zero mathematical reasoning |
|
||||
| **License** | Apache 2.0 |
|
||||
|
||||
## Available Versions
|
||||
|
||||
### GGUF Quantizations
|
||||
|
||||
| Quantization | Size | Quality | Use Case |
|
||||
|--------------|------|---------|----------|
|
||||
| `F16` | 14 GB | Near-perfect | Maximum quality, research |
|
||||
| `Q8_0` | 7.2 GB | Excellent | Near-lossless, high-end hardware |
|
||||
| `Q5_K_M` | 4.9 GB | Very Good | Excellent quality/size balance |
|
||||
| `Q4_K_M` | 4.2 GB | Good | **Recommended** for most users |
|
||||
| `IQ4_XS` | 3.8 GB | Good | Compact 4-bit |
|
||||
| `IQ3_M` | 3.2 GB | Acceptable | Ultra-compact, constrained devices |
|
||||
|
||||
### MLX (Apple Silicon)
|
||||
|
||||
4-bit quantized version in `MLX-4bit/` folder - optimized for M1/M2/M3/M4 Macs.
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Ollama (Easiest)
|
||||
|
||||
```bash
|
||||
ollama run richardyoung/olmo-3-7b-rlzero-math
|
||||
```
|
||||
|
||||
### llama.cpp
|
||||
|
||||
```bash
|
||||
# Download Q4_K_M (recommended)
|
||||
wget https://huggingface.co/richardyoung/OLMo-3-7B-RLZero-Math-GGUF/resolve/main/Olmo-3-7B-RLZero-Math-Q4_K_M.gguf
|
||||
|
||||
# Run inference
|
||||
./llama-cli -m Olmo-3-7B-RLZero-Math-Q4_K_M.gguf \
|
||||
-p "Solve step by step: What is 15% of 240?" \
|
||||
-n 512
|
||||
```
|
||||
|
||||
### MLX (Apple Silicon)
|
||||
|
||||
```bash
|
||||
pip install mlx-lm
|
||||
|
||||
mlx_lm.generate \
|
||||
--model richardyoung/OLMo-3-7B-RLZero-Math-GGUF \
|
||||
--prompt "Solve: Find the derivative of x^3 + 2x" \
|
||||
--trust-remote-code
|
||||
```
|
||||
|
||||
### Python
|
||||
|
||||
```python
|
||||
from llama_cpp import Llama
|
||||
|
||||
llm = Llama(
|
||||
model_path="Olmo-3-7B-RLZero-Math-Q4_K_M.gguf",
|
||||
n_ctx=4096
|
||||
)
|
||||
|
||||
output = llm(
|
||||
"Solve step by step: What is the sum of the first 10 prime numbers?",
|
||||
max_tokens=512
|
||||
)
|
||||
print(output["choices"][0]["text"])
|
||||
```
|
||||
|
||||
## System Requirements
|
||||
|
||||
| Quantization | Min RAM | Recommended | Apple Silicon |
|
||||
|--------------|---------|-------------|---------------|
|
||||
| IQ3_M | 4 GB | 8 GB | M1 8GB |
|
||||
| IQ4_XS / Q4_K_M | 6 GB | 12 GB | M1 8GB |
|
||||
| Q5_K_M / Q8_0 | 8 GB | 16 GB | M1 16GB |
|
||||
| F16 | 16 GB | 24 GB | M2 Pro+ |
|
||||
|
||||
## Prompt Format
|
||||
|
||||
```
|
||||
Solve the following math problem step by step:
|
||||
{your problem here}
|
||||
```
|
||||
|
||||
**Example:**
|
||||
```
|
||||
Solve the following math problem step by step:
|
||||
A train travels 120 miles in 2 hours. If it continues at the same speed,
|
||||
how long will it take to travel 300 miles?
