初始化项目，由ModelHub XC社区提供模型
Model: bitsydarel/road-freight-voice-assistant-350m Source: Original Platform
This commit is contained in:
ModelHub XC
2
.gitattributes
vendored
Normal file
2
.gitattributes
vendored
Normal file
@@ -0,0 +1,2 @@
|
||||
*.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
14
.hfignore
Normal file
14
.hfignore
Normal file
@@ -0,0 +1,14 @@
|
||||
# Local-only training and evaluation artifacts.
|
||||
.gitignore
|
||||
.DS_Store
|
||||
*.shortconv-fixed.gguf
|
||||
*.bdai-managed
|
||||
000*_adapters.safetensors
|
||||
adapters.safetensors
|
||||
adapter_config.json
|
||||
eval-q4-server/
|
||||
train.log
|
||||
training.manifest.json
|
||||
fused/layout.manifest.json
|
||||
fused/README.md
|
||||
fused/.bdai-managed
|
||||
3
Q4_K_M.gguf
Normal file
3
Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:210ee54d519e086d09c4b4fecd17a3274f9c77e9986f7555019753b123abd72e
|
||||
size 229312288
|
||||
3
Q4_K_S.gguf
Normal file
3
Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4342a9816550aa8539c71043b5868594d3647f6de0d42c467b9360d3ac68651c
|
||||
size 220751648
|
||||
3
Q5_K_M.gguf
Normal file
3
Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2ddd626da71d7c914b89311926c0b468f2b461a49ef7978cef888a9a77432308
|
||||
size 260376352
|
||||
3
Q5_K_S.gguf
Normal file
3
Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:90c4bb17d14d52561166aaf155e470d161ad864754aed621f058afb11f5839c4
|
||||
size 255223584
|
||||
3
Q6_K.gguf
Normal file
3
Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e5652871ef30d90db9496990b4cea71e884d20acec61cded7ed3b555915c3d69
|
||||
size 293381920
|
||||
3
Q8_0.gguf
Normal file
3
Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:38d0000eb8a82cb0edb751a6ebb423453f921e1b9f662d9da140bd1b03bcbab8
|
||||
size 379217696
|
||||
79
README.md
Normal file
79
README.md
Normal file
@@ -0,0 +1,79 @@
|
||||
---
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
base_model: LiquidAI/LFM2.5-350M
|
||||
license: other
|
||||
license_name: lfm1.0
|
||||
license_link: https://huggingface.co/LiquidAI/LFM2.5-350M/blob/main/LICENSE
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- gguf
|
||||
- voice-assistant
|
||||
- tool-calling
|
||||
- road-freight
|
||||
- 350m
|
||||
---
|
||||
|
||||
# Road Freight Voice Assistant 350M
|
||||
|
||||
Fine-tuned 350M model for road-freight voice workflows in mobile apps. It is
|
||||
built for app tasks like navigation, load search, quoting, form repair,
|
||||
instruction following, and skill selection.
|
||||
|
||||
## Intended use
|
||||
|
||||
Use this model inside a road-freight app, with the app supplying its tool
|
||||
definitions, current screen state, and confirmation rules. It is not a
|
||||
standalone assistant, route planner, pricing authority, or live operations
|
||||
record.
|
||||
|
||||
Give the model live app state: available vehicles, load cards, load details,
|
||||
quote state, current location, and whether the driver has confirmed an action.
|
||||
The app still validates every tool call and keeps final submission behind its
|
||||
own confirmation checks.
|
||||
|
||||
## Quick start
|
||||
|
||||
For the BDAIAssistant SDK, use the `.small` model family. The SDK defaults
|
||||
that family to `Q4_K_M.gguf`, the recommended mobile file.
|
||||
|
||||
```swift
|
||||
let spec = Lfm25GgufFileSpecification(family: .small, variant: .q4km)
|
||||
let path = try await Lfm25LlamaCppLLMDownloader().downloadGgufFile(spec)
|
||||
```
|
||||
|
||||
To download the GGUF directly:
|
||||
|
||||
```bash
|
||||
hf download bitsydarel/road-freight-voice-assistant-350m Q4_K_M.gguf
|
||||
```
|
||||
|
||||
## Files
|
||||
|
||||
- `fused/`: Hugging Face-format fused model.
|
||||
- `model.gguf`: F16 GGUF exported from the fused model.
|
||||
- `Q8_0.gguf`, `Q6_K.gguf`, `Q5_K_M.gguf`, `Q5_K_S.gguf`,
|
||||
`Q4_K_M.gguf`, `Q4_K_S.gguf`: available GGUF quantizations.
|
||||
- `quantization.manifest.json`: SHA-256 hashes and tensor-contract validation
|
||||
results for the GGUF files.
