Upload trained adapter
Browse files- config.json +1 -16
- generation_config.json +1 -1
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- tokenizer_config.json +1 -1
config.json
CHANGED
@@ -22,21 +22,6 @@
|
|
22 |
"num_hidden_layers": 32,
|
23 |
"num_key_value_heads": 8,
|
24 |
"pretraining_tp": 1,
|
25 |
-
"quantization_config": {
|
26 |
-
"_load_in_4bit": true,
|
27 |
-
"_load_in_8bit": false,
|
28 |
-
"bnb_4bit_compute_dtype": "float16",
|
29 |
-
"bnb_4bit_quant_storage": "uint8",
|
30 |
-
"bnb_4bit_quant_type": "nf4",
|
31 |
-
"bnb_4bit_use_double_quant": false,
|
32 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
33 |
-
"llm_int8_has_fp16_weight": false,
|
34 |
-
"llm_int8_skip_modules": null,
|
35 |
-
"llm_int8_threshold": 6.0,
|
36 |
-
"load_in_4bit": true,
|
37 |
-
"load_in_8bit": false,
|
38 |
-
"quant_method": "bitsandbytes"
|
39 |
-
},
|
40 |
"rms_norm_eps": 1e-05,
|
41 |
"rope_scaling": {
|
42 |
"factor": 8.0,
|
@@ -48,7 +33,7 @@
|
|
48 |
"rope_theta": 500000.0,
|
49 |
"tie_word_embeddings": false,
|
50 |
"torch_dtype": "float16",
|
51 |
-
"transformers_version": "4.43.
|
52 |
"use_cache": true,
|
53 |
"vocab_size": 128256
|
54 |
}
|
|
|
22 |
"num_hidden_layers": 32,
|
23 |
"num_key_value_heads": 8,
|
24 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
"rope_scaling": {
|
27 |
"factor": 8.0,
|
|
|
33 |
"rope_theta": 500000.0,
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "float16",
|
36 |
+
"transformers_version": "4.43.3",
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 128256
|
39 |
}
|
generation_config.json
CHANGED
@@ -8,5 +8,5 @@
|
|
8 |
],
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
-
"transformers_version": "4.43.
|
12 |
}
|
|
|
8 |
],
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.43.3"
|
12 |
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46dba0bce32623252ffe91fa750623e9f6cfb97cc575a8b334dd3e94ef122970
|
3 |
+
size 4976698592
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21167f94345a2d2337bb379bd31b69736f5cd053d200f9680641a35e7f418fe5
|
3 |
+
size 4999802616
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:512302f14115b64a28aff8e218e7495e76ab2d833c38864bb2f81c03c5140e62
|
3 |
+
size 4915916080
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86c405336bfa30ef3fc79cb9322d0f4388ddeddf004ba27e307adfb7cd784e95
|
3 |
+
size 1168138808
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -2050,7 +2050,7 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"chat_template": "{% set
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"model_input_names": [
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"model_input_names": [
|