Upload folder using huggingface_hub
Browse files- Modelfile +4 -8
- chat_template.jinja +3 -85
- config.json +44 -46
- generation_config.json +1 -4
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +357 -400
- tokenizer.json +2 -2
- tokenizer_config.json +5 -20
Modelfile
CHANGED
|
@@ -2,13 +2,9 @@
|
|
| 2 |
|
| 3 |
FROM .
|
| 4 |
|
| 5 |
-
TEMPLATE """{{ if .System }}<|
|
| 6 |
-
{{ .
|
| 7 |
-
{{
|
| 8 |
-
{{ .Content }}<|im_end|>
|
| 9 |
-
<|im_start|>assistant
|
| 10 |
-
{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
|
| 11 |
-
{{ end }}{{ end }}"""
|
| 12 |
|
| 13 |
-
PARAMETER stop "<|
|
| 14 |
PARAMETER num_ctx 4096
|
|
|
|
| 2 |
|
| 3 |
FROM .
|
| 4 |
|
| 5 |
+
TEMPLATE """<|endoftext|>{{ if .System }}{{ .System }}{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|user|>
|
| 6 |
+
{{ .Content }}<|assistant|>
|
| 7 |
+
{{ else if eq .Role "assistant" }}{{ .Content }}<|endoftext|>{{ end }}{{ end }}"""
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
+
PARAMETER stop "<|endoftext|>"
|
| 10 |
PARAMETER num_ctx 4096
|
chat_template.jinja
CHANGED
|
@@ -1,85 +1,3 @@
|
|
| 1 |
-
{%
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
-
{%- for message in messages[::-1] %}
|
| 19 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
-
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
-
{%- set ns.multi_step_tool = false %}
|
| 22 |
-
{%- set ns.last_query_index = index %}
|
| 23 |
-
{%- endif %}
|
| 24 |
-
{%- endfor %}
|
| 25 |
-
{%- for message in messages %}
|
| 26 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
-
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
-
{%- elif message.role == "assistant" %}
|
| 29 |
-
{%- set content = message.content %}
|
| 30 |
-
{%- set reasoning_content = '' %}
|
| 31 |
-
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
-
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
-
{%- else %}
|
| 34 |
-
{%- if '</think>' in message.content %}
|
| 35 |
-
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
-
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
-
{%- endif %}
|
| 38 |
-
{%- endif %}
|
| 39 |
-
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
-
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
-
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
-
{%- else %}
|
| 43 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
-
{%- endif %}
|
| 45 |
-
{%- else %}
|
| 46 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
-
{%- endif %}
|
| 48 |
-
{%- if message.tool_calls %}
|
| 49 |
-
{%- for tool_call in message.tool_calls %}
|
| 50 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
-
{{- '\n' }}
|
| 52 |
-
{%- endif %}
|
| 53 |
-
{%- if tool_call.function %}
|
| 54 |
-
{%- set tool_call = tool_call.function %}
|
| 55 |
-
{%- endif %}
|
| 56 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
-
{{- tool_call.name }}
|
| 58 |
-
{{- '", "arguments": ' }}
|
| 59 |
-
{%- if tool_call.arguments is string %}
|
| 60 |
-
{{- tool_call.arguments }}
|
| 61 |
-
{%- else %}
|
| 62 |
-
{{- tool_call.arguments | tojson }}
|
| 63 |
-
{%- endif %}
|
| 64 |
-
{{- '}\n</tool_call>' }}
|
| 65 |
-
{%- endfor %}
|
| 66 |
-
{%- endif %}
|
| 67 |
-
{{- '<|im_end|>\n' }}
|
| 68 |
-
{%- elif message.role == "tool" %}
|
| 69 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
-
{{- '<|im_start|>user' }}
|
| 71 |
-
{%- endif %}
|
| 72 |
-
{{- '\n<tool_response>\n' }}
|
| 73 |
-
{{- message.content }}
|
| 74 |
-
{{- '\n</tool_response>' }}
|
| 75 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
-
{{- '<|im_end|>\n' }}
|
| 77 |
-
{%- endif %}
|
| 78 |
-
{%- endif %}
|
| 79 |
-
{%- endfor %}
|
| 80 |
-
{%- if add_generation_prompt %}
|
| 81 |
-