|
||||
|
||||
For mobile deployments, start with `Q4_K_M.gguf` if the package size works for
|
||||
your app. Use `Q4_K_S.gguf` when size matters more. Keep `Q8_0.gguf` for
|
||||
comparison checks, and use `model.gguf` if you need to re-export or quantize
|
||||
again.
|
||||
|
||||
This release does not publish `BF16.gguf` or `Q4_0.gguf`. The BDAIAssistant
|
||||
SDK treats those variants as unavailable for the `.small` family and fails
|
||||
before trying to download them.
|
||||
|
||||
## Validation
|
||||
|
||||
The GGUF files listed above were regenerated from the fused model and passed
|
||||
the runtime tensor contract checks, including rank-2 shortconv tensors and
|
||||
token embedding dimensions.
|
||||
|
||||
## License and base model
|
||||
|
||||
This release is a fine-tune of `LiquidAI/LFM2.5-350M` and follows the upstream
|
||||
`lfm1.0` license linked in the repository metadata.
|
||||
64
fused/chat_template.jinja
Normal file
64
fused/chat_template.jinja
Normal file
@@ -0,0 +1,64 @@
|
||||
{{- bos_token -}}
|
||||
{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
|
||||
{%- set ns = namespace(system_prompt="") -%}
|
||||
{%- if messages[0]["role"] == "system" -%}
|
||||
{%- set sys_content = messages[0]["content"] -%}
|
||||
{%- if sys_content is not string -%}
|
||||
{%- for item in sys_content -%}
|
||||
{%- if item["type"] == "text" -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + item["text"] -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- else -%}
|
||||
{%- set ns.system_prompt = sys_content -%}
|
||||
{%- endif -%}
|
||||
{%- set messages = messages[1:] -%}
|
||||
{%- endif -%}
|
||||
{%- if tools -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
|
||||
{%- for tool in tools -%}
|
||||
{%- if tool is not string -%}
|
||||
{%- set tool = tool | tojson -%}
|
||||
{%- endif -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + tool -%}
|
||||
{%- if not loop.last -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + "]" -%}
|
||||
{%- endif -%}
|
||||
{%- if ns.system_prompt -%}
|
||||
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
|
||||
{%- endif -%}
|
||||
{%- set ns.last_assistant_index = -1 -%}
|
||||
{%- for message in messages -%}
|
||||
{%- if message["role"] == "assistant" -%}
|
||||
{%- set ns.last_assistant_index = loop.index0 -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- for message in messages -%}
|
||||
{{- "<|im_start|>" + message["role"] + "\n" -}}
|
||||
{%- set content = message["content"] -%}
|
||||
{%- if content is not string -%}
|
||||
{%- set ns.content = "" -%}
|
||||
{%- for item in content -%}
|
||||
{%- if item["type"] == "image" -%}
|
||||
{%- set ns.content = ns.content + "<image>" -%}
|
||||
{%- elif item["type"] == "text" -%}
|
||||
{%- set ns.content = ns.content + item["text"] -%}
|
||||
{%- else -%}
|
||||
{%- set ns.content = ns.content + item | tojson -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- set content = ns.content -%}
|
||||
{%- endif -%}
|
||||
{%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
|
||||
{%- if "</think>" in content -%}
|
||||
{%- set content = content.split("</think>")[-1] | trim -%}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{{- content + "<|im_end|>\n" -}}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{{- "<|im_start|>assistant\n" -}}
|
||||
{%- endif -%}
|
||||
60
fused/config.json
Normal file
60
fused/config.json
Normal file
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Lfm2ForCausalLM"
|
||||
],
|
||||
"block_auto_adjust_ff_dim": true,
|
||||
"block_dim": 1024,
|
||||
"block_ff_dim": 6656,
|
||||
"block_ffn_dim_multiplier": 1.0,
|
||||
"block_mlp_init_scale": 1.0,
|
||||
"block_multiple_of": 256,
|
||||
"block_norm_eps": 1e-05,
|
||||
"block_out_init_scale": 1.0,
|
||||
"block_use_swiglu": true,
|
||||
"block_use_xavier_init": true,
|
||||
"bos_token_id": 1,
|
||||
"conv_L_cache": 3,
|
||||
"conv_bias": false,
|
||||
"conv_dim": 1024,
|
||||
"conv_use_xavier_init": true,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 7,
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6656,
|
||||
"layer_types": [
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv"
|
||||
],
|
||||
"max_position_embeddings": 128000,
|
||||
"model_type": "lfm2",
|
||||
"norm_eps": 1e-05,
|
||||
"num_attention_heads": 16,
|
||||
"num_heads": 16,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_embedding": true,
|
||||
"transformers_version": "5.0.0rc1",
|
||||
"use_cache": true,
|
||||
"use_pos_enc": true,
|
||||
"vocab_size": 65536
|
||||
}
|
||||
7
fused/generation_config.json
Normal file
7
fused/generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 7,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.0.0rc1"
|
||||
}
|
||||
3
fused/model.safetensors
Normal file
3
fused/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:55a67ef4e3c3fc683d6a8a3ffd71939ea6f6f2452098eba0ef1d763a95ed6e76
|
||||
size 708984464
|
||||
156
fused/model.safetensors.index.json
Normal file
156
fused/model.safetensors.index.json
Normal file
@@ -0,0 +1,156 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 708967936,
|
||||
"total_parameters": 354483968
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model.safetensors",
|
||||
"model.embedding_norm.weight": "model.safetensors",
|
||||
