Upload 9 files
Browse files- .gitattributes +2 -0
- README.md +28 -4
- chat_template.jinja +87 -0
- config.json +32 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_loss.png +3 -0
- training_perplexity.png +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
training_loss.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
training_perplexity.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,4 +1,28 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Stentor-10M
|
| 2 |
+
|
| 3 |
+
This checkpoint was produced by the Stentor-10M training pipeline.
|
| 4 |
+
|
| 5 |
+
## Metadata
|
| 6 |
+
|
| 7 |
+
```json
|
| 8 |
+
{
|
| 9 |
+
"hidden_size": 256,
|
| 10 |
+
"intermediate_size": 1024,
|
| 11 |
+
"learning_rate": 0.0008,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"mixed_precision": "fp16",
|
| 14 |
+
"model_arch": "llama",
|
| 15 |
+
"num_attention_heads": 4,
|
| 16 |
+
"num_hidden_layers": 21,
|
| 17 |
+
"num_key_value_heads": 4,
|
| 18 |
+
"optimizer": "adamw",
|
| 19 |
+
"pad_vocab_to_multiple": 128,
|
| 20 |
+
"rope_theta": null,
|
| 21 |
+
"scheduler": "cosine",
|
| 22 |
+
"stable_ratio": 0.8,
|
| 23 |
+
"torch_compile": false,
|
| 24 |
+
"vocab_size": 32768,
|
| 25 |
+
"warmup_ratio": 0.02,
|
| 26 |
+
"weight_decay": 0.01
|
| 27 |
+
}
|
| 28 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if messages[0]["role"] == "system" %}
|
| 2 |
+
{%- set system_message = messages[0]["content"] %}
|
| 3 |
+
{%- set loop_messages = messages[1:] %}
|
| 4 |
+
{%- else %}
|
| 5 |
+
{%- set loop_messages = messages %}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{%- if not tools is defined %}
|
| 8 |
+
{%- set tools = none %}
|
| 9 |
+
{%- endif %}
|
| 10 |
+
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
| 11 |
+
|
| 12 |
+
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
| 13 |
+
{%- set ns = namespace() %}
|
| 14 |
+
{%- set ns.index = 0 %}
|
| 15 |
+
{%- for message in loop_messages %}
|
| 16 |
+
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
| 17 |
+
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
| 18 |
+
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- set ns.index = ns.index + 1 %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{%- endfor %}
|
| 23 |
+
|
| 24 |
+
{{- bos_token }}
|
| 25 |
+
{%- for message in loop_messages %}
|
| 26 |
+
{%- if message["role"] == "user" %}
|
| 27 |
+
{%- if tools is not none and (message == user_messages[-1]) %}
|
| 28 |
+
{{- "[AVAILABLE_TOOLS] [" }}
|
| 29 |
+
{%- for tool in tools %}
|
| 30 |
+
{%- set tool = tool.function %}
|
| 31 |
+
{{- '{"type": "function", "function": {' }}
|
| 32 |
+
{%- for key, val in tool.items() if key != "return" %}
|
| 33 |
+
{%- if val is string %}
|
| 34 |
+
{{- '"' + key + '": "' + val + '"' }}
|
| 35 |
+
{%- else %}
|
| 36 |
+
{{- '"' + key + '": ' + val|tojson }}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- if not loop.last %}
|
| 39 |
+
{{- ", " }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{{- "}}" }}
|
| 43 |
+
{%- if not loop.last %}
|
| 44 |
+
{{- ", " }}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- "]" }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- endfor %}
|
| 49 |
+
{{- "[/AVAILABLE_TOOLS]" }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- if loop.last and system_message is defined %}
|
| 52 |
+
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
| 53 |
+
{%- else %}
|
| 54 |
+
{{- "[INST] " + message["content"] + "[/INST]" }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- elif message.tool_calls is defined and message.tool_calls is not none %}
|
| 57 |
+
{{- "[TOOL_CALLS] [" }}
|
| 58 |
+
{%- for tool_call in message.tool_calls %}
|
| 59 |
+
{%- set out = tool_call.function|tojson %}
|
| 60 |
+
{{- out[:-1] }}
|
| 61 |
+
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
| 62 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- ', "id": "' + tool_call.id + '"}' }}
|
| 65 |
+
{%- if not loop.last %}
|
| 66 |
+
{{- ", " }}
|
| 67 |
+
{%- else %}
|
| 68 |
+
{{- "]" + eos_token }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- endfor %}
|
| 71 |
+
{%- elif message["role"] == "assistant" %}
|
| 72 |
+
{{- " " + message["content"]|trim + eos_token}}
|
| 73 |
+
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
| 74 |
+
{%- if message.content is defined and message.content.content is defined %}
|
| 75 |
+
{%- set content = message.content.content %}
|
| 76 |
+
{%- else %}
|
| 77 |
+
{%- set content = message.content %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
|
| 80 |
+
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
| 81 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
| 84 |
+
{%- else %}
|
| 85 |
+
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- endfor %}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 256,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 1024,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 4,
|
| 19 |
+
"num_hidden_layers": 21,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pad_token_id": 2,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"rope_type": "default"
|
| 27 |
+
},
|
| 28 |
+
"tie_word_embeddings": true,
|
| 29 |
+
"transformers_version": "5.2.0",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32768
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 2,
|
| 8 |
+
"transformers_version": "5.2.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cd2171cbc7fc7882408d0658847d3c4093b3a7e73e184214b2881d06165d893
|
| 3 |
+
size 121699864
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"legacy": false,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "</s>",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"spaces_between_special_tokens": false,
|
| 13 |
+
"tokenizer_class": "TokenizersBackend",
|
| 14 |
+
"unk_token": "<unk>",
|
| 15 |
+
"use_default_system_prompt": false
|
| 16 |
+
}
|
training_loss.png
ADDED
|
Git LFS Details
|
training_perplexity.png
ADDED
|
Git LFS Details
|