{{- '<|im_start|>assistant\n' }}
|
| 82 |
-
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
-
{%- endif %}
|
| 85 |
-
{%- endif %}
|
|
|
|
| 1 |
+
{{ '<|endoftext|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>
|
| 2 |
+
' + content + '<|assistant|>
|
| 3 |
+
' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' }}{% endif %}{% endfor %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -1,71 +1,69 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id":
|
| 10 |
-
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
-
"hidden_size":
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size":
|
| 15 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
| 16 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
| 17 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
| 18 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
| 19 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
| 20 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
| 21 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
| 22 |
"full_attention",
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
"full_attention"
|
| 52 |
],
|
| 53 |
-
"max_position_embeddings":
|
| 54 |
-
"
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers":
|
| 58 |
-
"num_key_value_heads":
|
| 59 |
-
"pad_token_id":
|
| 60 |
"rms_norm_eps": 1e-06,
|
| 61 |
"rope_parameters": {
|
| 62 |
-
"
|
| 63 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
},
|
| 65 |
-
"sliding_window":
|
| 66 |
-
"tie_word_embeddings":
|
| 67 |
"transformers_version": "5.2.0",
|
| 68 |
"use_cache": true,
|
| 69 |
-
"
|
| 70 |
-
"vocab_size": 151936
|
| 71 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"Olmo3ForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
|
|
|
| 10 |
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
"layer_types": [
|
| 15 |
+
"sliding_attention",
|
| 16 |
+
"sliding_attention",
|
| 17 |
+
"sliding_attention",
|
| 18 |
"full_attention",
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"full_attention"
|
| 47 |
],
|
| 48 |
+
"max_position_embeddings": 65536,
|
| 49 |
+
"model_type": "olmo3",
|
|
|
|
| 50 |
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"pad_token_id": 100277,
|
| 54 |
"rms_norm_eps": 1e-06,
|
| 55 |
"rope_parameters": {
|
| 56 |
+
"attention_factor": 1.2079441541679836,
|
| 57 |
+
"beta_fast": 32,
|
| 58 |
+
"beta_slow": 1,
|
| 59 |
+
"factor": 8.0,
|
| 60 |
+
"original_max_position_embeddings": 8192,
|
| 61 |
+
"rope_theta": 500000,
|
| 62 |
+
"rope_type": "yarn"
|
| 63 |
},
|
| 64 |
+
"sliding_window": 4096,
|
| 65 |
+
"tie_word_embeddings": false,
|
| 66 |
"transformers_version": "5.2.0",
|
| 67 |
"use_cache": true,
|
| 68 |
+
"vocab_size": 100278
|
|
|
|
| 69 |
}
|
generation_config.json
CHANGED
|
@@ -1,7 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"do_sample": false,
|
| 4 |
-
"eos_token_id": 151643,
|
| 5 |
-
"max_new_tokens": 8192,
|
| 6 |
"transformers_version": "5.2.0"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
|
|
|
|
|
|
|
|
|
| 3 |
"transformers_version": "5.2.0"
|
| 4 |
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d25c78968454558699ad6629bfd958e45ae00942a85c70cae5e90bf49e2abb55
|
| 3 |
+
size 4971407688
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09bedc5b3fec8f149c3273238d0f87d6c2b6778b5c6ce842c9e718160db25ba3
|
| 3 |
+
size 4947590320
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d459f67c8e3e67f86dd9eff5d8b8274cc169c72c4bffb06bb2f1c26032dfd17c
|
| 3 |
+
size 4677065648
|
model.safetensors.index.json
CHANGED
|
@@ -1,406 +1,363 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters":
|
| 4 |
-
"total_size":
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
-
"
|
| 8 |
-
"model.