"model.layers.0.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.0.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.0.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.0.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.0.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.0.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.0.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.0.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.1.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.1.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.1.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.1.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.1.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.1.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.1.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.1.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.10.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.10.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.10.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.10.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.10.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.out_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.11.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.11.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.11.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.11.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.11.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.11.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.11.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.11.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.12.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.12.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.12.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.12.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.12.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.out_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.13.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.13.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.13.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.13.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.13.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.13.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.13.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.13.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.14.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.14.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.14.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.14.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.14.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.out_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.15.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.15.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.15.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.15.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.15.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.15.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.15.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.15.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.2.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.2.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.2.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.2.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.2.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.out_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.3.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.3.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.3.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.3.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.3.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.3.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.3.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.3.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.4.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.4.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.4.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.4.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.4.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.4.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.4.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.4.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.5.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.5.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.5.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.5.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.5.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.out_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.6.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.6.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.6.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.6.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.6.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.6.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.6.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.6.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.7.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.7.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.7.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.7.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.7.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.7.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.7.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.7.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.8.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.8.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.8.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.8.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.8.operator_norm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.out_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.9.conv.conv.weight": "model.safetensors",
|
||||
"model.layers.9.conv.in_proj.weight": "model.safetensors",
|
||||
"model.layers.9.conv.out_proj.weight": "model.safetensors",
|
||||
"model.layers.9.feed_forward.w1.weight": "model.safetensors",
|
||||
"model.layers.9.feed_forward.w2.weight": "model.safetensors",
|
||||
"model.layers.9.feed_forward.w3.weight": "model.safetensors",
|
||||
"model.layers.9.ffn_norm.weight": "model.safetensors",
|
||||
"model.layers.9.operator_norm.weight": "model.safetensors"
|
||||
}
|
||||
}
|
||||
323830
fused/tokenizer.json
Normal file
323830
fused/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
22
fused/tokenizer_config.json
Normal file
22
fused/tokenizer_config.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|startoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"extra_special_tokens": [],
|
||||
"is_local": true,
|
||||
"legacy": false,
|
||||
"local_files_only": false,
|
||||
"model_input_names": [
|
||||
"input_ids",
|
||||
"attention_mask"
|
||||
],
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"model_specific_special_tokens": {},
|
||||
"pad_token": "<|pad|>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
3
model.gguf
Normal file
3
model.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cfde079e598a89d9c2a56c547bb6a754285c4b3ee8ec692b30ed7bae9042b872
|
||||
size 711485216
|
||||
97
quantization.manifest.json
Normal file
97
quantization.manifest.json
Normal file
@@ -0,0 +1,97 @@
|
||||
{
|
||||
"run_id": "2026-05-13T08:33:18Z-043b17",
|
||||
"rungs": [
|
||||
{
|
||||
"contract_status": "validated",
|
||||
"contract_summary": {
|
||||
"architecture": "lfm2",
|
||||
"artifact_label": "Q4_K_M",
|
||||
"gguf_path": "/Users/darelbitsy/Projects/BDAIAssistant/fine_tuning/out/teg-lfm25-sft-r8-quantized-iter3000/Q4_K_M.gguf",
|
||||
"metadata_fixes": [],
|
||||
"sha256": "210ee54d519e086d09c4b4fecd17a3274f9c77e9986f7555019753b123abd72e",
|
||||
"status": "validated",
|
||||
"tensor_checks": [
|
||||
"lfm2.shortconv.conv.weight",
|
||||
"token_embd.weight"
|
||||
],
|
||||
"tensor_count": 148,
|
||||
"tokenizer_checks": [
|
||||
"tokenizer.chat_template",
|
||||
"tokenizer.ggml.add_bos_token"
|
||||
]
|
||||
},
|
||||
"gguf_path": "/Users/darelbitsy/Projects/BDAIAssistant/fine_tuning/out/teg-lfm25-sft-r8-quantized-iter3000/Q4_K_M.gguf",
|
||||
"gguf_sha256": "210ee54d519e086d09c4b4fecd17a3274f9c77e9986f7555019753b123abd72e",
|
||||
"llama_quantize_type": "Q4_K_M",
|
||||
"llama_quantize_version": "553 (63d93d1)",
|
||||
"max_size_ratio": 0.38,
|
||||
"name": "Q4_K_M",
|
||||
"quantized_bytes": 229312288,
|
||||
"size_ratio": 0.3223008473587173,
|
||||
"source_bytes": 711485216,
|
||||
"source_sha256": "1131fc8b97daf84ef11a44a3d491be7a03065695d982d0ffcbf1f75d0190276b"
|
||||
},
|
||||
{
|
||||
"contract_status": "validated",
|
||||
"contract_summary": {
|
||||
"architecture": "lfm2",
|
||||
"artifact_label": "Q5_K_M",
|
||||
"gguf_path": "/Users/darelbitsy/Projects/BDAIAssistant/fine_tuning/out/teg-lfm25-sft-r8-quantized-iter3000/Q5_K_M.gguf",
|
||||
"metadata_fixes": [],
|
||||
"sha256": "2ddd626da71d7c914b89311926c0b468f2b461a49ef7978cef888a9a77432308",
|
||||
"status": "validated",
|
||||
"tensor_checks": [
|
||||
"lfm2.shortconv.conv.weight",
|
||||
"token_embd.weight"
|
||||
],
|
||||
"tensor_count": 148,
|
||||
"tokenizer_checks": [
|
||||
"tokenizer.chat_template",
|
||||
"tokenizer.ggml.add_bos_token"
|
||||
]
|
||||
},
|
||||
"gguf_path": "/Users/darelbitsy/Projects/BDAIAssistant/fine_tuning/out/teg-lfm25-sft-r8-quantized-iter3000/Q5_K_M.gguf",
|
||||
"gguf_sha256": "2ddd626da71d7c914b89311926c0b468f2b461a49ef7978cef888a9a77432308",
|
||||
"llama_quantize_type": "Q5_K_M",
|
||||
"llama_quantize_version": "553 (63d93d1)",
|
||||
"max_size_ratio": 0.45,
|
||||
"name": "Q5_K_M",
|
||||
"quantized_bytes": 260376352,
|
||||
"size_ratio": 0.3659617180295704,
|
||||
"source_bytes": 711485216,
|
||||
"source_sha256": "1131fc8b97daf84ef11a44a3d491be7a03065695d982d0ffcbf1f75d0190276b"
|
||||
},
|
||||
{
|
||||
"contract_status": "validated",
|
||||
"contract_summary": {
|
||||
"architecture": "lfm2",
|
||||
"artifact_label": "Q8_0",
|
||||
"gguf_path": "/Users/darelbitsy/Projects/BDAIAssistant/fine_tuning/out/teg-lfm25-sft-r8-quantized-iter3000/Q8_0.gguf",
|
||||
"metadata_fixes": [],
|
||||
"sha256": "38d0000eb8a82cb0edb751a6ebb423453f921e1b9f662d9da140bd1b03bcbab8",
|
||||
"status": "validated",
|
||||
"tensor_checks": [
|
||||
"lfm2.shortconv.conv.weight",
|
||||
"token_embd.weight"
|
||||
],
|
||||
"tensor_count": 148,
|
||||
"tokenizer_checks": [
|
||||
"tokenizer.chat_template",
|
||||
"tokenizer.ggml.add_bos_token"
|
||||
]
|
||||
},
|
||||
"gguf_path": "/Users/darelbitsy/Projects/BDAIAssistant/fine_tuning/out/teg-lfm25-sft-r8-quantized-iter3000/Q8_0.gguf",
|
||||
"gguf_sha256": "38d0000eb8a82cb0edb751a6ebb423453f921e1b9f662d9da140bd1b03bcbab8",
|
||||
"llama_quantize_type": "Q8_0",
|
||||
"llama_quantize_version": "553 (63d93d1)",
|
||||
"max_size_ratio": 0.6,
|
||||
"name": "Q8_0",
|
||||
"quantized_bytes": 379217696,
|
||||
"size_ratio": 0.5329944845965711,
|
||||
"source_bytes": 711485216,
|
||||
"source_sha256": "1131fc8b97daf84ef11a44a3d491be7a03065695d982d0ffcbf1f75d0190276b"
|
||||
}
|
||||
],
|
||||
"schema_version": "1.2",
|
||||
"source_gguf": "/Users/darelbitsy/Projects/BDAIAssistant/fine_tuning/out/teg-lfm25-sft-r8-fused-iter3000/model.gguf"
|
||||
}
|
||||
Reference in New Issue
Block a user