|
||||
```
|
||||
|
||||
## Links
|
||||
|
||||
| Resource | Link |
|
||||
|----------|------|
|
||||
| **Original Model** | [allenai/OLMo-3-7B-RLZero-Math](https://huggingface.co/allenai/OLMo-3-7B-RLZero-Math) |
|
||||
| **Ollama** | [richardyoung/olmo-3-7b-rlzero-math](https://ollama.com/richardyoung/olmo-3-7b-rlzero-math) |
|
||||
| **Allen AI** | [allenai.org](https://allenai.org/) |
|
||||
|
||||
---
|
||||
|
||||
**Quantization by** [Richard Young](https://huggingface.co/richardyoung) | **Original model by** [Allen Institute for AI](https://allenai.org/)
|
||||
7
mlx/README.md
Normal file
7
mlx/README.md
Normal file
@@ -0,0 +1,7 @@
|
||||
---
|
||||
language: en
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- mlx
|
||||
library_name: mlx
|
||||
---
|
||||
7
mlx/chat_template.jinja
Normal file
7
mlx/chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
Solve the following math problem step by step. The last line of your response should be the answer to the problem in form Answer: $Answer (without quotes) where $Answer is the answer to the problem.
|
||||
|
||||
{% for message in messages %}{{ '
|
||||
|
||||
' if not loop.first else '' }}{{ message['content'] + '
|
||||
' }}{% if loop.last and add_generation_prompt %}{{ '
|
||||
Remember to put your answer on its own line after "Answer:"' }}{% endif %}{% endfor %}
|
||||
78
mlx/config.json
Normal file
78
mlx/config.json
Normal file
@@ -0,0 +1,78 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Olmo3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 100257,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"layer_types": [
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 65536,
|
||||
"model_type": "olmo3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 100277,
|
||||
"quantization": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"quantization_config": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"attention_factor": 1.2079441541679836,
|
||||
"beta_fast": 32,
|
||||
"beta_slow": 1,
|
||||
"factor": 8.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "yarn"
|
||||
},
|
||||
"rope_theta": 500000,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 100278
|
||||
}
|
||||
4
mlx/generation_config.json
Normal file
4
mlx/generation_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
100001
mlx/merges.txt
Normal file
100001
mlx/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
mlx/model.safetensors
Normal file
3
mlx/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd7cc997b81bed8a9f77ee2b4e287ab60eefe07a551e7e0434635e3435785b64
|
||||
size 4105983200
|
||||
815
mlx/model.safetensors.index.json
Normal file
815
mlx/model.safetensors.index.json
Normal file
@@ -0,0 +1,815 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 4105890816,
|
||||
"total_parameters": 7298011136
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.biases": "model.safetensors",
|
||||
"lm_head.scales": "model.safetensors",
|
||||
"lm_head.weight": "model.safetensors",
|
||||
"model.embed_tokens.biases": "model.safetensors",
|
||||
"model.embed_tokens.scales": "model.safetensors",
|
||||
"model.embed_tokens.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.18.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.19.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.20.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.21.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.22.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.23.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.24.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.25.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.26.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.27.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.28.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.29.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.30.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.31.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.norm.weight": "model.safetensors"
|
||||
}
|
||||
}
|
||||
30
mlx/special_tokens_map.json
Normal file
30
mlx/special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
500524
mlx/tokenizer.json
Normal file
500524
mlx/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
189
mlx/tokenizer_config.json
Normal file
189
mlx/tokenizer_config.json
Normal file
@@ -0,0 +1,189 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"100256": {
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100257": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100258": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100259": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100260": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100261": {
|
||||
"content": "|||PHONE_NUMBER|||",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100262": {
|
||||
"content": "|||EMAIL_ADDRESS|||",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100263": {
|
||||
"content": "|||IP_ADDRESS|||",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100264": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100265": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100266": {
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100267": {
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100268": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100269": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100270": {
|
||||
"content": "<functions>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100271": {
|
||||
"content": "</functions>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100272": {
|
||||
"content": "<function_calls>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100273": {
|
||||
"content": "</function_calls>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100274": {
|
||||
"content": "<answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100275": {
|
||||
"content": "</answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"100276": {
|
||||
"content": "<|endofprompt|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100277": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|pad|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
1
mlx/vocab.json
Normal file
1
mlx/vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user