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
| 13 |
-
"model.layers.0.
|
| 14 |
-
"model.layers.0.self_attn.
|
| 15 |
-
"model.layers.0.self_attn.
|
| 16 |
-
"model.layers.0.self_attn.
|
| 17 |
-
"model.layers.0.self_attn.
|
| 18 |
-
"model.layers.0.self_attn.
|
| 19 |
-
"model.layers.
|
| 20 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-
|
| 21 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-
|
| 22 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-
|
| 23 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
| 24 |
-
"model.layers.1.
|
| 25 |
-
"model.layers.1.self_attn.
|
| 26 |
-
"model.layers.1.self_attn.
|
| 27 |
-
"model.layers.1.self_attn.
|
| 28 |
-
"model.layers.1.self_attn.
|
| 29 |
-
"model.layers.1.self_attn.
|
| 30 |
-
"model.layers.
|
| 31 |
-
"model.layers.10.mlp.down_proj.weight": "model-
|
| 32 |
-
"model.layers.10.mlp.gate_proj.weight": "model-
|
| 33 |
-
"model.layers.10.mlp.up_proj.weight": "model-
|
| 34 |
-
"model.layers.10.post_attention_layernorm.weight": "model-
|
| 35 |
-
"model.layers.10.
|
| 36 |
-
"model.layers.10.self_attn.
|
| 37 |
-
"model.layers.10.self_attn.
|
| 38 |
-
"model.layers.10.self_attn.
|
| 39 |
-
"model.layers.10.self_attn.
|
| 40 |
-
"model.layers.10.self_attn.
|
| 41 |
-
"model.layers.
|
| 42 |
-
"model.layers.11.mlp.down_proj.weight": "model-
|
| 43 |
-
"model.layers.11.mlp.gate_proj.weight": "model-
|
| 44 |
-
"model.layers.11.mlp.up_proj.weight": "model-
|
| 45 |
-
"model.layers.11.post_attention_layernorm.weight": "model-
|
| 46 |
-
"model.layers.11.
|
| 47 |
-
"model.layers.11.self_attn.
|
| 48 |
-
"model.layers.11.self_attn.
|
| 49 |
-
"model.layers.11.self_attn.
|
| 50 |
-
"model.layers.11.self_attn.
|
| 51 |
-
"model.layers.11.self_attn.
|
| 52 |
-
"model.layers.
|
| 53 |
-
"model.layers.12.mlp.down_proj.weight": "model-
|
| 54 |
-
"model.layers.12.mlp.gate_proj.weight": "model-
|
| 55 |
-
"model.layers.12.mlp.up_proj.weight": "model-
|
| 56 |
-
"model.layers.12.post_attention_layernorm.weight": "model-
|
| 57 |
-
"model.layers.12.
|
| 58 |
-
"model.layers.12.self_attn.
|
| 59 |
-
"model.layers.12.self_attn.
|
| 60 |
-
"model.layers.12.self_attn.
|
| 61 |
-
"model.layers.12.self_attn.
|
| 62 |
-
"model.layers.12.self_attn.
|
| 63 |
-
"model.layers.
|
| 64 |
-
"model.layers.13.mlp.down_proj.weight": "model-
|
| 65 |
-
"model.layers.13.mlp.gate_proj.weight": "model-
|
| 66 |
-
"model.layers.13.mlp.up_proj.weight": "model-
|
| 67 |
-
"model.layers.13.post_attention_layernorm.weight": "model-
|
| 68 |
-
"model.layers.13.
|
| 69 |
-
"model.layers.13.self_attn.
|
| 70 |
-
"model.layers.13.self_attn.
|
| 71 |
-
"model.layers.13.self_attn.
|
| 72 |
-
"model.layers.13.self_attn.
|
| 73 |
-
"model.layers.13.self_attn.
|
| 74 |
-
"model.layers.
|
| 75 |
-
"model.layers.14.mlp.down_proj.weight": "model-
|
| 76 |
-
"model.layers.14.mlp.gate_proj.weight": "model-
|
| 77 |
-
"model.layers.14.mlp.up_proj.weight": "model-
|
| 78 |
-
"model.layers.14.post_attention_layernorm.weight": "model-
|
| 79 |
-
"model.layers.14.
|
| 80 |
-
"model.layers.14.self_attn.
|
| 81 |
-
"model.layers.14.self_attn.
|
| 82 |
-
"model.layers.14.self_attn.
|
| 83 |
-
"model.layers.14.self_attn.
|
| 84 |
-
"model.layers.14.self_attn.
|
| 85 |
-
"model.layers.
|
| 86 |
-
"model.layers.15.mlp.down_proj.weight": "model-
|
| 87 |
-
"model.layers.15.mlp.gate_proj.weight": "model-
|
| 88 |
-
"model.layers.15.mlp.up_proj.weight": "model-
|
| 89 |
-
"model.layers.15.post_attention_layernorm.weight": "model-
|
| 90 |
-
"model.layers.15.
|
| 91 |
-
"model.layers.15.self_attn.
|
| 92 |
-
"model.layers.15.self_attn.
|
| 93 |
-
"model.layers.15.self_attn.
|
| 94 |
-
"model.layers.15.self_attn.
|
| 95 |
-
"model.layers.15.self_attn.
|
| 96 |
-
"model.layers.
|
| 97 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
| 98 |
-
"model.layers.16.mlp.gate_proj.weight": "model-
|
| 99 |
-
"model.layers.16.mlp.up_proj.weight": "model-
|
| 100 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
| 101 |
-
"model.layers.16.
|
| 102 |
-
"model.layers.16.self_attn.
|
| 103 |
-
"model.layers.16.self_attn.
|
| 104 |
-
"model.layers.16.self_attn.
|
| 105 |
-
"model.layers.16.self_attn.
|
| 106 |
-
"model.layers.16.self_attn.
|
| 107 |
-
"model.layers.
|
| 108 |
-
"model.layers.17.mlp.down_proj.weight": "model-
|
| 109 |
-
"model.layers.17.mlp.gate_proj.weight": "model-
|
| 110 |
-
"model.layers.17.mlp.up_proj.weight": "model-
|
| 111 |
-
"model.layers.17.post_attention_layernorm.weight": "model-
|
| 112 |
-
"model.layers.17.
|
| 113 |
-
"model.layers.17.self_attn.
|
| 114 |
-
"model.layers.17.self_attn.
|
| 115 |
-
"model.layers.17.self_attn.
|
| 116 |
-
"model.layers.17.self_attn.
|
| 117 |
-
"model.layers.17.self_attn.
|
| 118 |
-
"model.layers.
|
| 119 |
-
"model.layers.18.mlp.down_proj.weight": "model-
|
| 120 |
-
"model.layers.18.mlp.gate_proj.weight": "model-
|
| 121 |
-
"model.layers.18.mlp.up_proj.weight": "model-
|
| 122 |
-
"model.layers.18.post_attention_layernorm.weight": "model-
|
| 123 |
-
"model.layers.18.
|
| 124 |
-
"model.layers.18.self_attn.
|
| 125 |
-
"model.layers.18.self_attn.
|
| 126 |
-
"model.layers.18.self_attn.
|
| 127 |
-
"model.layers.18.self_attn.
|
| 128 |
-
"model.layers.18.self_attn.
|
| 129 |
-
"model.layers.
|
| 130 |
-
"model.layers.19.mlp.down_proj.weight": "model-
|
| 131 |
-
"model.layers.19.mlp.gate_proj.weight": "model-
|
| 132 |
-
"model.layers.19.mlp.up_proj.weight": "model-
|
| 133 |
-
"model.layers.19.post_attention_layernorm.weight": "model-
|
| 134 |
-
"model.layers.19.
|
| 135 |
-
"model.layers.19.self_attn.
|
| 136 |
-
"model.layers.19.self_attn.
|
| 137 |
-
"model.layers.19.self_attn.
|
| 138 |
-
"model.layers.19.self_attn.
|
| 139 |
-
"model.layers.19.self_attn.
|
| 140 |
-
"model.layers.
|
| 141 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-
|
| 142 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-
|
| 143 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-
|
| 144 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
| 145 |
-
"model.layers.2.
|
| 146 |
-
"model.layers.2.self_attn.
|
| 147 |
-
"model.layers.2.self_attn.
|
| 148 |
-
"model.layers.2.self_attn.
|
| 149 |
-
"model.layers.2.self_attn.
|
| 150 |
-
"model.layers.2.self_attn.
|
| 151 |
-
"model.layers.
|
| 152 |
-
"model.layers.20.mlp.down_proj.weight": "model-
|
| 153 |
-
"model.layers.20.mlp.gate_proj.weight": "model-
|
| 154 |
-
"model.layers.20.mlp.up_proj.weight": "model-
|
| 155 |
-
"model.layers.20.post_attention_layernorm.weight": "model-
|
| 156 |
-
"model.layers.20.
|
| 157 |
-
"model.layers.20.self_attn.
|
| 158 |
-
"model.layers.20.self_attn.
|
| 159 |
-
"model.layers.20.self_attn.
|
| 160 |
-
"model.layers.20.self_attn.
|
| 161 |
-
"model.layers.20.self_attn.
|
| 162 |
-
"model.layers.
|
| 163 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
| 164 |
-
"model.layers.21.mlp.gate_proj.weight": "model-
|
| 165 |
-
"model.layers.21.mlp.up_proj.weight": "model-
|
| 166 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
| 167 |
-
"model.layers.21.
|
| 168 |
-
"model.layers.21.self_attn.
|
| 169 |
-
"model.layers.21.self_attn.
|
| 170 |
-
"model.layers.21.self_attn.
|
| 171 |
-
"model.layers.21.self_attn.
|
| 172 |
-
"model.layers.21.self_attn.
|
| 173 |
-
"model.layers.
|
| 174 |
-
"model.layers.22.mlp.down_proj.weight": "model-
|
| 175 |
-
"model.layers.22.mlp.gate_proj.weight": "model-
|
| 176 |
-
"model.layers.22.mlp.up_proj.weight": "model-
|
| 177 |
-
"model.layers.22.post_attention_layernorm.weight": "model-
|
| 178 |
-
"model.layers.22.
|
| 179 |
-
"model.layers.22.self_attn.
|
| 180 |
-
"model.layers.22.self_attn.
|
| 181 |
-
"model.layers.22.self_attn.
|
| 182 |
-
"model.layers.22.self_attn.
|
| 183 |
-
"model.layers.22.self_attn.
|
| 184 |
-
"model.layers.
|
| 185 |
-
"model.layers.23.mlp.down_proj.weight": "model-
|
| 186 |
-
"model.layers.23.mlp.gate_proj.weight": "model-
|
| 187 |
-
"model.layers.23.mlp.up_proj.weight": "model-
|
| 188 |
-
"model.layers.23.post_attention_layernorm.weight": "model-
|
| 189 |
-
"model.layers.23.
|
| 190 |
-
"model.layers.23.self_attn.
|
| 191 |
-
"model.layers.23.self_attn.
|
| 192 |
-
"model.layers.23.self_attn.
|
| 193 |
-
"model.layers.23.self_attn.
|
| 194 |
-
"model.layers.23.self_attn.
|
| 195 |
-
"model.layers.
|
| 196 |
-
"model.layers.24.mlp.down_proj.weight": "model-
|
| 197 |
-
"model.layers.24.mlp.gate_proj.weight": "model-
|
| 198 |
-
"model.layers.24.mlp.up_proj.weight": "model-
|
| 199 |
-
"model.layers.24.post_attention_layernorm.weight": "model-
|
| 200 |
-
"model.layers.24.
|
| 201 |
-
"model.layers.24.self_attn.
|
| 202 |
-
"model.layers.24.self_attn.
|
| 203 |
-
"model.layers.24.self_attn.
|
| 204 |
-
"model.layers.24.self_attn.
|
| 205 |
-
"model.layers.24.self_attn.
|
| 206 |
-
"model.layers.
|
| 207 |
-
"model.layers.25.mlp.down_proj.weight": "model-
|
| 208 |
-
"model.layers.25.mlp.gate_proj.weight": "model-
|
| 209 |
-
"model.layers.25.mlp.up_proj.weight": "model-
|
| 210 |
-
"model.layers.25.post_attention_layernorm.weight": "model-
|
| 211 |
-
"model.layers.25.
|
| 212 |
-
"model.layers.25.self_attn.
|
| 213 |
-
"model.layers.25.self_attn.
|
| 214 |
-
"model.layers.25.self_attn.
|
| 215 |
-
"model.layers.25.self_attn.
|
| 216 |
-
"model.layers.25.self_attn.
|
| 217 |
-
"model.layers.
|
| 218 |
-
"model.layers.26.mlp.down_proj.weight": "model-
|
| 219 |
-
"model.layers.26.mlp.gate_proj.weight": "model-
|
| 220 |
-
"model.layers.26.mlp.up_proj.weight": "model-
|
| 221 |
-
"model.layers.26.post_attention_layernorm.weight": "model-
|
| 222 |
-
"model.layers.26.
|
| 223 |
-
"model.layers.26.self_attn.
|
| 224 |
-
"model.layers.26.self_attn.
|
| 225 |
-
"model.layers.26.self_attn.
|
| 226 |
-
"model.layers.26.self_attn.
|
| 227 |
-
"model.layers.26.self_attn.
|
| 228 |
-
"model.layers.
|
| 229 |
-
"model.layers.27.mlp.down_proj.weight": "model-
|
| 230 |
-
"model.layers.27.mlp.gate_proj.weight": "model-
|
| 231 |
-
"model.layers.27.mlp.up_proj.weight": "model-
|
| 232 |
-
"model.layers.27.post_attention_layernorm.weight": "model-
|
| 233 |
-
"model.layers.27.
|
| 234 |
-
"model.layers.27.self_attn.
|
| 235 |
-
"model.layers.27.self_attn.
|
| 236 |
-
"model.layers.27.self_attn.
|
| 237 |
-
"model.layers.27.self_attn.
|
| 238 |
-
"model.layers.27.self_attn.
|
| 239 |
-
"model.layers.
|
| 240 |
-
"model.layers.28.mlp.down_proj.weight": "model-
|
| 241 |
-
"model.layers.28.mlp.gate_proj.weight": "model-
|
| 242 |
-
"model.layers.28.mlp.up_proj.weight": "model-
|
| 243 |
-
"model.layers.28.post_attention_layernorm.weight": "model-
|
| 244 |
-
"model.layers.28.
|
| 245 |
-
"model.layers.28.self_attn.
|
| 246 |
-
"model.layers.28.self_attn.
|
| 247 |
-
"model.layers.28.self_attn.
|
| 248 |
-
"model.layers.28.self_attn.
|
| 249 |
-
"model.layers.28.self_attn.
|
| 250 |
-
"model.layers.
|
| 251 |
-
"model.layers.29.mlp.down_proj.weight": "model-
|
| 252 |
-
"model.layers.29.mlp.gate_proj.weight": "model-
|
| 253 |
-
"model.layers.29.mlp.up_proj.weight": "model-
|
| 254 |
-
"model.layers.29.post_attention_layernorm.weight": "model-
|
| 255 |
-
"model.layers.29.
|
| 256 |
-
"model.layers.29.self_attn.
|
| 257 |
-
"model.layers.29.self_attn.
|
| 258 |
-
"model.layers.29.self_attn.
|
| 259 |
-
"model.layers.29.self_attn.
|
| 260 |
-
"model.layers.29.self_attn.
|
| 261 |
-
"model.layers.
|
| 262 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-
|
| 263 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-
|
| 264 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-
|
| 265 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-
|
| 266 |
-
"model.layers.3.
|
| 267 |
-
"model.layers.3.self_attn.
|
| 268 |
-
"model.layers.3.self_attn.
|
| 269 |
-
"model.layers.3.self_attn.
|
| 270 |
-
"model.layers.3.self_attn.
|
| 271 |
-
"model.layers.3.self_attn.
|
| 272 |
-
"model.layers.
|
| 273 |
-
"model.layers.30.mlp.down_proj.weight": "model-
|
| 274 |
-
"model.layers.30.mlp.gate_proj.weight": "model-
|
| 275 |
-
"model.layers.30.mlp.up_proj.weight": "model-
|
| 276 |
-
"model.layers.30.post_attention_layernorm.weight": "model-
|
| 277 |
-
"model.layers.30.
|
| 278 |
-
"model.layers.30.self_attn.
|
| 279 |
-
"model.layers.30.self_attn.
|
| 280 |
-
"model.layers.30.self_attn.
|
| 281 |
-
"model.layers.30.self_attn.
|
| 282 |
-
"model.layers.30.self_attn.
|
| 283 |
-
"model.layers.
|
| 284 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
| 285 |
-
"model.layers.31.mlp.gate_proj.weight": "model-
|
| 286 |
-
"model.layers.31.mlp.up_proj.weight": "model-
|
| 287 |
-
"model.layers.31.post_attention_layernorm.weight": "model-
|
| 288 |
-
"model.layers.31.
|
| 289 |
-
"model.layers.31.self_attn.
|
| 290 |
-
"model.layers.31.self_attn.
|
| 291 |
-
"model.layers.31.self_attn.
|
| 292 |
-
"model.layers.31.self_attn.
|
| 293 |
-
"model.layers.31.self_attn.
|
| 294 |
-
"model.layers.
|
| 295 |
-
"model.layers.
|
| 296 |
-
"model.layers.
|
| 297 |
-
"model.layers.
|
| 298 |
-
"model.layers.
|
| 299 |
-
"model.layers.
|
| 300 |
-
"model.layers.
|
| 301 |
-
"model.layers.
|
| 302 |
-
"model.layers.
|
| 303 |
-
"model.layers.
|
| 304 |
-
"model.layers.
|
| 305 |
-
"model.layers.
|
| 306 |
-
"model.layers.
|
| 307 |
-
"model.layers.
|
| 308 |
-
"model.layers.
|
| 309 |
-
"model.layers.
|
| 310 |
-
"model.layers.
|
| 311 |
-
"model.layers.
|
| 312 |
-
"model.layers.
|
| 313 |
-
"model.layers.
|
| 314 |
-
"model.layers.
|
| 315 |
-
"model.layers.
|
| 316 |
-
"model.layers.
|
| 317 |
-
"model.layers.
|
| 318 |
-
"model.layers.
|
| 319 |
-
"model.layers.
|
| 320 |
-
"model.layers.
|
| 321 |
-
"model.layers.
|
| 322 |
-
"model.layers.
|
| 323 |
-
"model.layers.
|
| 324 |
-
"model.layers.
|
| 325 |
-
"model.layers.
|
| 326 |
-
"model.layers.
|
| 327 |
-
"model.layers.
|
| 328 |
-
"model.layers.
|
| 329 |
-
"model.layers.
|
| 330 |
-
"model.layers.
|
| 331 |
-
"model.layers.
|
| 332 |
-
"model.layers.
|
| 333 |
-
"model.layers.
|
| 334 |
-
"model.layers.
|
| 335 |
-
"model.layers.
|
| 336 |
-
"model.layers.
|
| 337 |
-
"model.layers.
|
| 338 |
-
"model.layers.
|
| 339 |
-
"model.layers.
|
| 340 |
-
"model.layers.
|
| 341 |
-
"model.layers.
|
| 342 |
-
"model.layers.
|
| 343 |
-
"model.layers.
|
| 344 |
-
"model.layers.
|
| 345 |
-
"model.layers.
|
| 346 |
-
"model.layers.
|
| 347 |
-
"model.layers.
|
| 348 |
-
"model.layers.
|
| 349 |
-
"model.layers.
|
| 350 |
-
"model.layers.
|
| 351 |
-
"model.layers.
|
| 352 |
-
"model.layers.
|
| 353 |
-
"model.layers.
|
| 354 |
-
"model.layers.
|
| 355 |
-
"model.layers.
|
| 356 |
-
"model.layers.
|
| 357 |
-
"model.layers.
|
| 358 |
-
"model.layers.
|
| 359 |
-
"model.layers.
|
| 360 |
-
"model.layers.
|
| 361 |
-
"model.
|
| 362 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
-
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
-
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
-
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
-
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 383 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
-
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
-
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
-
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
-
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
-
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
-
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
-
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
-
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 405 |
}
|
| 406 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_parameters": 7298011136,
|
| 4 |
+
"total_size": 14596022272
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 142 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 143 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 144 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 145 |
+
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 151 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 152 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 154 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 255 |
+
"model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 261 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 295 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 298 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 299 |
+
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 300 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 301 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 302 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 303 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 304 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 305 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 306 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 307 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 308 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 309 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 310 |
+
"model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 311 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 312 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 313 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 314 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 315 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 316 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 317 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 318 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 319 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 320 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 321 |
+
"model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 322 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 323 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 324 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 325 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 326 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 327 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 328 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 329 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 330 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 331 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 332 |
+
"model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 333 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 334 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 335 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 336 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 337 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 338 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 339 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 340 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 347 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 348 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 349 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 350 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 351 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 352 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 353 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 354 |
+
"model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 355 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 356 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 357 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 358 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 359 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 360 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 361 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 362 |
}
|
| 363 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a6b266d2726d8b67d9ababa39be46cc5617a240d15c83c30255abdbbece5d8a
|
| 3 |
+
size 7137190
|
tokenizer_config.json
CHANGED
|
@@ -3,28 +3,13 @@
|
|
| 3 |
"backend": "tokenizers",
|
| 4 |
"bos_token": null,
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|
|
| 7 |
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"<|im_start|>",
|
| 10 |
-
"<|im_end|>",
|
| 11 |
-
"<|object_ref_start|>",
|
| 12 |
-
"<|object_ref_end|>",
|
| 13 |
-
"<|box_start|>",
|
| 14 |
-
"<|box_end|>",
|
| 15 |
-
"<|quad_start|>",
|
| 16 |
-
"<|quad_end|>",
|
| 17 |
-
"<|vision_start|>",
|
| 18 |
-
"<|vision_end|>",
|
| 19 |
-
"<|vision_pad|>",
|
| 20 |
-
"<|image_pad|>",
|
| 21 |
-
"<|video_pad|>"
|
| 22 |
-
],
|
| 23 |
"is_local": false,
|
| 24 |
-
"model_max_length":
|
| 25 |
-
"pad_token": "<|
|
| 26 |
"padding_side": "left",
|
| 27 |
"split_special_tokens": false,
|
| 28 |
-
"tokenizer_class": "
|
| 29 |
-
"unk_token":
|
| 30 |
}
|
|
|
|
| 3 |
"backend": "tokenizers",
|
| 4 |
"bos_token": null,
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
"errors": "replace",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"is_local": false,
|
| 9 |
+
"model_max_length": 65536,
|
| 10 |
+
"pad_token": "<|pad|>",
|
| 11 |
"padding_side": "left",
|
| 12 |
"split_special_tokens": false,
|
| 13 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 14 |
+
"unk_token": "<|endoftext|>"
|
| 15 |
}
|